Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks549 from public data
- Video Question Answering via Gradually Refined Attention over Appearance and Motion840
This paper proposes an end-to-end model which gradually refines its attention over the appearance and motion features of the video using the question as guidance and demonstrates the effectiveness of the model by analyzing the refined attention weights during the question answering procedure.
- Deeply-Learned Part-Aligned Representations for Person Re-identification813
This paper proposes a simple yet effective human part-aligned representation for handling the body part misalignment problem, and shows state-of-the-art results over standard datasets, Market-1501,CUHK03, CUHK01 and VIPeR.
- ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering793
This work introduces ActivityNet-QA, a fully annotated and large scale VideoQA dataset, which consists of 58,000 QA pairs on 5,800 complex web videos derived from the popular ActivityNet dataset and explores various video representation strategies to improve videoQA performance.
- 642
- DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection538
This paper proposes a multi-task deep saliency model based on a fully convolutional neural network with global input (whole raw images) and global output (Whole saliency maps) and presents a graph Laplacian regularized nonlinear regression model for saliency refinement.
- Dynamic Network Embedding by Modeling Triadic Closure Process514
This paper presents a novel representation learning approach, DynamicTriad, to preserve both structural information and evolution patterns of a given network, and demonstrates that, compared with several state-of-the-art techniques, this approach achieves substantial gains in several application scenarios.
- 490
- Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning412
This paper proposes a new approach, namely Hierarchical Recurrent Neural Encoder (HRNE), to exploit temporal information of videos to exploit video temporal structure in a longer range by reducing the length of input information flow, and compositing multiple consecutive inputs at a higher level.
- 406
- 401
- Counterfactual Samples Synthesizing for Robust Visual Question Answering341
A model-agnostic Counterfactual Samples Synthesizing (CSS) training scheme that significantly improves both visual-explainable and question-sensitive abilities of VQA models and, in return, the performance of these models is further boosted.
- Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies309
MKR is an advanced AI representation framework for more complete intelligent functions, such as raw signal perception, feature extraction and vectorization, knowledge symbolization, and logical reasoning, and it is expected that MKR research and its applications will drive the evolution of AI 2.0 and beyond.
- Towards a new generation of artificial intelligence in China285
This Perspective briefly introduces the New Generation Artificial Intelligence Development Plan of China (2015–2030) from the point of view of the authors, a group of AI experts from academia and industry who have been involved in various stages of the plan.
- 242
- Challenges and opportunities: from big data to knowledge in AI 2.0210
It is concluded that integrating data-driven machine learning with human knowledge can effectively lead to explainable, robust, and general AI.
- A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data193
Self-entropy descent (SED) is a metric proposed to search an appropriate confidence threshold for reliable pseudo label generation without using any handcrafted labels in object detection, where completely clean labels are still unattainable.
- 193
- Ranking with local regression and global alignment for cross media retrieval191
A novel ranking algorithm, namely ranking with Local Regression and Global Alignment (LRGA), which learns a robust Laplacian matrix for data ranking and a unified objective function to globally align the local models from all the data points so that an optimal ranking value can be assigned to each data point.
- Federated unsupervised representation learning174
The federated contrastive averaging with dictionary and alignment (FedCA) algorithm, composed of two key modules: a dictionary module to aggregate the representations of samples from each client which can be shared with all clients for consistency of representation space, is adopted for local model training.
- 167
- Automatic generation of human animation based on motion programming: Virtual Humans and Social Agents165
This paper proposes a method for rendering photo-realistic animations of dynamic scenes under environment illumination in real time and makes a distinction between self-shadow and shadows cast by other objects and computes these two kinds of shadows efficiently.
- Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning156
The proposed Momentor, a Video-LLM capable of accomplishing fine-grained temporal understanding tasks, is designed and trained on Moment-10M, a large-scale video instruction dataset with segment-level instruction data, enabling it to perform segment-level reasoning and localization.
- Zero-Shot Recognition Using Dual Visual-Semantic Mapping Paths156
A novel framework for zero-shot recognition is proposed that can not only apply prior semantic knowledge to infer underlying semantic manifold in the image feature space, but also generate optimized semantic embedding space, which can enhance the transfer ability of the visual-semantic mapping to unseen classes.
- Discriminative coupled dictionary hashing for fast cross-media retrieval150
The experiments show that the DCDH and MV-DCDH outperform the state-of-the-art methods significantly on cross-media retrieval and conjecture that a balanced representation is crucial in cross- media retrieval.
- Effective multi-modal retrieval based on stacked auto-encoders150
This paper proposes an effective mapping mechanism based on deep learning (i.e., stacked auto-encoders) for multi-modal retrieval that achieves significant improvement in search accuracy over the state-of-the-art methods.
- Learning Domain Adaptive Object Detection with Probabilistic Teacher144
A simple yet effective framework, termed as Probabilistic Teacher (PT), which aims to capture the uncertainty of unlabeled target data from a gradually evolving teacher and guides the learning of a student in a mutually beneficial manner, and proposes to leverage the uncertainty-guided consistency training to promote classification adaptation and localization adaptation.
- Hallucinating faces: LPH super-resolution and neighbor reconstruction for residue compensation141
The proposed locality preserving hallucination (LPH) algorithm combines locality preserving projection (LPP) and radial basis function (RBF) regression together to hallucinate the global high-resolution face.
- 140
- HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation138
This work presents HealthGPT, a powerful Medical Large Vision-Language Model (Med-LVLM) that integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm through a novel heterogeneous low-rank adaptation technique and a tailored hierarchical visual perception approach.
- Adaptive Unsupervised Multi-view Feature Selection for Visual Concept Recognition132
An unsupervised learning method called Adaptive Unsupervised Multi-view Feature Selection (AUMFS), which combines data cluster labels prediction and adaptive multi-view visual similar graph learning into a unified framework to solve the objective function of AUMFS.
- 130
- 130
- Effective deep learning-based multi-modal retrieval122
This paper proposes a general learning objective that effectively captures both intramodal and intermodal semantic relationships of data from heterogeneous sources and proposes two learning algorithms to realize it: an unsupervised approach that uses stacked auto-encoders and requires minimum prior knowledge on the training data and a supervised approach using deep convolutional neural network and neural language model.
- Video Question Answering via Attribute-Augmented Attention Network Learning118
This paper proposes the attribute-augmented attention network learning framework that enables the joint frame-level attribute detection and unified video representation learning for video question answering and incorporates the multi-step reasoning process for the proposed attention network to further improve the performance.
- 117
- Video Question Answering via Hierarchical Spatio-Temporal Attention Networks117
The hierarchical spatio-temporal attention network is proposed for learning the joint representation of the dynamic video contents according to the given question and the multi-step reasoning process for open-ended video question answering is developed.
- 115
- 113
- 107
- Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning105
A variational cross-graph reasoning framework that explicitly decomposes video and language into multiple structured hierarchies and learns fine-grained semantic correspondence among them is proposed and empirically finds that they fail to generalize to queries with novel combinations of seen words.
- A Sequence-to-Set Network for Nested Named Entity Recognition105
A novel sequence-to-set neural network for nested NER with fixed set of learnable vectors to learn the patterns of the valuable spans and is more suitable for such unordered recognition task as it is insensitive to the label order.
- De-Biased Court’s View Generation with Causality101
A novel Attentional and Counterfactual based Natural Language Generation (AC-NLG) method, consisting of an attentional encoder and a pair of innovative counterfactual decoders, to eliminate the confounding bias in data and generate judgment-discriminative court’s views by incorporating with a synergistic judgment predictive model.
- Exploring Semantic Inter-Class Relationships (SIR) for Zero-Shot Action Recognition101
SIR is proposed to perform action recognition when no positive exemplars of that class are provided, which is often known as the zero-shot learning, which directly leverages the semantic inter-class relationships between the known and unknown actions followed by label transfer learning.
- Label Matching Semi-Supervised Object Detection97
A novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly is presented.
- Relational Knowledge Transfer for Zero-Shot Learning97
This paper reveals a novel relational knowledge transfer mechanism for ZSL, which is simple, generic and effective, and resolves the inherent semantic shift problem existing in ZSL through restoring the missing manifold structure of unseen categories via optimizing semantic mapping.
- 96
- Multi-label boosting for image annotation by structural grouping sparsity95
The proposed Multi-label Boosting by the selection of heterogeneous features with structural Grouping Sparsity (MtBGS) has better multi-label image annotation performance and leads to a quite interpretable model for image understanding.
- VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM93
The VideoRefer Suite is introduced to empower Video LLM for finer-level spatial-temporal video understanding, i.e., enabling perception and reasoning on any objects throughout the video, and comprehensively assess the spatial-temporal understanding capability of a Video LLM.
- Video Relation Detection with Spatio-Temporal Graph93
By combining the model (VRD-GCN) and the proposed association method, the framework for video relation detection achieves the best performance in the latest benchmarks and a series of ablation studies demonstrate the method's effectiveness.
- 91
- Expert finding for community-based question answering via ranking metric network learning88
This paper proposes a novel ranking metric network learning framework for expert finding by exploiting both users' relative quality rank to given questions and their social relations and develops a random-walk based learning method with recurrent neural networks forranking metric network embedding.
- 87
- 87
- 87
- 86
- Cross-media semantic representation via bi-directional learning to rank85
This paper proposes a general cross-media ranking algorithm to optimize the bi-directional listwise ranking loss with a latent space embedding, which it is called Bi- Directional Cross-Media Semantic Representation Model (Bi-CMSRM).
- Community-Based Question Answering via Heterogeneous Social Network Learning84
This paper proposes a novel framework which encodes not only the contents of question-answer(Q-A) but also the social interaction cues in the community to boost the cQA tasks and shows that leveraging the heterogeneous social information indeed achieves better performance than other state-of-the-art cZA methods.
- Cross-modal correlation learning for clustering on image-audio dataset84
This paper analyzes canonical correlation between feature matrices of images and audios during subspace mapping; then it design correlation-based similarity reinforcement for images and Audios; thirdly it implements image clustering and audio clustering with affinity propagation.
- Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets83
This paper proposes to extract time-aware shapelets by designing a two-level timing factor, and defines and construct the shapelet evolution graph, which captures how shapelets evolve over time and can be incorporated into the time series embeddings by graph embedding algorithms.
- Parallel Instance Query Network for Named Entity Recognition81
Parallel Instance Query Network (PIQN) is proposed, which sets up global and learnable instance queries to extract entities from a sentence in a parallel manner and outperforms previous state-of-the-art models.
- WorldGPT: Empowering LLM as Multimodal World Model80
WorldGPT is introduced, a generalist world model built upon Multimodal Large Language Model (MLLM) that acquires an understanding of world dynamics through analyzing millions of videos across various domains and is integrated with a novel cognitive architecture that combines memory offloading, knowledge retrieval, and context reflection.
- Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation80
This paper proposes a novel unsupervised reinforcement learning approach to learn transferable meta-skills from unannotated environments without any supervisory signals, and shows that this method learns transferable motor primitives for visual navigation.
- Exploiting temporal stability and low-rank structure for motion capture data refinement79
An efficient optimization method derived from the augmented Lagrange multiplier algorithm is presented to solve the mocap data refinement problem and a trust data detection method is introduced to improve the degree of automation for processing the entire set of the data and boost the performance.
- SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models78
This work designs a three-stage progressive training framework that establishes spatial perception through object localization, develops spatial understanding through multi-dimensional spatial tasks, and strengthens complex reasoning via reinforcement learning with verifiable rewards, and yields SpatialLadder, a 3B-parameter model that achieves state-of-the-art performance on spatial reasoning benchmarks.
- 76
- Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation73
A simple yet effective Self-Supervised Noisy Label Learning method, which injects self-supervised learning to impose the intrinsic data structure and facilitate label-denoising in the source domain pre-trained model.
- A Survey on (M)LLM-Based GUI Agents72
This survey identifies key technical challenges, including accurate element localization, effective knowledge retrieval, long-horizon planning, and safety-aware execution control, while outlining promising research directions for enhancing GUI Agents' capabilities.
- Cross-Relation Cross-Bag Attention for Distantly-Supervised Relation Extraction72
This paper proposes to conduct multi-instance learning with a novel Cross-relation Cross-bag Selective Attention (C2SA), which leads to noise-robust training for distant supervised relation extractor and employs the sentence-level selective attention to reduce the effect of noisy or mismatched sentences.
- Learning Dynamic Context Augmentation for Global Entity Linking72
A simple yet effective solution, called Dynamic Context Augmentation (DCA), for collective EL, which requires only one pass through the mentions in a document, and can cope with different local EL models as a plug-and-enhance module.
- A hierarchical clustering algorithm based on fuzzy graph connectedness72
The investigation demonstrates that the proposed algorithm for hierarchical clustering based on fuzzy graph connectedness algorithm (FHC) generates better quality clusters than traditional algorithms, and scales up well for large databases.
- 68
- GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding66
This work introduces GUI Gaussian Grounding Rewards (GUI-G2), a principled reward framework that models GUI elements as continuous Gaussian distributions across the interface plane and reveals that continuous modeling provides superior robustness to interface variations and enhanced generalization to unseen layouts.
- Learning Hybrid Behavior Patterns for Multimedia Recommendation65
A Hybrid Clustering Graph Convolutional Network (HCGCN) is proposed for multimedia recommendation that performs high-order graph convolutions inside user- item clusters and item-item clusters to capture various user behavior patterns and designs corresponding clustering losses to enhance user-item preference feedback and multimodal representation learning constraint to adjust the modality importance.
- Local and global approaches of affinity propagation clustering for large scale data65
Two variants of AP for grouping large scale data with a dense similarity matrix are presented, the local approach is partition affinity propagation (PAP) and the global method is landmark affinity propagate (LAP).
- CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction64
This paper proposes a novel contrastive instance learning (CIL) framework, which regards the initial MIL as the relational triple encoder and constraint positive pairs against negative pairs for each instance.
- Consensus Graph Representation Learning for Better Grounded Image Captioning64
The Consensus Rraph Representation Learning framework (CGRL) is proposed for GIC that incorporates a consensus representation into the grounded captioning pipeline that can capture both the correct linguistic characteristics and visual relevance, and then grounding appropriate image regions further.
- Recognizing an Action Using Its Name: A Knowledge-Based Approach64
This paper proposes an algorithm, namely adaptive multi-model rank-preserving mapping (AMRM), to train a classifier for action recognition, which is able to evaluate the relatedness of each video in the analogy pool adaptively, and has better capability to bridge the gap between visual features and the semantic information inferred from the ontology.
- Deep Learning Driven Visual Path Prediction From a Single Image64
A deep learning framework is proposed, which simultaneously performs deep feature learning for visual representation in conjunction with spatiotemporal context modeling and a unified path-planning scheme is proposed to make accurate path prediction based on the analytic results returned by the deep context models.
- A remote control training system for rat navigation in complicated environment64
The results indicated that the system worked stably and that the stimulation was effective for different types of rat behavior controls, and showed that stimulation in the whisker barrel region of rat primary somatosensory cortex acted like a cue.
- 64
- A new approach to retrieve video by example video clip64
A new video similarity model is proposed that embodies the degree of similarity completely and systematically and has resolution adaptation because it can be applied to every level of video structure.
- Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World63
A Cross-modal prediCate boosting (CaCao) framework, where a visually-prompted language model is learned to generate diverse fine-grained predicates in a low-resource way for open-world predicate scene graph generation (Epic).
- 63
- Content-based video similarity model62
A new approach to solve the difficulty of video similarity, considering all the factors existing in human vision perception, and introduces a new comparison algorithm based on multi-granularity of video structure, which has great flexibility.
- Open-Ended Long-form Video Question Answering via Adaptive Hierarchical Reinforced Networks61
This paper proposes the adaptive hierarchical encoder network to learn the joint representation of the long-form video contents according to the question with adaptive video segmentation and develops the reinforced decodernetwork to generate the natural language answer for open-ended video question answering.
- Multi-interaction Network with Object Relation for Video Question Answering60
A new attention mechanism called multi-interaction, which can capture both element-wise and segment-wise sequence interactions, simultaneously, simultaneously is proposed, which achieves the new state-of-the-art performance.
- Local and Global Regressive Mapping for Manifold Learning with Out-of-Sample Extrapolation60
The proposed algorithm, namely Local and Global Regressive Mapping (LGRM), employs local regression models to grasp the manifold structure and imposes a global regression term as regularization to learn a model for out-of-sample data extrapolation.
- Steerable pyramid-based face hallucination60
A robust learning-based face hallucination algorithm, which predicts a high-resolution face image from an input low-resolution image, which can be utilized for many computer vision tasks, such as face recognition and face tracking.
- Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning59
This paper proposes a novel asymmetric multi-faceted ranking network learning framework for community-based question answering by jointly exploiting the deep semantic relevance between question-answer pairs and the answerers' authority to the given question.
- Hierarchical Cross-Modal Graph Consistency Learning for Video-Text Retrieval58
A Hierarchical Cross-Modal Graph Consistency Learning Network (HCGC) for video-text retrieval task, which considers multi-level graph consistency for video -text matching and designs three types of graph consistency: inter-graph parallel consistency, inter- graph cross consistency and intra-graph cross consistency.
- 55
- Multi-modal Mutual Topic Reinforce Modeling for Cross-media Retrieval55
This work proposes a supervised multi-modal mutual topic reinforce modeling (M$^3$R) approach, which seeks to build a joint cross- modal probabilistic graphical model for discovering the mutually consistent semantic topics via appropriate interactions between model factors.
- 54
- Microblog Sentiment Classification via Recurrent Random Walk Network Learning54
This paper proposes a novel recurrent random walk network learning framework for the microblog sentiment classification problem by exploiting both users’ posted tweets and their social relations in microblogs, and introduces the deep recurrent neural networks with random-walk layer for heterogeneous MSC network embedding.
- Deep Compositional Cross-modal Learning to Rank via Local-Global Alignment54
This paper considers learning a multi-modal embedding from the perspective of optimizing a pairwise ranking problem while enhancing both local alignment and global alignment and demonstrates the superiority of the proposed C2MLR due to its nature of multi- modal compositional embedding.
- Mining Spatial-Temporal Patterns and Structural Sparsity for Human Motion Data Denoising53
This paper proposes a data-driven-based robust human motion denoising approach by mining the spatial-temporal patterns and the structural sparsity embedded in motion data by replacing the regularly used entire pose model with a much fine-grained partlet model as feature representation to exploit the abundant local body part posture and movement similarities.
- 53
- Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models52
This work proposes a novel method for zero-shot VRD: RECODE, which solves RElation detection via COmposite DEscription prompts, and introduces a chain-of-thought method that prompts LLMs to generate reasonable weights for different visual cues.
- A low rank structural large margin method for cross-modal ranking52
A general cross-modal ranking algorithm to optimize the listwise ranking loss with a low rank embedding, which is called Latent Semantic Cross-Modal Ranking (LSCMR) and shows significant improvements over the state-of-the-art methods.
- Unified fair federated learning for digital healthcare51
This work proposes Federated Learning with Unified Fairness Objective (FedUFO), a unified framework consolidating diverse fairness levels within FL that ensures consistent performance across all subpopulations and enhances the overall efficacy of FL in healthcare and other domains while maintaining accuracy levels comparable with those of existing methods.
- A hybrid brain-computer interface control strategy in a virtual environment51
This paper presents a hybrid brain-computer interface (BCI) control strategy, the goal of which is to expand control functions of a conventional motor imagery or a P300 potential based BCI in a virtual environment.
- Continual Vision-Language Representation Learning with Off-Diagonal Information50
A new continual vision-language representation learning framework Mod-X is proposed: Maintain off-diagonal information-matriX, which improves the capability of the multi-modal model by maintaining the multi -modal representation space alignment on the old data domain during continuously fitting the new training data domain.
- Logistic Tensor Regression for Classification50
The proposed Logistic Tensor Regression not only reserves the underlying structural information embedded in data by tensorial representations, but also avoids overfitting by the introduction of a sparsity regularizer.
- 49
- Natural Language Video Localization with Learnable Moment Proposals49
It is argued that the performance of propose-and-rank models are underestimated due to the predefined manners: 1) Hand-designed rules are hard to guarantee the complete coverage of targeted segments and 2) Densely sampled candidate moments cause redundant computation and degrade theperformance of ranking process.
- 47
- 46
- Video Question Answering via Hierarchical Dual-Level Attention Network Learning46
This paper develops the hierarchical duallevel attention networks to learn the question-aware video representations with word-level and question-level attention mechanisms, and devise thequestion-level fusion attention mechanism for the proposed networks to learning the questionaware joint video representation.
- Apply semantic template to support content-based image retrieval45
By the approach, in the keyword query of the user, relevant images will be returned to the user by the help of semantic template association even those images are not annotated by keyword.
- Heterogeneous Attributed Network Embedding with Graph Convolutional Networks44
HANE is proposed, a novel network embedding method based on Graph Convolutional Networks, that leverages both the heterogeneity and the node attributes to generate high-quality embeddings.
- 44
- DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition43
- Data Shunt: Collaboration of Small and Large Models for Lower Costs and Better Performance42
The proposed Data Shunt (DS), a general paradigm for collaboration of small and large models, which not only substantially reduces the cost associated with deploying large models but also effectively enhances overall performance.
- 42
- 42
- The Next Breakthroughs of Artificial Intelligence: The Interdisciplinary Nature of AI42
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
- Auto-Encoding Morph-Tokens for Multimodal LLM41
This work proposes encoding images into morph-tokens to serve a dual purpose: for comprehension, they act as visual prompts instructing MLLM to generate texts; for generation, they take on a different, non-conflicting role as complete visual-tokens for image reconstruction, where the missing visual cues are recovered by the MLLM.
- Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models41
A novel Gradient-RegulAted Meta-prompt learning (GRAM) framework that jointly meta-learns an efficient soft prompt initialization for better adaptation and a lightweight gradient regulating function for strong cross-domain generalizability in a meta-learning paradigm using only the unlabeled image-text pre-training data.
- Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference41
This paper proposes to transfer knowledge from some important discourse markers to augment the quality of the NLI model by using reinforcement learning to optimize a new objective function with a reward defined by the property of theNLI datasets to make full use of the labels information.
- Sparse motion bases selection for human motion denoising41
A data-driven based human motion denoising method that sparsely selects the most correlated subset of motion bases for clean motion reconstruction that outperforms its competitors and can be more easily applied to real-world applications.
- Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels40
This work introduces a novel task, Partial labeling and Long-Tailed Multi-Label Classification (PLT-MLC), and proposes an end-to-end learning framework, COMIC, which significantly outperforms general MLC, LT-MLC and PL-MLC methods in terms of effectiveness and robustness on newly created PLT-MLC datasets.
- Cross-Media Hashing with Neural Networks40
This work proposes a cross-media hashing approach based on multi-modal neural networks that achieves superior cross- media retrieval performance compared with the state-of-the-art methods.
- Classification by semi-supervised discriminative regularization40
This paper proposes a novel method, referred to as semi-supervised discriminative regularization (SSDR), to incorporate LDA and MR into a coherent framework for data classification, which exploits both label information and data distribution.
- Retrieval based interactive cartoon synthesis via unsupervised bi-distance metric learning40
A gesture recognition method for cartoon character images with two applications, namely content-based cartoon image retrieval and cartoon clip synthesis, that learns the optimal distance metric from the heterogeneous distance metrics derived from intra-features and inter-features.
- Retrieval of Chinese Calligraphic Character Image40
A novel method is presented to retrieve Chinese calligraphic character images using approximate correspondence point algorithm, which first compute point contexts and find approximate point correspondence in the other character, and then retrievecalligraphic characters according to their accumulated matching cost.
- Disentangled Motif-aware Graph Learning for Phrase Grounding39
A novel graph learning framework for phrase grounding in the image with special attention to different motifs implied in the context of the scene graph and devise the disentangled graph network to integrate the motif-aware contextual information into representations.
- Applying probabilistic latent semantic analysis to multi-criteria recommender system39
Two types of multi-criteria probabilistic latent semantic analysis algorithms extended from the single-rating version are proposed, inspired by the Bayesian network and linear regression.
- Cross-media retrieval using query dependent search methods38
This work constructs an MMD semi-semantic graph (MMDSSG) by jointly analyzing the heterogeneous multimedia data and proposes different learning methods of relevance feedback (RF) to improve the performance of cross-media retrieval.
- An Efficient Keyframe Extraction from Motion Capture Data38
The experiments demonstrate that the proposed keyframe extraction method can not only compress and summarize the motion capture data efficiently, but also keep the consistency of keyframe collection between similar human motion sequences, which is of great benefit to further motion data retrieval or editing.
- 37
- 37
- 36
- 35
- Diverse image captioning via grouptalk35
A novel iterative update strategy is proposed to separate training sentence samples into groups and learn their distributions at the same time and introduce an efficient classifier to solve the problem brought about by the non-linear and discontinuous nature of language distributions which will impair performance.
- 35
- 35
- Degeneration-Tuning: Using Scrambled Grid shield Unwanted Concepts from Stable Diffusion34
A novel strategy named Degeneration-Tuning (DT) is proposed to shield contents of unwanted concepts from SD weights by utilizing Scrambled Grid to reconstruct the correlation between undesired concepts and their corresponding image domain, and guide SD to generate meaningless content when such textual concepts are provided as input.
- 34
- Topic aspect-oriented summarization via group selection34
This paper attempts to exploit appropriate priors to generate topic aspect-oriented summarization (abbreviated as TAOS) and can generate meaningful summarization in terms of ROUGE and Jensen–Shannon Divergence metrics.
- Multichannel Attention Refinement for Video Question Answering33
Appearance, motion, and audio features are extracted from the video, and question-guided attentions are refined to generate the expressive clues that support the correct answer in VideoQA.
- Semantic Locality-Aware Deformable Network for Clothing Segmentation33
A semantic locality-aware segmentation model is proposed, which adaptively attaches an original clothing image with a semantically similar auxiliary exemplar by search to make the learning process of small sample learning more stable and tractable.
- Heterogeneous feature selection by group lasso with logistic regression33
The selection of groups of discriminative features by the extension of group lasso with logistic regression for high-dimensional feature setting is formulates as the heterogeneous feature selection by Group Lasso with Logistic Regression (GLLR).
- Latent Style Model: Discovering writing styles for calligraphy works33
This paper proposes calligraphic style representation which is a multinomial probability distribution over visual words, and Latent Style Model to discover the style of calligraphy works and organize the works by style and illustrates the Calligraphic Style Browser to organize and exhibit the resource according to the styles.
- OCTOPUS33
An aggressive search mechanism called Octopus is proposed which addresses the retrieval of multi-modality data using multifaceted knowledge and a unique relevance feedback technique is developed to update the knowledge base by learning from user behaviors, and to enhance the retrieval performance in a progressive manner.
- Multi-Task Sparse Discriminant Analysis (MtSDA) with Overlapping Categories32
MtSDA formulates multi-label prediction as a quadratic optimization problem whereas SDA obtains single labels via a nearest class mean rule and a class of equicorrelation matrices to use in MtSDA which includes the identity matrix are proposed.
- Let LRMs Break Free from Overthinking via Self-Braking Tuning31
This paper proposes a novel framework, Self-Braking Tuning (SBT), which tackles overthinking from the perspective of allowing the model to regulate its own reasoning process, thus eliminating the reliance on external control mechanisms.
- Saliency Detection within a Deep Convolutional Architecture31
This work proposes to learn adaptive mid-level features to represent image local information, and presents an efficient way to calculate multi-scale and multi-level saliency maps, using the simple k-means algorithm.
- Hypergraph spectral hashing for similarity search of social image31
Unified hypergraph is implemented to model the various relationships among images and other contexts in social media and traditional spectral hashing is extended to hypergraph to accelerate similarity search of social images by mapping semantically related vertices into similar binary codes within a short Hamming distance.
- 31
- EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model30
The Eyecare Kit is proposed, which systematically tackles three key challenges of intelligent ophthalmic diagnosis with the tailored dataset, benchmark and model, and develops the EyecareGPT, optimized for fine-grained ophthalmic visual understanding thoroughly.
- 30
- Large Language Models Improve Alzheimer's Disease Diagnosis Using Multi-Modality Data30
The approach is based on an existing pretrained large language model (LLM) to enhance the model's ability to utilize non-image data on diagnosing AD and results show that the approached achieved state-of-the-art (SOTA) performance.
- Supervised Nonnegative Tensor Factorization with Maximum-Margin Constraint30
The proposed Supervised Non-negative Tensor Factorization with Maximum-Margin Constraint (SNTFM2) formulates the optimal discriminative factorization of non-negative tensorial data as a coupled least-squares optimization problem via a maximum-margin method.
- Deep Residual Weight-Sharing Attention Network With Low-Rank Attention for Visual Question Answering29
- Skeleton-Based Recognition of Chinese Calligraphic Character Image29
A novel skeletonization algorithm called MFITS (morphology-fused index table skeletonization) is proposed and a skeleton-based Chinese calligraphic character recognition method is proposed too.
- Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference28
An adaptive hierarchical graph network is proposed that achieves in-depth understanding of the video over complex interactions andsemantic coherence learning is introduced to explicitly encourage the semantic coherence of the adaptive hierarchicalgraph network from three hierarchies.
- 28
- 27
- Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images27
This work designs a depth decoupling convolutional neural network (DDCNN), which contains a depth estimation branch and a saliency detection branch, and introduces a consistency loss on the intermediate attention and saliency maps for the unlabeled data, as well as a supervised depth and Saliency loss for labeled data.
- 27
- Hypergraph Spectral Hashing for image retrieval with heterogeneous social contexts27
Unified hypergraph is implemented to model the various relationships among images and other contexts in social media and traditional spectral hashing is extended to hypergraph to accelerate similarity search of social images by mapping semantically related vertices into similar binary codes within a short Hamming distance.
- Tell and guess: cooperative learning for natural image caption generation with hierarchical refined attention26
This paper designed the “Tell and Guess” Cooperative Learning model with a Hierarchical Refined Attention mechanism (CL-HRA) that bidirectionally improves the performance to generate more informative captions.
- 26
- Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training25
This paper proposes collaborative adversarial training to improve the data utilization, which coordinates virtual adversarialTraining (VAT) and adversarial Training (AT) at different levels, and employs the instance-level VAT to recycle instances abandoned by MIL.
- Informative Visual Storytelling with Cross-modal Rules25
This work proposes a method to mine the cross-modal rules to help the model infer these informative concepts given certain visual input, and leverages these concepts in the authors' encoder-decoder framework with the attention mechanism.
- 25
- A locally weighted sparse graph regularized Non-Negative Matrix Factorization method25
A noise robust NMF method named as Locally Weighted Sparse Graph regularized Non-negative Matrix Factorization (LWSG_NMF) is proposed, which reformulate the empirical likelihood term of the standard NMF by explicitly imposing a sparse noise term.
- Content-based retrieval of Flash™ movies: research issues, generic framework, and future directions25
A generic framework termed as FLAME (FLash Access and Management Environment) embodying a 3-layer structure that addresses the representation, indexing, and retrieval of Flash movies by mining and understanding of the movie content is proposed.
- 25
- SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation24
SVGenius establishes the first systematic evaluation framework for SVG processing, providing crucial insights for developing more capable vector graphics models and advancing automated graphic design applications.
- 24
- A semantic feature for human motion retrieval24
This paper proposes a high level semantic feature in a low dimensional space to represent the essential characteristic of different motion classes and shows that this feature can effectively achieve motion matching on both global clip level and local frame level.
- 24
- 23
- ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 202223
A multi-scale cross-modal transformer and a video frame-level contrastive loss are proposed to fully uncover the correlation between language queries and video clips to solve the Ego4D Natural Language Queries challenge.
- Walking with MIND23
A novel Mental Imagery eNhanceD (MIND) module for the embodied agent, as well as a relevant deep reinforcement framework for training, which proves that the agent with the MIND module is superior to its counterparts not only in EQA performance but in many other aspects such as route planning, behavioral interpretation, and the ability to generalize from a few examples.
- Metric Learning Driven Multi-Task Structured Output Optimization for Robust Keypoint Tracking23
This work proposes a robust keypoint tracker based on spatio-temporal multi-task structured output optimization driven by discriminative metric learning, which is simultaneously optimized in a joint learning scheme.
- Online Metric-Weighted Linear Representations for Robust Visual Tracking23
It is shown that online distance metric learning significantly improves the robustness of the tracker, especially on those sequences exhibiting drastic appearance changes, and design a time-weighted reservoir sampling method in order to bound growth in the number of training samples.
- The heterogeneous feature selection with structural sparsity for multimedia annotation and hashing: a survey23
This paper introduces many of the recent efforts in sparsity-based heterogenous feature selection, the representation of the intrinsic latent structure embedded in multimedia, and the related hashing index techniques.
- HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models22
HyperLLaVA is introduced, which involves adaptive tuning of the projector and LLM parameters, in conjunction with a dynamic visual expert and language expert, respectively, derived from HyperNetworks, enabling dynamic projector and LLM modeling in two-stage training.
- 22
- Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering22
This work proposes to regularize distantly supervised models with Compact Latent Space Clustering (CLSC) to bypass the problem of dealing with false entity type labels, and effectively utilize noisy data yet.
- To Stay or to Leave: Churn Prediction for Urban Migrants in the Initial Period22
It is found that migrants who end up leaving early tend to neither develop diverse connections in their first weeks nor move around the city, and their active areas also have higher housing prices than that of staying migrants.
- Flickr group recommendation with auxiliary information in heterogeneous information networks22
The group recommendation in this paper is formulated as a non-negative matrix factorization (NMF) method regularized with user–user similarity via visual features and heterogeneous information networks, and experiments show that the proposed approach outperforms other counterpart recommendation approaches.
- The classification of multi-modal data with hidden conditional random field22
The experimental results show the effectiveness of the proposed Multi-modal Hidden Conditional Random Field (M-HCRF), which represents the intrinsical structure shared by different modalities as hidden variables in a undirected general graphical model when learning the latent shared structure of the multi- modal data.
- Manifold Learning Based Cross-media Retrieval: A Solution to Media Object Complementary Nature22
A manifold learning based cross-media retrieval approach that gives solutions to the two intrinsically basic but crucial questions of media objects semantics understanding and cross- media retrieval.
- Video based human animation technique22
This paper proposes a new video based human animation technique that has the characteristic of rich source material, low computing cost, efficient production, and realistic animation result.
- Hierarchical Attention Based Spatial-Temporal Graph-to-Sequence Learning for Grounded Video Description21
Two ways to construct a sequence graph that captures spatial-temporal correlations among different objects in each frame are exploited and a novel graph topology refinement technique is presented to discover optimal underlying graph structure.
- Video Question Answering via Knowledge-based Progressive Spatial-Temporal Attention Network21
A knowledge-based progressive spatial-temporal attention network is proposed to tackle the problem of video question answering by taking the spatial and temporal dimension of video content into account and employing an external knowledge base to improve the answering ability of the network.
- 21
- Correlated attribute transfer with multi-task graph-guided fusion21
The novelty of CAT-MtG2F is to encourage highly correlated attributes to share a common set of relevant low-level features and transfer the learned common structure from the source image set to the target image set.
- An iris recognition method based on multi-orientation features and Non-symmetrical SVM21
Experimental data shows that Non-symmetrical SVM can satisfy various security requirements in iris recognition applications and performs more satisfactorily when compared to former algorithms.
- Dancing Avatar: Pose and Text-Guided Human Motion Videos Synthesis with Image Diffusion Model20
Dancing Avatar is proposed, designed to fabricate human motion videos driven by poses and textual cues, that exhibits the capacity to generate human videos with markedly superior quality, both in terms of human and background fidelity, as well as temporal coherence compared to existing state-of-the-art approaches.
- Attentional Image Retweet Modeling via Multi-Faceted Ranking Network Learning20
A novel attentional multi-faceted ranking network learning framework with multi-modal neural networks is developed for the proposed heterogenous IRM network to learn the joint image tweet representations and user preference representations for prediction task.
- 20
- Joint Multilabel Classification With Community-Aware Label Graph Learning20
This work proposes a multilabel classification framework based on a joint learning approach called label graph learning (LGL) driven weighted Support Vector Machine (SVM) which explicitly models the inter-label correlations by LGL, which is jointly optimized with multILabel classification in a unified learning scheme.
- 20
- Active post-refined multimodality video semantic concept detection with tensor representation20
A novel dimension reduction method that explicitly considers the manifold structure of the tensor space from multimodal media data which is temporal associated co-occurrence and then detect video semantic concepts through powerful classifiers which take tensor as input is proposed.
- 20
- Slimmable Domain Adaptation19
A simple framework to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs, and augment the existing bi-classifier domain confusion architecture into an Optimization-Separated Tri-Classifier counterpart.
- Understanding Default Behavior in Online Lending19
This paper proposes a novel probabilistic framework to identify default borrowers and cheating agents simultaneously, and establishes a mobile network and explores social factors that predict borrowers' default.
- Perceptual 3D pose distance estimation by boosting relational geometric features19
A new perceptual pose distance that accumulates the differences over a set of features that reflects the geometric relations between different body parts is proposed that outperforms others in emulating human perception in pose similarity.
- Silhouette representation and matching for 3D pose discrimination – A comparative study19
This paper gives a systematic study on the performances of shape representation and matching algorithms for pose discrimination, and explores the influences of different realistic factors encountered in practical systems, such as yaw angle, camera tilt, silhouette noise, and the selection of training examples.
- 19
- 19
- Search for Multi-modality Data in Digital Libraries19
2M2Net is presented as a generic framework for retrieval of multimodality data in digital libraries and a learning- from-elements strategy is devised for propagation of semantic descriptions.
- VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models18
VerifyBench and its challenging variant VerifyBench-Hard are introduced, two benchmarks specifically designed to assess reference-based reward systems and establish a standardized framework for improving verification accuracy, ultimately enhancing reasoning capabilities in models trained via RL.
- On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals18
The validated techniques are combined and improve the baseline performances of five small architectures with considerable margins, which indicates that training small self-supervised contrastive models is feasible even without distillation signals.
- What Makes a Good Team? A Large-scale Study on the Effect of Team Composition in Honor of Kings18
The results confirm the importance of team diversity with respect to player roles, and show that diversity has varying effects on team effectiveness: although diverse teams perform well and show tenacity in adversity, they are more likely to abuse when losing than less diverse teams.
- Temporality-enhanced knowledgememory network for factoid question answering18
This paper devise an architecture named the temporality-enhanced knowledge memory network (TE-KMN) and apply the model to a factoid question answering dataset from a trivia competition called quiz bowl and demonstrates that the method achieves better performance than several state-of-the-art methods.
- 18
- 17
- Interactive Data Synthesis for Systematic Vision Adaptation via LLMs-AIGCs Collaboration17
This work extensively study how LLMs communicate with AIGC model to achieve more controllable image generation and makes the first attempt to collaborate them for automatic data augmentation for a variety of downstream tasks.
- Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos17
A cross-modal consensus learning paradigm is introduced, which leverages the inherent semantic consensus between the aligned video and subtitle to achieve weakly-supervised learning on temporal emotion localization.
- A unified framework for web video topic discovery and visualization17
This paper tries to solve web video topic discovery problem with visualization under a single framework, and proposes a Star-structured K-partite Graph based co-clustering and ranking framework, which consists of three stages.
- 16
- DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition16
A unified retrieval-augmented system (U-RaNER) for fine-grained multilingual NER, which incorporates the entity-centric Wikidata knowledge base, while utilizing the infusion approach to broaden the contextual scope of the model.
- 16
- Link Prediction via Ranking Metric Dual-Level Attention Network Learning16
This paper proposes a novel proximity ranking metric attention network learning framework by jointly exploiting both node-level and path-level attention proximity of the endpoints to their betweenness paths for learning the discriminative feature representation for link prediction.
- 16
- Interactive high-dimensional index for large Chinese calligraphic character databases16
This article proposes an interactive partial-distance-map(PDM)- based high-dimensional indexing scheme which is designed specifically to speed up the retrieval performance of the large Chinese calligraphic character databases effectively and utilizes users' relevance feedback to refine the query gradually.
- Understanding Multimedia Document Semantics for Cross-Media Retrieval16
The definition of MMD is given and a manifold learning method to discover MMD semantics is proposed and results are encouraging and indicate that the performance of the proposed approach is effective.
- 16
- Audio Retrieval with Fast Relevance Feedback Based on Constrained Fuzzy Clustering and Stored Index Table16
A new and efficient audio retrieval algorithm by unsupervised fuzzy clustering is presented: first, audio features are extracted from compressed domain, these features are processed by temporal-spatial constrained fuzzy clusters, and the relevant audio clips can be represented by the clustering centroids.
- EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering15
This work presents EasySteer, a unified framework for high-performance, extensible LLM steering built on vLLM, and demonstrates its effectiveness in overthinking mitigation, hallucination reduction, and other key applications.
- FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL15
This work proposes FocusDiff, which enhances fine-grained text-image semantic alignment by focusing on subtle differences between similar text-image pairs, and achieves state-of-the-art performance on existing text-to-image benchmarks and significantly outperforms prior methods on PairComp.
- Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program15
Experimental results demonstrate that SVIP-Reward improves MLLM performance across training and inference-time scaling, yielding better results on benchmarks while reducing hallucinations and enhancing reasoning ability.
- Learning Combinatorial Prompts for Universal Controllable Image Captioning15
This work reformulates the CIC as a prompt-guide sentence generation problem, and proposes a new lightweight prompt generation network to generate the combinatorial prompts for different kinds of control signals, which can help to bridge the gap between different signal-specific CIC architectures.
- Feature Enhancement in Attention for Visual Question Answering15
This work focuses on region representation and proposes the idea of feature enhancement, which includes three aspects, which include to leverage region semantic representation which is more consistent with the question representation and enrich the region representation using features from multiple hierarchies.
- Partial Multi-Modal Sparse Coding via Adaptive Similarity Structure Regularization15
This paper proposes a partial multi-modal sparse coding framework termed Adaptive Partial Multi-Modal Similarity Structure Regularization for Sparse Coding (AdaPM2SC), which preserves the similarity structure within the same modality and between different modalities.
- Scalable Linear Visual Feature Learning via Online Parallel Nonnegative Matrix Factorization15
A parallel NMF method called alternating least square block decomposition (ALSD), which efficiently solves a set of conditionally independent optimization subproblems based on a highly parallelized fine-grained grid-based blockwise matrix decomposition, can be effectively implemented in a MapReduce-based Hadoop framework.
- D-Ocean: an unstructured data management system for data ocean environment15
D-Ocean is presented, an unstructured data management system for data ocean environment that exploits a unified storage framework to store data in different kinds of data stores, integrates batch and incremental processing mechanisms to process unstructured data, and provides a combined search engine to conduct compound queries.
- Audio steganalysis based on “negative resonance phenomenon” caused by steganographic tools15
The proposed method can be very effectively used to detect hidden messages embedded by Hide4PGP, Stegowav and S-Tools4 and also identify the tools used to hide them.
- Searching for Flash Movies on the Web: A Content and Context Based Framework15
This paper presents the first piece of work (to the best of the knowledge) in this domain by suggesting an integrated framework for the retrieval of Flash movies based on their content characteristics as well as contextual information.
- 15
- Towards Data-Adaptive and User-Adaptive Image Retrieval by Peer Indexing15
This paper proposes an elegant and effective approach to data-adaptive and user- Adaptive image retrieval based on the idea of peer indexing—describing an image through semantically relevant peer images.
- De-fine: De composing and Re fin ing Visual Programs with Auto-Feedback14
Inspired by benders decomposition, this work introduces De-fine, a training-free framework that automatically decomposes complex tasks into simpler subtasks and refines programs through auto-feedback, which can improve logical reasoning performance by integrating the strengths of multiple models.
- 14
- Structured Embedding via Pairwise Relations and Long-Range Interactions in Knowledge Base14
This paper introduces Path-Ranking to capture the long-range interactions of knowledge graph and at the same time preserve the pairwise relations of knowledgeGraph (SePLi), which achieves better performances of embeddings.
- A GPU-accelerated non-negative sparse latent semantic analysis algorithm for social tagging data14
The experimental results on image classification and tag recommendation tasks on MIRFLICKR and NUS-WIDE datasets show that the parallelized fast optimization algorithm can achieve comparable or even better performance than the other examined methods, while speeds up the original optimization algorithm 20-110 times.
- Supervised cross-collection topic modeling14
The results suggest that the proposed scLDA can generate meaningful collection-specific topics and achieves better retrieval accuracy than other related topic models.
- Efficient shape matching for Chinese calligraphic character retrieval14
A novel shape descriptor called SC-HoG is proposed by integrating global and local features for more discriminability, where a gradient descent algorithm is used to learn the optimal combining parameter.
- 14
- 14
- 13
- Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile13
Eigen-Reptile (ER) is presented that updates the meta-parameters with the main direction of historical task-specific parameters to alleviate sampling and label noise and Introspective Self-paced Learning (ISPL) is proposed, to obtain a more accurate main direction for Eigen- reptile in the presence of many noisy labels.
- Urban Dreams of Migrants: A Case Study of Migrant Integration in Shanghai13
A one-month complete dataset of telecommunication metadata in Shanghai with 54 million users and 698 million call logs is employed to investigate the process of migrant integration and finds systematic differences between locals and migrants in their mobile communication networks and geographical locations.
- Learning Multimodal Neural Network with Ranking Examples13
This paper considers learning with neural networks, from the perspective of optimizing the listwise ranking loss of the cross-modal ranking examples, and proposes a proposed model, named Cross-Modal Ranking Neural Network (CMRNN), which benefits from the advance of both neural networks on learning high-level semantics and learning to rank techniques on learning ranking function.
- Image annotation by semi-supervised cross-domain learning with group sparsity13
The strength of the proposed S^2CLGS method for multi-label image annotation is to integrate semi-supervised discriminant analysis, cross-domain learning and sparse coding together.
- Multiple Hypergraph Clustering of Web Images by MiningWord2Image Correlations13
A novel visibility model is proposed to compute the extent to which a word can be perceived visually in images, and then infer the correlation of word to image by the integration of visibility with tf-idf.
- Perspective‐aware cartoon clips synthesis13
In order to construct the cartoons smoothly, the character's edge distance and motion direction distance are demonstrated to be the factors affecting the human perception in similarity evaluation, and utilized in cartoon clips synthesis.
- 13
- Mastering Collaborative Multi-Modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness12
A collaborative framework, DataTailor, is proposed, which leverages three key principles,formativeness, uniqueness, and representativeness, for effective data selection and achieves 101.3% of the performance of full-data fine-tuning with only 15% of the data, significantly reducing computational costs while maintaining superior results.
- Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales12
Fact is introduced, a novel paradigm designed to generate multimodal rationales that are faithful, concise, and transferable for teaching MLLMs and filter rationales that can be transferred to end-to-end paradigms from programming paradigms to guarantee transferability.
- 12
- Hashing with List-Wise learning to rank12
In this paper, the hashing problem is considered from the perspective of optimizing a list-wise learning to rank problem and an approach called List-Wise supervised Hashing (LWH) is proposed, which obtains a significant improvement over the state-of-the-art hashing approaches due to both structural large margin and list- Wise ranking pursuing in a supervised manner.
- Patch-guided facial image inpainting by shape propagation12
An algorithm that can repair occluded or damaged facial images automatically, named ‘facial image inpainting’ is proposed, which outperforms the traditional inPainting methods by propagating the facial shapes from a face database, and avoids the problem of variations in imaging conditions from different images by inferring colors and textures from the same face image.
- Indexing high-dimensional data in dual distance spaces: a symmetrical encoding approach12
The results demonstrate that this method outperforms the state-of-the-art high dimensional search techniques such as the X-Tree, VA-file, iDistance and NB- tree, especially when the query radius is not very large.
- 12
- Web-Based Chinese Calligraphy Retrieval and Learning System12
A novel Chinese calligraphy retrieval and learning system was proposed, and dynamic writing process was simulated to help learners get thecalligraphy character they are interested in and watch how it was written.
- 12
- Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning11
This paper proposes to enable the collaborative co-evolution of visual comprehension and generation, advancing image generation into an iterative introspective process and introduces a two-stage training approach: supervised fine-tuning teaches the MLLM with the foundational ability to generate genuine CoT for visual generation, while reinforcement learning activates its full potential via an exploration-exploitation trade-off.
- 11
- Balance-Subsampled Stable Prediction Across Unknown Test Data11
A novel balance-subsampled stable prediction (BSSP) algorithm based on the theory of fractional factorial design is proposed, which isolates the clear effect of each predictor from the confounding variables and can reduce the confounding effects among predictors induced by the distribution shift.
- Disambiguating named entities with deep supervised learning via crowd labels11
A crowd model is devised to elicit the underlying features (crowd features) from crowd labels that indicate a matching candidate for each mention, and then use the crowd features to fine-tune a dynamic convolutional neural network (DCNN).
- 11
- Dynamic Time Warping for Chinese calligraphic character matching and recognizing11
Historical Chinese calligraphy is now being scanned by ongoing project of Universal Digital Library to enable universal access.
- Topic discovery of web video using star-structured K-partite graph11
An approach to represent the explicit and implicit correlations hidden in web videos by a star-structured K-partite graph model, and then a co-clustering process is conducted to discover video topics is proposed.
- Style-consistency calligraphy synthesis system in digital library11
A novel approach is proposed to synthesize Chinese calligraphic characters which are in the same style of some calligraphist, and a corresponding system is developed for calligraphy works generation and tablets design.
- Ensemble learning HMM for motion recognition and retrieval by Isomap dimension reduction11
A novel approach is presented for motion recognition and retrieval based on ensemble HMM (hidden Markov model) learning and experiment results showed that the approaches are effective for motion data recognition and retrieved.
- Multimedia Knowledge Exploitation for E-Learning: Some Enabling Techniques11
Different ways of feature extraction from multimedia are explored and the integration of multi-modal media is laid down for exploiting media knowledge effectively, which can greatly enhance the performance of the high-level semantic retrieval desired by advanced applications such as e-learning.
- 11
- Hierarchical Budget Policy Optimization for Adaptive Reasoning10
Hierarchical Budget Policy Optimization is presented, a reinforcement learning framework that enables models to learn problem-specific reasoning depths without sacrificing capability, and exhibits emergent adaptive behavior where models automatically adjust reasoning depth based on problem complexity.
- What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities10
OmniBench is introduced, a self-generating, cross-platform, graph-based benchmark with an automated pipeline for synthesizing tasks of controllable complexity through subtask composition and OmniEval, a multidimensional evaluation framework that includes subtask-level evaluation, graph-based metrics, and comprehensive tests across 10 capabilities.
- Improving Reference-Based Distinctive Image Captioning with Contrastive Rewards10
A two-stage matching mechanism, which strictly controls the similarity between the target and reference images at the object-/attribute-level (vs. scene-level), and a Transformer-based Ref-DIC baseline TransDIC, which can generate distinctive captions are developed.
- 10
- Sketch the storyline with CHARCOAL: a non-parametric approach10
The adaptation of non-parametric nature in CHARCOAL makes the model can adaptively learn the appropriate number of stories and topics from news corpus and demonstrates both interpretability and superiority of the proposed approach.
- Random walk models for top-N recommendation task10
This work employs a Gaussian random field to model the top-N recommendation task as a semi-supervised learning problem, taking into account the degree of each node on the user-item bipartite graph, and induces an effective absorbing random walk (ARW) algorithm for the top of the recommendation task.
- A group of novel approaches and a toolkit for motion capture data reusing10
A group of novel approaches for posture feature representation, motion sequence segmentation, key-frame extraction and content-based motion retrieval, which are all very important for MoCap data reusing and benefit to the efficient animation production are proposed.
- 10
- 10
- 10
- Unsupervised Domain Adaptation for Video Object Grounding with Cascaded Debiasing Learning9
This paper addresses the Unsupervised Domain Adaptation (UDA) for the dense frame prediction task - Video Object Grounding and measures Grounding Coordinate Offset based on the semantic distance of the model's prediction across domains, based on which it alleviate source-domain bias in the target model through adversarial learning.
- 9
- Jointly Discovering Fine-grained and Coarse-grained Sentiments via Topic Modeling9
The proposed MgS-LDA not only discovers the topics in social media, but also identifies opinions about a given topic in terms of fine-grained and coarse- grained sentiment.
- Group sparse representation for image categorization and semantic video retrieval9
This paper develops a novel approach to image representation, which it is called group sparse representation (GSR), for image classification and video retrieval, and introduces two sets of weight coefficients, one for each training image and the other for each class.
- Stable multi-label boosting for image annotation with structural feature selection9
The proposed approach, called stable multi-label boosting with structural feature selection (S-MtBFS), for image annotation has better and stable performance of multi- label image annotation and leads to a quite interpretable model for image understanding.
- Sample based 3D face reconstruction from a single frontal image by adaptive locally linear embedding9
This approach has several advantages: (1) Only a single frontal face image is needed for highly automatic face reconstruction; (2) Compared with former works, this reconstruction approach provides higher accuracy; (3) Constraint based RBF texture mapping provides natural appearance for reconstructed face.
- 9
- Visual Verification of Historical Chinese Calligraphy Works9
Features that characterize an individual calligrapher's writing style are extracted and modeled and compared with the genuine in the reference database to detect problematic characters and to calculate total accepting probability.
- Adaptive audio watermarking based on SNR in localized regions9
A novel localized audio watermarking scheme based on signal to noise ratio (SNR) to determine a scaling parameter α is proposed and shows strong robustness against common problems in audio signal processing, random cropping, time scale modification, etc.
- 9
- Improving Web-Based Learning: Automatic Annotation of Multimedia Semantics and Cross-Media Indexing9
A novel algorithm is proposed for automatic annotation of image based on support vector machine and statistical learning and cross-media indexing is constructed for multi-modal data upon the annotation result to support cross- media search.
- Logic Distillation: Learning from Code Function by Function for Decision-making Tasks8
Experiments demonstrate that with the assistance of LD, S-LLMs can achieve outstanding results in continuous decision-making tasks, comparable to, or even surpassing, those of L-LLMs.
- 2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining8
This paper introduces a high-quality multimodal textbook corpus with richer foundational knowledge for VLM pretraining, and demonstrates its superb pretraining performance, particularly in knowledge- and reasoning-intensive tasks like ScienceQA and MathVista.
- Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining8
Iris is introduced, a foundational visual agent that addresses challenges in visual perception through two key innovations: Information-Sensitive Cropping (ISC) and Self-Refining Dual Learning (SRDL).
- 8
- Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification8
The objective is to customize a student model for distribution-agnostic downstream tasks with given category concepts, inheriting the out-of-distribution generalization capability from the pre-trained foundation models without access to the billion-level image-text datasets.
- A knowledge-guided and traditional Chinese medicine informed approach for herb recommendation8
A knowledge-guided and TCM-informed approach for herb recommendation, which applies on a TCM prescription dataset, demonstrating significant improvements over state-of-the-art herb recommendation methods.
- 8
- Weak Supervision Enhanced Generative Network for Question Generation8
The Weak Supervision Enhanced Generative Network (WeGen) is proposed which automatically discovers relevant features of the passage given the answer span in a weakly supervised manner to improve the quality of generated questions.
- NITE: A Neural Inductive Teaching Framework for Domain Specific NER8
It is proved that without using any labeled data, NITE can significantly boost the performance of a CNN-bidirectional LSTM-CRF NER neural network nearly over 30% in terms of F1-score.
- 8
- 8
- Image annotation by composite kernel learning with group structure8
Comparisons with other image annotation algorithms show that the proposed Composite Kernel Learning with Group Structure for image annotation achieves a better performance.
- Discovering calligraphy style relationships by Supervised Learning Weighted Random Walk Model8
A Supervised Learning Weighted Random Walk Model is proposed to discover calligraphy style relationships on heterogeneous graphs and some strategies to enhance the performance with the explicit or implicit user interaction including feedback, clickthrough data tracking.
- Search-Based Automatic Web Image Annotation Using Latent Visual and Semantic Analysis8
A search-based automatic web image annotation using latent visual and semantic analysis to find the synonyms of initial annotations is proposed, which demonstrates the effectiveness of the proposed approach.
- Multi-sensor image registration using multi-resolution shape analysis8
An image registration method based on multi-resolution shape analysis is proposed, to deal with the problem that the shape of similar objects is always invariant, and the results have been shown to be superior to the classical ones.
- Towards Robust 3D Reconstruction of Human Motion from Monocular Video8
A robust, adaptive system for reconstructing 3D human motion from monocular video is presented, which is robust, getting rid of error accumulation in tracking, and adaptive, being able to tell the user when and where more information is needed.
- A New Iris Recognition Approach for Embedded System8
An iris recognition system using SVM to classify the acquired features series and several optimizations are made to make the SVM more applicable in embedded systems, including Active Learning, Kernel Selection and Negative Samples Reuse Strategy.
- Multi-Modal Retrieval for Multimedia Digital Libraries: Issues, Architecture, and Mechanisms.8
This paper proposes 2M2Net as a generic framework for multi-modal retrieval of multimedia data (text, image, video and audio) and is capable of progressive improvement of its retrieval performance.
- Exploring financial sentiment analysis via fine-tuning large language model and attributed graph neural network7
A novel framework that synergizes an LLM with a Graph Neural Network to model stock price dynamics, leveraging stock sentiment signals extracted from financial news and outperforms previous baselines and exhibits an average improvement of 50% in Sharpe ratio.
- From Easy to Hard: Learning Curricular Shape-Aware Features for Robust Panoptic Scene Graph Generation7
This work proposes a model-agnostic Curricular shApe-aware FEature (CAFE) learning strategy for PSG, which outperforms existing state-of-the-art methods by a large margin and incorporates shape-aware features into PSG, moving beyond reliance solely on bbox features.
- VL-NMS: Breaking Proposal Bottlenecks in Two-stage Visual-language Matching7
VL-NMS is proposed, which is the first method to yield query-aware proposals at the first stage of a two-stage matching method and validated on three multimodal matching tasks, namely referring expression grounding, phrase grounding, and image-text matching.
- 7
- 7
- Video Dialog via Multi-Grained Convolutional Self-Attention Context Networks7
A novel approach for video dialog called multi-grained convolutional self-attention context network, which combines video information with dialog history and can achieve higher time efficiency and the extensive experiments also show the effectiveness of the method.
- Learning Deep Contextual Attention Network for Narrative Photo Stream Captioning7
A novel deep contextual attention network (CAN) is proposed to narratively describe photo streams by jointly exploring the rich context among attended regions and the coherence in sentences by exploiting visual attention and context in the photo stream.
- Efficient semi-supervised multiple feature fusion with out-of-sample extension for 3D model retrieval7
This paper first extracts multiple visual features to describe both the local and global appearance characteristics of multiple 2D projected images that are generated from 3D models and adopts SMFF to learn a more compact and discriminative low-dimensional feature representation via multiple feature fusion using both the labeled and unlabeled3D models.
- Multiple kernel learning with NOn-conVex group spArsity7
The proposed MKL-NOVA (Multiple Kernel Learning with NOn-conVex group spArsity) conducts a non-convex penalty for the selection of groups of features, and achieves the consistent selection, and considering the contextual correlation between multi labels, sparse canonical correlation analysis is conducted to boost the image annotation performance by MKL -NOVA.
- Real‐time motion data annotation via action string7
A new motion annotation method that achieves both the aforementioned two targets at the same time, using a probabilistic pose feature based on the Gaussian Mixture Model to represent each pose.
- Retrieval-based cartoon gesture recognition and applications via semi-supervised heterogeneous classifiers learning7
A heterogeneous cartoon gesture recognition method with applications that simultaneously integrate shared structure learning (SSL) and graph-based transductive learning into a joint framework to learn reliable classifiers on heterogeneous features.
- 7
- 7
- HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding6
Heartcare Suite is a multimodal comprehensive framework for fine-grained electrocardiogram (ECG) understanding and evaluation that achieves strong generalization and SoTA performance across multiple clinically meaningful tasks.
- 6
- 6
- Transductive Clip with Class-Conditional Contrastive Learning6
This work proposes Transductive CLIP, a novel framework for learning a classification network with noisy labels from scratch, and proposes a class-conditional contrastive learning mechanism to mitigate the reliance on pseudo labels and boost the tolerance to noisy labels.
- BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval6
A novel Bottom-up crOss-modal Semantic compoSition (BOSS) with Hybrid Counterfactual Training framework, which sheds new light on the CIR task by studying it from two previously overlooked perspectives.
- Photo Stream Question Answer6
This paper presents a new visual question answering (VQA) task -- Photo Stream QA, which aims to answer the open-ended questions about a narrative photo stream, and proposes an end-to-end baseline (E-TAA), which provides promising results outperforming all the other baseline methods.
- Bi-Decoder Augmented Network for Neural Machine Translation6
This paper proposes a novel Bi-Decoder Augmented Network (BiDAN) for the neural machine translation task, and adds an auxiliary decoder to generate back the source language sequence at the training time.
- Intra-view and Inter-view Attention for Multi-view Network Embedding6
A novel network embedding method, Intra-view and Inter-view attention for Multi-view Network Embedding (I2MNE), which leverages both the multi-view network structure and the node features to efficiently generate node representations.
- 6
- Entity mention aware document representation6
Experimental results demonstrate that the proposed approach to learning low-dimensional vector representations of documents is able to significantly improve text clustering, text classification performance and outperform previous studies on the TAC-KBP entity linking benchmark.
- Fast view-based 3D model retrieval via unsupervised multiple feature fusion and online projection learning6
A fast view-based 3D model retrieval framework that cannot only dramatically improve the retrieval performance but also reduce the computational cost in dealing with the newcome models.
- 6
- 6
- Review-oriented metadata enrichment6
An Book-Centric Diverse Random Walk algorithm on a four-partite graph containing three kinds of relations among authors, books, reviews and words is proposed in order to produce highly relevant as well as diverse keywords for a book.
- Heterogeneous multimedia data semantics mining using content and location context6
A method of integrating the content and location context for multimedia data mining to enable the cross-media retrieval, by which the query examples and the returned results can be of different modalities, e.g. to query audios by an example of image.
- Recognition and Retrieval of 3D Terrain Based on Level of Detail and Minimum Spanning Tree6
In this paper, an algorithm is presented to implement the similar 3D object recognition and retrieval, and the proposed algorithm works well when it is used to recognize and retrieve a 3D.
- Quasi-Facial Communication for Online Learning Using 3D Modeling Techniques6
The experimental results show that the algorithm can robustly produce 3D facial models from images captured in various scenarios to enhance the lifelikeness in distant learning.
- 6
- 6
- 6
- 6
- Digital libraries: A testbed for multimedia technology6
Challenging issues of some key techniques used in digital libraries and their specific needs for multimedia technologies are presented.
- MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task5
This paper introduces MathFimer, a novel framework for mathematical reasoning step expansion inspired by the''Fill-in-the-middle''task from code reasoning", and offers a practical, scalable solution for enhancing mathematical reasoning capabilities in LLMs without relying on powerful external models or expensive inference procedures.
- STRIDE: Automating Reward Design, Deep Reinforcement Learning Training and Feedback Optimization in Humanoid Robotics Locomotion5
STRIDE, a novel framework built on agentic engineering to automate reward design, DRL training, and feedback optimization for humanoid robot locomotion tasks, outperforms the state-of-the-art reward design framework EUREKA.
- Improving large models with small models: Lower costs and better performance5
DS+ not only substantially reduces the cost associated with querying large models but also effectively improves large models' performance, and experiments prove that the proposed collaborative-based paradigm can better inject specific task knowledge into PLMs compared to fine-tuning.
- GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable Recommendation5
GaVaMoE significantly outperforms existing methods in explanation quality, personalization, and consistency, and exhibits robust performance in scenarios with sparse user-item interactions, maintaining high-quality explanations even for users with limited historical data.
- Attribute-driven streaming edge partitioning with reconciliations for distributed graph neural network training5
A novel distributed graph training approach, attribute-driven streaming edge partitioning with reconciliations (ASEPR), where the local model loads only the subgraph stored on its own machine to make fewer communications.
- Lformer: Text-to-Image Generation with L-shape Block Parallel Decoding5
Lformer, a semi-autoregressive text-to-image generation model that achieves faster speed than the existing transformer-based methods while keeping good generation quality and can edit images without the requirement for finetuning.
- 5
- Video Dialog via Progressive Inference and Cross-Transformer5
This paper introduces a novel progressive inference mechanism for video dialog, which progressively updates query information based on dialog history and video content until the agent think the information is sufficient and unambiguous.
- 5
- 5
- Adaptive and compact shape descriptor by progressive feature combination and selection with boosting5
- Hierarchical Approximate Matching for Retrieval of Chinese Historical Calligraphy Character5
A novel approach to efficiently retrieving Chinesecalligraphy characters on the basis of similarity: calligraphy character image is represented by a collection of discriminative features, and high retrieval speed with reasonable effectiveness is achieved.
- 5
- Mining Frequent Closed Patterns by Adaptive Pruning5
The experimental results show that the algorithm developed is a factor of five to three orders of magnitude more time efficient than several recently proposed algorithms, and is also the most scalable one.
- 3D Model and Motion Retrieval: The Extended Dimensions for Web-Based Learning5
3D model and motion retrieval as a part of e-learning architecture is validated and a novel shape descriptor for arbitrary 3D polygon models is proposed as initial solutions to these problems.
- Popular Song Retrieval Based on Singing Matching5
An approach to retrieval popular song by singing matching by employing recurrent neural network to remember the self-similarity sequence and building a retrieval list generated by correlation degree of self-Similarity sequence.
- 5
- MediaView : A Semantic View Mechanism for Multimedia Modeling5
This paper proposes MediaView as an extended object-oriented view mechanism to bridge the "semantic gap" between conventional databases and semantics-intensive multimedia applications.
- Content-based video retrieval integrating human perception5
This work proposes a unified video retrieval model to simulate human perception, and shows how this learning strategy can emphasize the aspect user cares about, and embodies int in the next iteration of similarity computing.
- Robust Modality-Incomplete Anomaly Detection: A Modality-Instructive Framework with Benchmark4
RADAR, a robust two-stage Robust modAlity-instructive fusing & Detecting frAmewoRk, is proposed, which integrates a Modality-Incomplete Instruction mechanism-guiding the multimodal Transformer to focus more on available modal info, and a Double-Pseudo Hybrid Module to highlight unique modality combinations and reduce overfitting.
- Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts4
A novel Chart Hypothetical Question Answering (HQA) task is introduced, which imposes assumptions on the same question to compel models to engage in counterfactual reasoning based on the chart content, and HAI, a human-AI interactive data synthesis approach that leverages the efficient text-editing capabilities of LLMs alongside human expert knowledge to generate diverse and high-quality HQA data at a low cost.
- ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses4
A novel approach, named ProSwitch, which enables a language model to switch between professional and non-professional answers, by tuning and evaluating through the guidance of domain and style knowledge.
- DEMON24: ACM MM24 Demonstrative Instruction Following Challenge4
The DEMON Challenge aims to assess the ability of models and systems to comprehend demonstrative instructions consisting of multiple, interleaved, and multimodal context that demonstrate the required information to complete a task.
- Spatially Visual Perception for End-to-End Robotic Learning4
This paper introduces a video-based spatial perception framework that leverages 3D spatial representations to address environmental variability, with a focus on handling lighting changes, and integrates a novel image augmentation technique, AugBlender, with a state-of-the-art monocular depth estimation model trained on internet-scale data.
- 4
- Learning embeddings of a heterogeneous behavior network for potential behavior prediction4
A novel network embedding method is proposed, human-action-attribute-aware heterogeneous network embedding (a4HNE), which jointly considers structural proximity, attribute resemblance, and heterogeneity fusion and outperforms other similar methods on various heterogeneous information network mining tasks for potential behavior prediction.
- A human motion feature based on semi-supervised learning of GMM4
This paper presents a novel statistic feature to represent each motion according to the pre-labeled categories of key-poses, and shows that the method performs more accurately and efficiently in motion retrieval and annotation.
- 4
- Content integration in digital libraries4
A content integration method that extracts semi-structured information from textbooks and integrates relevant content based on the relations extracted and operates on an operational public digital library, China America Digital Academic Library (CADAL).
- 4
- Chinese Brush Calligraphy Character Retrieval and Learning4
A retrieval engine was constructed and a dynamic writing process was simulated to help learners get the calligraphy character they were interested in and watch how it was generated step by step.
- 4
- Towards interactive indexing for large Chinese calligraphic character databases4
An interactive partial-distance-map (PDM)- based high-dimensional indexing scheme to speed up the retrieval performance of the large Chinese calligraphic character databases is proposed.
- AN APPROACH TO SEMANTICS-BASED IMAGE RETRIEVAL AND BROWSING *4
The power of thesaurus-aided approaches to facilitate semantics-based access to image collections is exploited by constructing a dynamic semantic hierarchy (DSH) to support flexible browsing of images by semantic subjects, as well as formulating a semantic similarity metric to improve the accuracy of semantic matching.
- Structural-temporal coupling anomaly detection with dynamic graph transformer3
A structural-temporal coupling anomaly detection architecture with a dynamic graph transformer model that outperforms current state-of-the-art models and introduces structural and temporal features from two integration levels to provide anomaly-aware graph evolutionary patterns.
- 3
- EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution3
A progressive instruction evolution framework to gradually generate more complex questions via editing instructions in an adversarial way, progressively aligned with the model’s evolving capabilities, which achieves state-of-the-art performance among open-source RL models on multi-modal reasoning tasks, even approaching the closed-source GPT-4o in reasoning capabilities.
- 3
- 3
- LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation3
This paper introduces LASER, a tuning-free LLM-driven attention control framework that follows a progressive process: LLM planning, feature-attention injection, and stable animation generation, and proposes a Text-conditioned Image-to-Animation Benchmark to validate the effectiveness and efficacy of LASER.
- 3
- Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization Framework3
This paper focuses on the efficient adaptation of EMLLMs to private domains, specifically in two areas: how to reduce data requirements, and how to avoid parameter fine-tuning.
- 3
- FedAA: Using Non-sensitive Modalities to Improve Federated Learning while Preserving Image Privacy3
Experiments show that FedAA significantly outperforms recent non-IID federated learning algorithms while preserving image privac, by sharing information from non-sensitive modalities.
- 3
- 3
- 3
- Learning Max-Margin GeoSocial Multimedia Network Representations for Point-of-Interest Suggestion3
This paper proposes a novel max-margin metric geosocial multimedia network representation learning framework by exploiting users' check-in behavior and their social relations and develops a random-walk based learning method with max- margin metric network embedding.
- ENCORE3
A novel neural framework, named ENCORE (External Neural COnstraints REgularized distant supervision), which allows an integration of other information for standard DS through regularizations under multiple external neural networks.
- Panel3
In this panel, the recent emerging theoretical and technological advances and trends of cross-media are reviewed and the existence of unified framework to bridge the gap between multi-modality is discussed.
- Flickr group recommendation via heterogeneous information networks3
The group recommendation in this paper is formulated as a non-negative matrix factorization (NMF) method regularized with user-user similarity via heterogeneous information networks, and experiments show that the proposed approach outperforms other counterpart recommendation techniques.
- πLDA3
A model called πLDA is proposed, which introduces a latent variable π into LDA, a traditional topic model, to capture the characteristic of each segment unit to determine whether a segment unit is assigned (or selected) to the topic embedded in its corresponding segment.
- Multi-label Image Annotation by Structural Grouping Sparsity3
This chapter introduces one approach for multi-label image annotation with a regularized penalty by the selection of heterogeneous features with structural Grouping Sparsity (MtBGS), which induces a (structural) sparse selection model to identify subgroups of homogeneous features for predicting a certain label.
- 3
- The Clustering of Large Scale E-Learning Resources3
With the pervasion of the Internet, e-learning is more and more popular, which provides a brand new way for people to learn without attending face-to-face class.
- CMSOF: a structured data organization framework for scanned Chinese medicine books in digital libraries3
This paper proposes a novel structured data organization framework called CMSOF to organize scanned data automatically, and applies it to a Chinese medicine digital library and can organize the Chinese medicine books well and users can access the books with flexibility, indicating that CMSOF is an efficient framework to organize books mixed with images and text.
- 3
- Personalized Multimedia Retrieval in CADAL Digital Library3
The details of the algorithms used in the personalized cross-media retrieval, which is a new kind of retrieval technology by which query examples and search results can be of different modalities, are presented.
- A Prediction Error Compression Method with Tensor-PCA in Video Coding3
This paper tries to use a matrix form of PCA (which they call tensor-PCA) to encode prediction errors in video coding, which retains the performance of traditional PCA, but can be computed with much less time and space complexity.
- Research of 3D Chinese Calligraphic Handwriting Recur System and Its Key Algorithm3
A new approach to animate Chinese calligraphy writing process by 3D visualization method and two novel algorithms are presented to extract the intrinsic feature which is needed to rebuild the writing process.
- View-Independent Human Action Recognition by Action Hypersphere in Nonlinear Subspace3
This paper proposes a template-based view-independent human action recognition approach that comprises a series of "action hyperspheres" in a nonlinear subspace and encodes multi-view information of several typical human actions to facilitate the view- independent recognition.
- Video-Based Facial Expression Hallucination: A Two- Level Hierarchical Fusion Approach3
A novel two-level hierarchical fusion approach to hallucinate dynamic expression video sequences when given only one neutral expression face image by fusion of local linear and global nonlinear subspace learning provides a sound solution to organizing the complex video sample space.
- 3
- Data-driven facial animation based on manifold Bayesian regression3
A novel distance metric, the geodesic manifold distance, is introduced to replace the Euclidean distance and put facial animation into the framework of Bayesian regression, showing that the algorithm can robustly produce facial animation with large motions and complex face models.
- Modeling Data and User Characteristics by Peer Indexing in Content-based Image Retrieval.3
This paper proposes a novel approach to dataadaptive and user-adaptive image retrieval based on the idea of peer indexing—describing an image through semantically relevant peer images that models the " data characteristics" of the image as well as the “user characteristics” of individual users with respect to this image.
- 3
- A Framework for Garment Shopping over the Internet3
This chapter proposes a framework for integrated design, advertisement and retailing of garments over the Internet that would make use of the latest research in computer graphics, image processing, computer vision and artificial intelligence.
- Video motion capture in VBA—Video-based animation3
A new approach to do motion capture in video that analyzes large scale motion from frame to frame in complex, variational background, and sets up a 3D motion skeleton in the perspective projection is proposed.
- Video key frame extraction by unsupervised clustering and feedback adjustment3
This paper introduces a new algorithm for key frame extraction based on unsupervised clustering and provides a feedback chain to adjust the granularity of the extraction result.
- Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning2
Arcadia delivers consistent gains on navigation and manipulation benchmarks and transfers robustly to physical robots, indicating that a tightly coupled lifecycle: continuous real-world data acquisition, generative simulation update, and shared-representation learning, supports lifelong improvement and end-to-end generalization.
- 2
- Fast Thinking for Large Language Models2
GainRouter is proposed, a lightweight routing mechanism that adaptively switches between fast codebook guided inference and slow explicit reasoning, thereby suppressing overthinking and reducing unnecessary token generation in large language models.
- Align2LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation2
A novel instruction curation algorithm, derived from two unique perspectives, human and LLM preference alignment, to compress this vast corpus of machine-generated multimodal instructions to a compact and high-quality form.
- 1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track2
A simple yet effective Generalize-then-Adapt (G&A) framework, which is composed of a two-stage domain generalization part and a one-stagedomain adaptation part, to solve the problem in object detection track of the OOD-CV challenge.
- 2
- 2
- 2
- Neural-DINF: A Neural Network based Framework for Measuring Document Influence2
This paper uses both frequency changes and word semantic shifts to measure document influence by developing a neural network framework and shows that the model outperforms DIM.
- KCAT: A Knowledge-Constraint Typing Annotation Tool2
An efficient Knowledge Constraint Fine-grained Entity Typing Annotation Tool is proposed, which further improves the entity typing process through entity linking together with some practical functions.
- 2
- Multi-Label Community-Based Question Classification via Personalized Sequence Memory Network Learning2
This work introduces the personalized sequence memory network that leverages not only the semantics of questions but also the personalized information of askers to provide the sequence tag learning function to capture the high-order tag dependency.
- Video question answering via multi-granularity temporal attention network learning2
This work proposes the multi-granularity temporal attention network (MGTA-Net) that enables to search for the specific frames in a video that are holistically and locally related to the answer.
- The ZHI-EDL System for Entity Discovery and Linking at TAC KBP 2017.2
This report gives a detailed description of ZHI(知)-EDL system of team ‘rise_dcd_zju’, which submitted to the TAC KBP 2017 Trilingual Entity Detection and Linking (EDL) track.
- Ad Recommendation for Sponsored Search Engine via Composite Long-Short Term Memory2
This paper addresses ad recommendation problem that finding and ranking the most relevant ads with respect to users' search queries by utilizing the long-short term memory (LSTM) network to effectively encode two kinds of sequences: the (user, query) sequence and the query word sequence to represent users' query intention in a continuous vector space and decode them as distributions over ads respectively.
- 2
- 2
- Competitive motion synthesis based on hybrid control2
The proposed framework of hybrid paradigm to boxing sport is applied and a rule‐based control scheme is proposed to simulate routine steps based on statistical analysis and the interactive models are designed for simulating dense interactions between two players.
- 2
- A Piece-Wise Learning Approach to 3D Facial Animation2
This paper presents an effective preprocessing algorithm for non-rigid motion extraction and data alignment based on the statistical and kinematical analysis of motion capture data and the topological analysis of facial mesh that is fast enough for real time applications.
- Composite Distance Transformation for Indexing and k-Nearest-Neighbor Searching in High-Dimensional Spaces2
A novel composite distance transformation method, which is called CDT, is proposed to support a fast k-nearest-neighbor (k-NN) search in high-dimensional spaces and outperforms the state-of-the-art high- dimensional search techniques, such as the X-Tree, VA-file, iDistance and NB-Tree.
- A New Reconstruction Algorithm in Spline Signal Spaces2
In this research letter, a reconstruction formula in spline signal spaces which is a generalization of former results in [11] is introduced and the explicit convergence rate of the algorithm is obtained.
- Boosting Cross-Media Retrieval by Learning with Positive and Negative Examples2
A graph based approach is proposed to achieve the content-based cross-media retrieval and MMD retrieval and experiments show that the proposed methods are very effective.
- 2
- Media-Based Presentation with Personalization in a Web-Based eLearning System2
A SMIL-based approach to manage text, graphics, audio, and video for presenting the personalized media-based lesson on the Web for e-Learning system and students is introduced.
- Research on Grid-Aware Mechanisms and Issues for CADAL Project2
This paper analyzes how design principles and mechanisms, applied to digital libraries, can be nested within the OGSA paradigm, and further improves multimedia retrieval.
- Technical features in the portal to CADAL2
The underlying novel multimedia retrieval methods as well as visualization techniques, which are used in the CADAL portal, are investigated.
- Error-Bounded Solid Voxelization for Polygonal Model Based on Heuristic Seed Filling2
This paper presents a fast and easy to implement error-bounded solid voxelization algorithm in three subtasks, which is the result of Heuristic Seed Filling as the critical portion of the algorithm.
- Video segmentation using Maximum Entropy Model2
This paper extends the Maximum Entropy (ME) statistical model to segment layers with features, which are collected by constructing a codebook with a set of codewords for each pixel, and indicates how the training models are used for the discrimination of target objects in surveillance video.
- MFV-Class: a multi-faceted visualization tool of object classes2
A class comprehension model based on constructivist learning theory is proposed, and a software visualization tool (MFV-Class) is implemented to help in the comprehension of a class.
- Subdivision Feedback Based 3D Facial Modeling for E-learning2
Experimental results show that the model becomes more photorealistic after subdivision feedback, and this paper proposes a subdivision feedback based personalized 3D facial modeling algorithm.
- Self-adaptive semantic schema mechanism for multimedia databases2
This paper presents a self-adaptive semantic schema mechanism (SSM) for multimedia databases that allows a schema to optimize for the requirements of each specific application, thereby achieving a dynamic, application-specific balance between accuracy and efficiency.
- A Robust Algorithm for Video Based Human Motion Tracking2
A robust algorithm to capture rapid human motion with self-occlusion is presented, which proposes a multiresolution search strategy: the initial candidate feature set is estimated at the low resolution image and successively refined at higher resolution levels.
- A Hybrid Motion Data Manipulation: Wavelet Based Motion Processing and Spacetime Rectification2
A hybrid approach to motion data manipulation in which motion signal is decomposed into multi-resolution levels with wavelet analysis and Spacetime rectification is proposed to reserve the essential constraints.
- Development of a web-based video management and application processing system2
This paper extends the VideoMAP architecture with specific web-oriented mechanisms, which include: Concurrency control facilities for the editing of video data among different types of users, and query profiling database which records the `histories' of various clients' query activities.
- 1
- Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs1
The proposed MIND (Meta-cognitive INtegrated Dynamic Knowledge Editing), a framework that constructs a meta-knowledge memory for self-awareness, employs game-theoretic interactions to monitor knowledge activation, and incorporates label refinement for noise-robust updates, significantly outperforms existing cognitive editing approaches.
- GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection1
More grained multi-modal feature based on the video snippet, which summarizes the main content, and text features based on the captions of original video will be introduced to further enhance the visual features of highlighted portions to reduce the redundancy in visual features.
- Counterfactual Evolution of Multimodal Datasets via Visual Programming1
Experiments show that SCOPE improves reasoning performance, exposes model blind spots, and enhances visual dialog capabilities, and is proposed to support training, a curriculum learning strategy that aligns model capacity with sample difficulty.
- 1
- DuetRAG: Collaborative Retrieval-Augmented Generation1
This work proposes a novel Collaborative Retrieval-Augmented Generation framework, DuetRAG, to simultaneously integrate the domain fintuning and RAG models to improve the knowledge retrieval quality, thereby enhancing generation quality.
- 1
- 1
- 1
- 1
- ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking1
This study converts bounding boxes to masks in reference frames with the help of the Segment Anything Model (SAM) and Alpha-Refine, and then propagate the masks to the current frame, transforming the task from Video Object Tracking (VOT) to video object segmentation (VOS).
- Unfolding and modeling the recovery process after COVID lockdowns1
A novel computational method based on electricity data to study the recovery process, and develops a deep neural network, TPG, to model recovery trends, which utilizes the graph structure learning to perceive influences between sectors.
- 1
- 1
- 1
- 1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification Track1
This work proposes a simple yet effective Mask-Level Copy-Paste data augmentation strategy to enhance out-of-distribution generalization ability so as to resist shape, pose, context, texture, occlusion, and weather domain shifts in this challenge.
- Citation Trajectory Prediction via Publication Influence Representation Using Temporal Knowledge Graph1
CTPIR is a new citation trajectory prediction framework that is able to represent the influence (the momentum of citation) of either new or existing publications using the history information of all their attributes, composed of three modules: difference-preserved graph embedding, fine-grained influence representation, and learning-based trajectory calculation.
- 1
- Visual knowledge: an attempt to explore machine creativity1
This paper discusses the issues of visual knowledge representation and its potential applications to machine creativity, and enumerates related research on imagery-thinking-based reasoning, then focuses on a special type of visualknowledge representation, i.e., visual scene graph, and reviews the problem of visual scenegraph construction and its possible applications in detail.
- Active instance matching with pairwise constraints and its application to Chinese knowledge base construction1
A novel instance matching approach Active Instance Matching with Pairwise Constraints, which can bring the human into the loop of instance matching, which is evaluated one two publicly available datasets AMINER and WIDE-NUS and then applied to the two large-scale real-world datasets, Baidu Baike and Hudong Baike, to build a Chinese knowledge base.
- 1
- The ZJU-EDL System for Entity Discovery and Linking at TAC KBP 2015.1
A fully pipelined EDL system implemented by ZJU-DCD-EDL team for the TAC 2015 EDL (Entity Discovery and Linking) task, which mainly focuses on the linking of English name mentions, is described.
- Multi-modal Retrieval via Deep Textual-Visual Correlation Learning1
The experimental results indicate the effectiveness of the proposed Deep Textual-Visual correlation learning (DTV) when applied to multi-modal retrieval.
- 1
- 1
- 1
- Image Retrieval Approach Based on Sparse Canonical Correlation Analysis1
An algorithm for solving sparse canonical correlation analysis (CCA) in a sparse framework and the experimental result demonstrates that Sparse CCA outperform CCA in the context, and substantiates the feasibility of the proposed approach to image retrieval.
- Societally connected multimedia across cultures1
This position paper proposes to define a new research area called ‘connected multimedia’, which is the study of a collection of research issues of the super-area social media that receive little attention in the literature.
- Guest Editors' Introduction: Special Section on Connected Multimedia1
This editorial is co-authored by the guest-editors who also organized the two editions of the workshop on the newly emerged theme of connected multimedia held in Hangzhou, China and in Florence, Italy, in October, 2010.
- Synthesizing style-preserving cartoons via non-negative style factorization1
A non-negative style factorization (NNSF) algorithm is presented to obtain style basis and weights and simultaneously preserve class separability and factorized style basis can be combined with heterogeneous weights to re-synthesize style-preserving features.
- Javelin: an access and manipulation interface for large displays1
The experiment and user study show that Javelin can extend user access field and enhance widget manipulation in large displays.
- Cartoon synthesis using constrained spreading activation network1
The experiment results demonstrate that the combination of the three proposed features are effective in similarity evaluation, and the candidates selected by Constrained Spreading Activation Algorithm, are more similar to the current frame compared with other algorithms.
- Notice of Violation of IEEE Publication Principles - The Explore of Some Cases with the Data Mining Techniques1
This paper describes how BT has used data mining techniques to convert volume data into high-value information which can be used to aid decision making in a number of key business processes.
- An Integrated Indexing Structure for Large-Scale Cross-Media Retrieval1
A novel integrated indexing structure for the large-scale cross-media retrieval by using a cross reference graph generated by hyperlink analysis of the webpages and a refinement process conducted by users' relevance feedbacks.
- Content subscribing mechanism in P2P streaming based on gamma distribution prediction1
Experiments show that CSM significantly reduces the content data transmission latency, and is proposed to eliminate unnecessary time delays during data relaying.
- 1
- 1
- 1
- A novel incremental mining algorithm of frequent patterns for web usage mining1
There is significant application potential to a prototype of Web log Analyzer in web usage mining that can help us to discover useful knowledge effectively, even help managers making decision.
- A Scalable Byzantine Fault Tolerant Service in Grid System.1
The scalable Byzantine fault tolerant MDS system can tolerate not only benign faults, but also arbitrary (Byzantine) ones and an optimizing key management and caching mechanism is explored in this paper.
- 1
- 1
- On Identity-Discrepancy-Contrary Connection Degree in SPA and Its Applications1
The concepts and applications of IDC connection degree andIDC connection number in SPA are introduced and the applications are provided.
- 1
- 1
- A Novel Watermarking Scheme Based on Video Content1
A novel blind MPEG video watermarking technology to hide copyright information by a slight modification of discrete cosine transformation domain in I-frames is proposed and illustrated the robustness of the scheme to several video distortions.
- Towards Comprehensive 3D Enabled Web-Based Learning1
3D model and 3D motion retrieval as an integrated part of e-learning architecture is validated and new approaches, including a novel shape representation of arbitrary 3D polygon models, are proposed as preliminary solutions, with potential applications in digital library, interactive learning, etc.
- Multi-document Summarization Based on Link Analysis and Text Classification1
A multi-document summarizer in Chinese, ACRUX, which contains three new techniques: a fuzzy classification method based on KNN (FAMKNN), Subject-Oriented Multi- document Summarization (SOMS), and Multi-document Summarizing with Link Analysis.
- Embedded Zerotree Wavelet Image Coding Algorithm Based on Single List and Recursive Scan1
A single list scheme is used in successive-approximation Quantization (SAQ), dispensing with double dynamic list of EZW algorithm, and a new Markov model based on quantization symbol field relativity for adaptive arithmetic coding algorithm is used, for higher compression efficient.
- Case-based synthesis in automatic advertising creation system1
After careful analysis of the mental behavior of a human ad designer, it is concluded that case-based approach is appropriate to its intelligent modeling.
- –
- –
- –
- –
- SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments–
Experiments in open-ended environments show that SCOPE significantly improves the completeness of the symbolic world, the success rate of plans under environment perturbations, and cross-task grounding and adaptability across diverse embodied scenarios.
- The 2nd International Workshop on Deep Multi-modal Generation and Retrieval–
This workshop aims to encourage more explorations in Deep Multimodal Generation and Retrieval, providing a platform for researchers to share insights and advancements in this rapidly evolving domain.
- ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: Semi-Supervised Video Object Segmentation–
This study introduces MSDeAOT, a variant of the AOT series that incorporates transformers at multiple feature scales that achieves the top-ranking position in the EPIC-KITCHEN VISOR Semi-supervised Video Object Segmentation Challenge.
- –
- –
- –
- –
- –
- WAB'21: 1st Workshop on Multimodal Product Identification in Livestreaming and WAB Challenge–
To promote the research on product identification in livestreaming, the largest multimodal product retrieval dataset named "Watch and Buy" (WAB) is presented and the multimodale product retrieval challenge is launched.
- –
- –
- Posterior-regularized REINFORCE for Instance Selection in Distant Supervision–
This paper adopts posterior regularization (PR) to integrate some domain-specific rules in instance selection using REINFORCE and remarkably improves the performance of the relation classifier trained on cleaned distant supervision dataset as well as the efficiency of the REIN FORCE training.
- Integrating Side Information for Boosting Machine Comprehension–
A novel attention-based architecture is presented which could feed the side information representations into word level embeddings to explore the comprehension performance and show consistent improvements of the model over various baselines.
- Detecting Temporal Proposal for Action Localization with Tree-structured Search Policy–
A reinforcement learning based method, which trains a localizer that learns a search policy that finds an optimal search path to locate a salient proposal based on the currently observing video segment in a tree structure, therefore reduces the number of video segments fed into the proposal detector.
- The Y_dcd_zju Slot Filling System for TAC KBP 2017.–
This report describes the Y dcd zju Slot Filling System for the TAC KBP 2017 Cold Start slot Filling task, which uses text-CNN (Convolutional Neural Network) model to detect sentences that contain pre-defined relations, then the NER tag to identify slot fillers.
- ZJU Participation in TAC 2016 EDL task.–
The modifications made to the last year’s system and the neural network approach for entity discovery are introduced and the results of some experiments conducted are demonstrated.
- –
- –
- –
- –
- Special section on learning from multiple evidences for large scale multimedia analysis–
This special issue is presenting the latest research on combing multiple evidences for multimedia analysis, and proposes a novel method to automatically retrieve the video shots of that action from Internet by jointly exploiting the metadata and visual features of web videos.
- –
- –
- –
- –
- –
- –
- –
- Presentation Session 2: Improving CADAL Portal Usability: Book Search, Reading, Reporting Services–
A quick book search application whose effective hybrid ranking mechanism combines content similarities with reading tendencies mined from book clickthrough logs and Ajax and Flex technologies to improve user experiences of book search, reading and reporting services in CADAL portal is presented.
- –
- Transductive Multi-Modality Video Semantic Concept Detection with Tensor Representation–
A transductive support tensor machines algorithm is proposed to train effective classifier, which preserves the intrinsic structure of the submanifold where tensorshots are sampled, and is also able to map out-of-sample data points directly.
- An encoding-based dual distance tree high-dimensional index–
The results demonstrate that this method outperforms the state-of-the-art high-dimensional search techniques such as the X-tree, VA-file, iDistance and NB-Tree, especially when the query radius is not very large.
- –
- 3D Facial Modeling for Animation: A Nonlinear Approach–
This paper presents an efficient nonlinear method for 3D facial modeling from a single image, with the support of 3D face examples, that can robustly produce3D facial models from images captured in various scenarios.
- –
- –
- Zhejiang University at TRECVID 2006–
This work develops a new approach to represent the relations between seperate shots, which mainly uses SimFusion and Locality Preserving Projections (LPP), an effective algorithm to reinforce or propagate the similarity relations between multi-modalities.
- Facial Expression Hallucination Through Eigen-Associative Learning–
A facial expression hallucination approach through eigen-associative learning (EAL) which can synthesize the imaginary facial expressions of the input face with neutral expression and is easily applied to new test data and retain high computational efficiency.
- A retrospective event detection method in news video–
In this approach, both content and time information on a news video is utilized to transcribe the news story into terms, which are divided into classes by their semantics, and a probabilistic model, composed of sub-models corresponding to the semantic classes respectively is proposed.
- Vision Character based Multi-Sensor Image Registration–
Facing with the difficulties of multi-modal images, this registration algorithm adopts the vision characters and multi-resolution based feature matching to carry out the new coarse-to-fine registration and experimental results show that this registration is superior to the classical ones.
- Automatic Video Knowledge Mining for Summary Generation Based on Un-supervised Statistical Learning–
Experiments show that the proposed approach to video summarization can generate the most concise and informative video summary.
- Multiple description wavelet image robust doding algorithm based on zeroblock coding–
The experimental results show that in MD-EZBC a damage caused by a transmission error can be diffused over the entire image with the high compression efficiency remained, and stabale quality of reconstructed image can be obtained.
- –
- Content-based Video Retrieval by Example Clip on WWW–
This paper introduces a new model of video similarity that embodies the degree of similarity completely and systematically and has resolution adaptation because it can be applied to every level of video structure.
- OOADS: An object-oriented design model for advertising CAD system–
In this paper, an object-oriented design model called OOADS is presented, around which five categories of operations, namely CMPDS (Clip/Modify/Paste/Draw/Select) are organized.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.