Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Yongtian WangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works557 from public data
- 1,955
- Multi-level Wavelet-CNN for Image Restoration934
This paper presents a novel multi-level wavelet CNN model for better tradeoff between receptive field size and computational efficiency, and shows the effectiveness of MWCNN for image denoising, single image super-resolution, and JPEG image artifacts removal.
- Proceedings of the 29th ACM International Conference on Multimedia922
A robust deep learning framework for real-world SR that randomly erases potential adversarial noises in the frequency domain of input images or features and is more insensitive to adversarial attacks and presents more stable SR results than existing models and defenses is proposed.
- Joint Detection and Identification Feature Learning for Person Search913
A new deep learning framework for person search that jointly handles pedestrian detection and person re-identification in a single convolutional neural network and converges much faster and better than the conventional Softmax loss.
- Is Faster R-CNN Doing Well for Pedestrian Detection?837
A very simple but effective baseline for pedestrian detection, using an RPN followed by boosted forests on shared, high-resolution convolutional feature maps, presenting competitive accuracy and good speed.
- Cost-Effective Active Learning for Deep Image Classification756
This paper proposes a novel active learning (AL) framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner and incorporates deep convolutional neural networks into AL.
- Deep feature learning with relative distance comparison for person re-identification687
A scalable distance driven feature learning framework based on the deep neural network for person re-identification that achieves very promising results and outperforms other state-of-the-art approaches.
- Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning620
This work extends Faster /Mask R-CNN by proposing meta-learning over RoI (Region-of-Interest) features instead of a full image feature, and introduces a Predictor-head Remodeling Network (PRN) that shares its main backbone with Faster / Mask R- CNN.
- Unsupervised Image Super-Resolution Using Cycle-in-Cycle Generative Adversarial Networks594
This work proposes a Cycle-in-Cycle network structure with generative adversarial networks (GAN) as the basic component to tackle the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable.
- 584
- Look into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing516
A new benchmark Look into Person (LIP) is introduced that makes a significant advance in terms of scalability, diversity and difficulty, and a novel self-supervised structure-sensitive learning approach, which imposes human pose structures into parsing results without resorting to extra supervision.
- Toward Characteristic-Preserving Image-Based Virtual Try-On Network504
A new fully-learnable Characteristic-Preserving Virtual Try-On Network (CP-VTON) for addressing all real-world challenges in this task, and achieves the state-of-the-art virtual try-on performance both qualitatively and quantitatively.
- Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift440
This paper proposes a deep cocktail network (DCTN) to battle the domain and category shifts among multiple sources and evaluates DCTN in three domain adaptation benchmarks, which clearly demonstrate the superiority of the framework.
- Knowledge-Embedded Routing Network for Scene Graph Generation432
This work finds that the statistical correlations between object pairs and their relationships can effectively regularize semantic space and make prediction less ambiguous, and thus well address the unbalanced distribution issue.
- Component Divide-and-Conquer for Real-World Image Super-Resolution419
This paper proposes a Component Divide-and-Conquer model and a Gradient-Weighted loss for SR, exploring the utility of guiding SR model with low-level image components, and proposes a feasible way to balance the difficulties of image components for SR.
- 412
- 389
- Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI384
This survey gives a comprehensive exploration of the latest advancements in Embodied AI, exploring the complexities of MLMs in virtual and real embodied agents, highlighting their significance in facilitating interactions in digital and physical environments.
- Instance-Level Human Parsing via Part Grouping Network383
This work makes the first attempt to explore a detection-free Part Grouping Network (PGN) for efficiently parsing multiple people in an image in a single pass and outperforms all state-of-the-art methods on PASCAL-Person-Part dataset.
- Look into Person: Joint Body Parsing & Pose Estimation Network and a New Benchmark379
A new benchmark named “Look into Person (LIP)” is introduced that provides a significant advancement in terms of scalability, diversity, and difficulty, which are crucial for future developments in human-centric analysis.
- Semantic Object Parsing with Graph LSTM370
The Graph Long Short-Term Memory network is proposed, which is the generalization of LSTM from sequential data or multi-dimensional data to general graph-structured data.
- Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition366
A Semantic-Specific Graph Representation Learning (SSGRL) framework that consists of a semantic decoupling module that incorporates category semantics to guide learning semantic-specific representations and a semantic interaction module that correlates these representations with a graph built on the statistical label co-occurrence and explores their interactions via a graph propagation mechanism.
- 360
- GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning351
This paper proposes a Geometric Question Answering dataset GeoQA, containing 4,998 geometric problems with corresponding annotated programs, which illustrate the solving process of the given problems, and introduces a Neural Geometric Solver (NGS) to address geometric problems by comprehensively parsing multimodal information and generating interpretable programs.
- Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering348
Extensive experiments demonstrate the superiority of the CMCIR in discovering visual-linguistic causal structures and achieving robust event-level visual question answering.
- 346
- Multi-label Image Recognition by Recurrently Discovering Attentional Regions338
This work achieves the interpretable and contextualized multi-label image classification by developing a recurrent memorized-attention module that demonstrates superior performances over other existing state-of-the-arts in both accuracy and efficiency.
- Instance-Level Salient Object Segmentation297
This paper presents a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image, and proposes a multiscale saliency refinement network, which generates high-quality salient region masks and salient object contours.
- Crowd Counting With Deep Structured Scale Integration Network289
A novel Deep Structured Scale Integration Network (DSSINet) for crowd counting is proposed, which addresses the scale variation of people by using structured feature representation learning and hierarchically structured loss function optimization.
- BeautyGAN283
A dual input/output Generative Adversarial Network that enables the network to learn translation on instance-level through unsupervised adversarial learning, and could generate visually pleasant makeup faces and accurate transferring results.
- Contextualized Spatial–Temporal Network for Taxi Origin-Destination Demand Prediction279
A novel contextualized spatial–temporal network (CSTN) for taxi origin-destination demand prediction, which consists of three components for the modeling of local spatial context (LSC), temporal evolution context (TEC), and global correlation context (GCC), respectively.
- Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining262
A non-locally enhanced encoder-decoder network framework that can effectively remove rain-streaks on rainy image of various densities while well preserving the image details, which achieves significant improvements over the recent state-of-the-art methods.
- 250
- End-to-End Deep Learning for Person Search.242
An end-to-end deep learning framework to jointly handle pedestrian detection and person re-identification is proposed and a random sampling softmax loss is proposed to effectively train the model under the supervision of sparse and unbalanced labels.
- Proposal-Free Network for Instance-Level Object Segmentation239
A Proposal-Free Network (PFN) is proposed to address the instance-level object segmentation problem, which outputs the numbers of instances of different categories and the pixel-level information on i) the coordinates of the instance bounding box each pixel belongs to, and ii) the confidences ofDifferent categories for each pixel, based on pixel-to-pixel deep convolutional neural network.
- 237
- Attention-Aware Face Hallucination via Deep Reinforcement Learning235
A novel Attention-aware Face Hallucination (Attention-FH) framework which resorts to deep reinforcement learning for sequentially discovering attended patches and then performing the facial part enhancement by fully exploiting the global interdependency of the image.
- Clothing Co-Parsing by Joint Image Segmentation and Labeling216
This paper aims at developing an integrated system of clothing co-parsing, in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic configurations, and proposes a data-driven framework consisting of two phases of inference.
- DreamEditor: Text-Driven 3D Scene Editing with Neural Fields213
This paper proposes DreamEditor, a novel framework that enables users to perform controlled editing of neural fields using text prompts by representing scenes as mesh-based neural fields, and generates highly realistic textures and geometry.
- Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning210
In comparison to conventional human-designed networks, RL-Restore is capable of restoring images corrupted with complex and unknown distortions in a more parameter-efficient manner using the dynamically formed toolchain1.
- Graphonomy: Universal Human Parsing via Graph Transfer Learning204
A new universal human parsing agent, named ``Graphonomy", is proposed, which incorporates hierarchical graph transfer learning upon the conventional parsing network to encode the underlying label semantic structures and propagate relevant semantic information.
- End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis203
An End-to-End Knowledge-routed Relational Dialogue System (KR-DS) that seamlessly incorporates rich medical knowledge graph into the topic transition in dialogue management, and makes it cooperative with natural language understanding and natural language generation is proposed.
- Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation201
This work proposes to modularize the large search space of NAS into blocks to ensure that the potential candidate architectures are fully trained, and distill the neural architecture (DNA) knowledge from a teacher model to supervise the block-wise architecture search, which significantly improves the effectiveness of NAS.
- Single View Stereo Matching201
This paper shows for the first time that the monocular depth estimation problem can be reformulated as two sub-problems, a view synthesis procedure followed by stereo matching, with two intriguing properties, namely i) geometrical constraints can be explicitly imposed during inference; ii) demand on labelled depth data can be greatly alleviated.
- Deep Reasoning with Knowledge Graph for Social Relationship Understanding198
This work has found that the interplay between these two factors can be effectively modeled by a novel structured knowledge graph with proper message propagation and attention and can be efficiently integrated into the deep neural network architecture to promote social relationship understanding.
- Crowd Counting using Deep Recurrent Spatial-Aware Network198
A unified neural network framework, named Deep Recurrent Spatial-Aware Network, which adaptively addresses the two issues in a learnable spatial transform module with a region-wise refinement process, and achieves an improvement on the largest dataset WorldExpo’10 and the most challenging dataset UCF-CC.
- 189
- Semantic Object Parsing with Local-Global Long Short-Term Memory188
A novel deep Local-Global Long Short-Term Memory architecture to seamlessly incorporate short-distance and long-distance spatial dependencies into the feature learning over all pixel positions and demonstrates the significant superiority of this LG-LSTM over other state-of-the-art methods.
- Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting184
It is found that incorporating optical and thermal information can greatly help to recognize pedestrians and the proposed approach is universal for multimodal crowd counting and is also capable to achieve superior performance on the ShanghaiTechRGBD dataset.
- 184
- Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition182
This paper investigates how to integrate the semantic relationship propagation between AUs in a deep neural network framework to enhance the feature representation of facial regions, and proposes an AU semantic relationship embedded representation learning (SRERL) framework.
- Learning Warped Guidance for Blind Face Restoration178
Experiments show that the GFRNet not only performs favorably against the state-of-the-art image and face restoration methods, but also generates visually photo-realistic results on real degraded facial images.
- Recurrent Attentional Reinforcement Learning for Multi-Label Image Recognition175
A recurrent attention reinforcement learning framework to iteratively discover a sequence of attentional and informative regions that are related to different semantic objects and further predict label scores conditioned on these regions to facilitate multi-label recognition.
- LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling172
This paper addresses the problem of semantic labeling of RGB-D scenes by developing a novel Long Short-Term Memorized Context Fusion (LSTM-CF) Model that captures and fuses contextual information from multiple channels of photometric and depth data, and incorporating this model into deep convolutional neural networks (CNNs) for end-to-end training.
- Symbolic Graph Reasoning Meets Convolutions169
A new Symbolic Graph Reasoning (SGR) layer is proposed, which performs reasoning over a group of symbolic nodes whose outputs explicitly represent different properties of each semantic in a prior knowledge graph.
- Matching-CNN meets KNN: Quasi-parametric human parsing169
This work aims to develop a new solution with the advantages of both methodologies, namely supervision from annotated data and the flexibility to use newly annotated (possibly uncommon) images, and present a quasi-parametric human parsing model.
- 166
- Active Self-Paced Learning for Cost-Effective and Progressive Face Identification165
A novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals by naturally combining two recently rising techniques: active learning and self-paced learning, capable of automatically annotating new instances and incorporating them into training under weak expert recertification.
- 162
- PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report161
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones and proposes solutions that significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.
- DISC: Deep Image Saliency Computing via Progressive Representation Learning161
This work provides a novel deep image saliency computing (DISC) framework, and utilizes the deep convolutional neural network (CNN) to learn the saliency representation in a progressive manner, built upon two stacked CNNs.
- End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning153
This paper proposes a novel approach for photo-sketch generation, aiming to automatically transform face photos into detail-preserving personal sketches, and develops a fully convolutional network to learn the end-to-end photo-Sketch mapping.
- 147
- Person Search in a Scene by Jointly Modeling People Commonness and Person Uniqueness146
This paper proposes a unified framework which jointly models the commonness of people and the uniqueness of a person and demonstrates superior performance of this approach on public benchmarks compared with the sequential combination of the state-of-the-art detection and identification algorithms.
- LSTM Pose Machines142
It is shown that if the weight sharing scheme is imposed to the multi-stage CNN, it could be re-written as a Recurrent Neural Network (RNN), which decouples the relationship among multiple network stages and results in significantly faster speed in invoking the network for videos.
- A stochastic graph grammar for compositional object representation and recognition140
A hierarchical generative model for representing and recognizing compositional object categories with large intra-category variance that combines the power of a stochastic context free grammar (SCFG) to express the variability of part configurations, and a Markov random field (MRF) to represent the pictorial spatial relationships between these parts.
- Semi-Supervised Video Salient Object Detection Using Pseudo-Labels136
This paper presents an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module and proposes a novel method for generating pixel-level pseudo-labels from sparsely annotated frames.
- Weakly Supervised Salient Object Detection Using Image Labels135
This paper proposes to use the combination of a coarse salient object activation map from the classification network and saliency maps generated from unsupervised methods as pixel-level annotation, and develops a simple yet very effective algorithm to train fully convolutional networks for salient object detection supervised by these noisy annotations.
- Collaborative Training Between Region Proposal Localization and Classification for Domain Adaptive Object Detection131
This paper is the first to reveal that the region proposal network (RPN) and region proposal classifier~(RPC) in the endemic two-stage detectors demonstrate significantly different transferability when facing large domain gap.
- Tree-Structured Policy Based Progressive Reinforcement Learning for Temporally Language Grounding in Video127
A novel Tree-Structured Policy based Progressive Reinforcement Learning (TSP-PRL) framework to sequentially regulate the temporal boundary by an iterative refinement process, which contributes to efficiently decomposing complex policies into an interpretable primitive action.
- Prototypical Graph Contrastive Learning126
This article proposes a prototypical graph contrastive learning approach, which models the underlying semantic structure of the graph data via clustering semantically similar graphs into the same group and simultaneously encourages the clustering consistency for different augmentations of the same graph.
- Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection126
This paper presents a principled Self-supervised Sample Mining (SSM) process accounting for the real challenges in object detection, and proposes a new AL framework for gradually incorporating unlabeled or partially labeled data into the model learning while minimizing the annotating effort of users.
- 123
- TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts121
TIP-Editor is proposed, a 3D scene editing framework that accepts both text and image prompts and a 3D bounding box to specify the editing region, and employs a stepwise 2D personalization strategy to better learn the representation of the existing scene and the reference image.
- Learning Support Correlation Filters for Visual Tracking120
This paper derives an equivalent formulation of a SVM model with the circulant matrix expression and presents an efficient alternating optimization method for visual tracking and extends the SCF-based tracking algorithm with multi-channel features, kernel functions, and scale-adaptive approaches to further improve the tracking performance.
- Monocular Depth Estimation with Affinity, Vertical Pooling, and Label Enhancement120
This work explicitly model the relationships of different image locations with an affinity layer and combine absolute and relative features in an end-to-end network to obtain global understanding of the image depth and exploit residual learning to help depth refinement.
- Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding119
This work investigates simultaneously predicting categories of different levels in the hierarchy and integrating this structured correlation information into the deep neural network by developing a novel Hierarchical Semantic Embedding (HSE) framework.
- GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems117
This work proposes a new evaluation metric GRADE, which stands for Graph-enhanced Representations for Automatic Dialogue Evaluation, which incorporates both coarse-grained utterance-level contextualized representations and fine- grained topic-level graph representations to evaluate dialogue coherence.
- Recurrent 3D Pose Sequence Machines116
A Recurrent 3D Pose Sequence Machine (RPSM) is presented to automatically learn the image-dependent structural constraint and sequence-dependent temporal context by using a multi-stage sequential refinement.
- Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation115
A geometry-aware 3D representation for the human pose is proposed to address this limitation by using multiple views in a simple auto-encoder model at the training stage and only 2D keypoint information as supervision, and injecting the representation as a robust 3D prior.
- 111
- 107
- Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid107
A novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both global and local representations in multiple scales, and achieves considerable improvements on all empirical settings.
- A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition106
A novel deep structured model, which adaptively decomposes an activity instance into temporal parts using the convolutional neural networks, and incorporates latent temporal structure into the deep model, accounting for large temporal variations of diverse human activities.
- 103
- Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation101
A creative Leap-of-Thought (CLoT) paradigm is introduced to improve LLM's LoT ability and boosts creative abilities in various tasks like “cloud guessing game” and “divergent association task”.
- An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation101
This work proposes to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations and achieves the state-of-the-art performance on two challenging domain adaptation tasks for semantic segmentation.
- Interpretable Structure-Evolving LSTM101
The effectiveness of structure-evolving LSTM in the application of semantic object parsing is evaluated and it is demonstrated to have an advantage over state-of-the-art L STM models on standard benchmarks.
- Blending-Target Domain Adaptation by Adversarial Meta-Adaptation Networks100
Empirical results show that BTDA is a quite challenging transfer setup for most existing DA algorithms, yet AMEAN significantly outperforms these state-of-the-art baselines and effectively restrains the negative transfer effects in BTDA.
- 99
- Saliency Detection on Light Field98
Experimental results show that this approach can achieve 0.6--6.7% relative improvements over state-of-the-art methods in terms of the F-measure and Precision metrics, which demonstrates the effectiveness of the proposed approach.
- 3D Human Pose Machines with Self-supervised Learning97
A simple yet effective self-supervised correction mechanism to learn all intrinsic structures of human poses from abundant images and develops a 3D human pose machine, which jointly integrates the 2D spatial relationship, temporal smoothness of predictions and 3D geometric knowledge.
- 97
- Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking96
This work examines the insecurity of current best-performing ReID models by proposing a learning-to-mis-rank formulation to perturb the ranking of the system output and performs a back-box attack by developing a novel multi-stage network architecture that pyramids the features of different levels to extract general and transferable features for the adversarial perturbations.
- 96
- 95
- Correntropy Induced L2 Graph for Robust Subspace Clustering95
This paper proposes a new robust clustering method by using the correntropy induced metric, which is robust for handling the non-Gaussian and impulsive noises and extends the method for dealing with the data with outlier rows/features.
- SCAN: Self-and-Collaborative Attention Network for Video Person Re-Identification92
A novel and practical deep architecture for video person re-identification termed self-and-collaborative attention network (SCAN), which adopts the video pairs as the input and outputs their matching scores and can be predicted by the binary classifier.
- Discriminatively Trained And-Or Graph Models for Object Shape Detection92
This paper proposes a novel structural optimization algorithm to discriminatively train the And-Or model from weakly annotated data and demonstrates the effectiveness to perform robust shape-based object detection against background clutter and outperforms the other state-of-the-art approaches.
- SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training91
An asymmetric graph-based encoder-decoder pre-training architecture named SkeletonMAE is built, which embeds skeleton joint sequence into graph convolutional network and reconstructs the masked skeleton joints and edges based on the prior human topology knowledge.
- Structured Semantic Transfer for Multi-Label Recognition with Partial Labels88
A structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i.e., merely some labels are known while other labels are missing (also called unknown labels) per image is proposed.
- Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition88
This work investigates how to unify rich professional knowledge with deep neural network architectures and proposes a Knowledge-Embedded Representation Learning (KERL) framework for handling the problem of fine-grained image recognition, which has several appealing properties.
- PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Edge-Preserving Coherence88
A unified framework called pixelwise image saliency aggregating (PISA) various bottom-up cues and priors is proposed, which generates spatially coherent yet detail-preserving, pixel-accurate, and fine-grained saliency, and overcomes the limitations of previous methods.
- Fine-Grained Image Captioning With Global-Local Discriminative Objective86
A novel global-local discriminative objective that is formulated on top of a reference model to facilitate generating fine-grained descriptive captions and outperforms the baseline methods by a sizable margin and achieves competitive performance over existing leading approaches.
- 86
- Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning81
This work proposes a novel cross-modal matching strategy to detect OOD samples that substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.
- Efficient Crowd Counting via Structured Knowledge Transfer81
A novel Structured Knowledge Transfer (SKT) framework, which fully exploits the structured knowledge of a well-trained teacher network to generate a lightweight but still highly effective student network that can derive the layer-wise and cross-layer knowledge from the teacher networkto learn compact yet effective features.
- 81
- Causal Reasoning Meets Visual Representation Learning: A Prospective Study76
This paper conducts a comprehensive review of existing causal reasoning methods for visual representation learning, covering fundamental theories, models, and datasets, and proposes some prospective challenges, opportunities, and future research directions for benchmarking causal reasoning algorithms inVisual representation learning.
- Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems75
A simple but efficient method to make the first attempt to represent the equations of various MWPs uniformly, and a semantically-aligned universal tree-structured solver (SAU-Solver) based on an encoder-decoder framework is proposed to resolve multiple types of MWPs in a unified model, benefiting from the UET representation.
- Attentive Crowd Flow Machines75
A unified neural network module, called Attentive Crowd Flow Machine~ (ACFM), which is able to infer the evolution of the crowd flow by learning dynamic representations of temporally-varying data with an attention mechanism, and achieves significant improvements over the state-of-the-art methods.
- Kernel sparse representation for time series classification74
A family of Gaussian elastic matching kernels was introduced to deal with the problems of time shift and nonlinear representation and Experimental results showed that the proposed methods generally outperformed state-of-the-arts methods in terms of classification accuracy.
- Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks73
The Neural-Symbolic Solver (NS-Solver) is proposed to explicitly and seamlessly incorporate different levels of symbolic constraints by auxiliary tasks to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions.
- Adaptive Temporal Encoding Network for Video Instance-level Human Parsing71
This paper introduces a novel Adaptive Temporal Encoding Network (ATEN) that alternatively performs temporal encoding among key frames and flow-guided feature propagation from other consecutive frames between two key frames to achieve a good balance between frame-level accuracy and time efficiency.
- Generative Semantic Manipulation with Mask-Contrasting GAN70
This work introduces a contrasting GAN (contrast-GAN) with a novel adversarial contrasting objective which is able to perform all types of semantic translations with one category-conditional generator, and proposes a novel mask-Conditional contrast-GAN architecture to enable disentangle image background with object semantic changes.
- Adaptively Connected Neural Networks69
This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects: first, ACNet employs a flexible way to switch global and local inference in processing the internal feature representations by adaptively determining the connection status among the feature nodes.
- 69
- Solving Inefficiency of Self-supervised Representation Learning68
This paper proposes a novel self-supervised learning framework using a truncated triplet loss that demonstrates the model’s superiority over the latest state-of-the-art methods by a clear margin.
- Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos68
A Boundary Adaptive Refinement framework that resorts to reinforcement learning (RL) to guide the process of progressively refining the temporal boundary and is offered the first attempt to extend RL to temporal localization task with weak supervision.
- Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation67
A Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues and addresses the real-world challenges that the disease- symptom correlations of each disease may vary or evolve along with more diagnostic cases.
- 67
- DRPose3D: Depth Ranking in 3D Human Pose Estimation66
This paper proposes a two-stage depth ranking based method that outperforms the state-of-the-art methods in the Human3.6M benchmark for all three testing protocols, indicating that depth ranking is an essential geometric feature which can be learned to improve the 3D pose estimation.
- 65
- Being Comes from Not-Being: Open-Vocabulary Text-to-Motion Generation with Wordless Training65
This paper pretrain a motion generator that learns to reconstruct the full motion from the masked motion, inspired by the prompt learning in NLP, and proposes the first text-pose alignment model for measuring the alignment between texts and 3D poses.
- Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation65
A novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM) is proposed, which fully exploits heterogeneous information of historical data to jointly learn the evolutionary patterns of OD and DO ridership and develops a unified Seq2Seq network to forecast the future OD andDO ridership simultaneously.
- Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition65
This work proposes a novel Adversarial Graph Representation Adaptation (AGRA) framework that unifies graph representation propagation with adversarial learning for cross-domain holistic-local feature co-adaptation and shows that the proposed AGRA framework achieves superior performance over previous state-of-the-art methods.
- Bidirectional Graph Reasoning Network for Panoptic Segmentation64
A Bidirectional Graph Reasoning Network (BGRNet), which incorporates graph structure into the conventional panoptic segmentation network to mine the intra-modular and inter- modular relations within and between foreground things and background stuff classes, and proposes a Biddirectional Graph Connection Module to diffuse information across branches in a learnable fashion.
- Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains64
This work proposes a self-adaptation approach for CNN training, utilizing both synthetic training data and stereo pairs in the new domain (without ground-truths), and forms an iterative optimization problem with graph Laplacian regularization.
- SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models63
This work proposes a simple-yet-effective parameter-efficient fine-tuning approach called the Semantic Understanding and Reasoning adapter (SUR-adapter) for pre-trained diffusion models that can make text-to-image diffusion models easier to use with better user experience.
- 63
- Reversible Recursive Instance-Level Object Segmentation61
This work proposes a novel Reversible Recursive Instance-level Object Segmentation (R2-IOS) framework that consists of a reversible proposal refinement sub-network that predicts bounding box offsets for refining the object proposal locations, and an instance-level segmentation sub- network that generates the foreground mask of the dominant object instance in each proposal.
- 60
- AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay59
Extensive evaluations show that AlphaAgent outperforms traditional and LLM-based methods in mitigating alpha decay across bull and bear markets, consistently delivering significant alpha in Chinese CSI 500 and U.S. S&P 500 markets over the past four years.
- 59
- Learning a Wavelet-Like Auto-Encoder to Accelerate Deep Neural Networks59
A Wavelet-like Auto-Encoder that decomposes the original input image into two low-resolution channels (sub-images) and incorporate the WAE into the classification neural networks for joint training and provides an interpretable way to preserve the main components of the input image for classification.
- Interpretable Visual Question Answering by Reasoning on Dependency Trees58
A novel neural network model that performs global reasoning on a dependency tree parsed from the question and is capable of building an interpretable visual question answering (VQA) system that gradually derives image cues following question-driven parse-tree reasoning.
- 58
- IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-Sensing Images57
This work presents an iterative diffusion process for cloud removal (IDF-CR), which exhibits strong generative capabilities to achieve component divide-and-conquer (CDC) cloud removal and refine the stable diffusion by implementing ControlNet.
- 57
- 57
- Cross-Modal Causal Representation Learning for Radiology Report Generation56
A two-stage framework named Cross-Modal Causal Representation Learning (CMCRL), consisting of the Radiological Cross-modal Alignment and Reconstruction Enhanced (RadCARE) pre-training and the Visual-Linguistic Causal Intervention (VLCI) fine-tuning, which establishes robust cross-modal correlations even with incomplete data.
- Integrating Graph Partitioning and Matching for Trajectory Analysis in Video Surveillance56
This paper proposes a unified approach for global trajectory analysis that recovers target trajectories based on a short sequence of video frames, e.g., 15 frames, and outperforms the state-of-the-art methods.
- NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results54
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single image super- resolution.
- 53
- 52
- Context-Aware Semantic Inpainting52
An improved GAN-based framework consists of a fully convolutional design for the generator which helps to better preserve spatial structures and a joint loss function with a revised perceptual loss to capture high-level semantics in the context.
- 51
- 51
- Visual Causal Scene Refinement for Video Question Answering50
To discover critical video segments and frames that serve as the visual causal scene for generating reliable answers, a causal analysis of VideoQA is presented and a framework for cross-modal causal relational reasoning, named Visual Causal Scene Refinement (VCSR), is proposed.
- 50
- 50
- Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding50
A novel data set named knowledge-routed visual question reasoning is proposed, which aims to cut off the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question Reasoning.
- 50
- SIRST-5K: Exploring Massive Negatives Synthesis With Self-Supervised Learning for Robust Infrared Small Target Detection49
A negative augmentation approach is proposed to generate massive negatives for self-supervised learning to enrich diversity as well as maintain semantic invariance in single-frame infrared small target (SIRST) detection.
- Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism49
Comprehensive experiments show that ROSETTA yields state-of-the-art performance on both task-based and class-based continual object detection.
- 49
- Representing and recognizing objects with massive local image patches49
This paper presents a novel generative learning algorithm that automatically generates features (@e-balls) from local image patches rather than designing marginal feature carefully and category-specifically and uses these selected @e-ball features to explain object in a generative way and are mutually independent.
- Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion48
This work proposes a novel reward-adaptive reinforcement learning method for biped locomotion, allowing the control policy to be simultaneously optimized by multiple criteria using a dynamic mechanism, leading to hybrid policy gradients.
- 48
- 48
- 47
- Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels46
This work proposes a novel heterogeneous semantic transfer (HST) framework that consists of two complementary transfer modules that explore both within-image and cross-image semantic correlations to transfer the knowledge possessed by known labels to generate pseudo labels for the unknown labels.
- Understanding Self-attention Mechanism via Dynamical System Perspective46
It is shown that the intrinsic stiffness phenomenon (SP) in the high-precision solution of ordinary differential equations (ODEs) also widely exists in high-performance neural networks (NN), and the ability of NN to measure SP at the feature level is necessary to obtain high performance and is an important factor in the difficulty of training NN.
- 45
- 45
- Semantic event representation and recognition using syntactic attribute graph grammar45
An attribute graph grammar for events modeling models the variability of semantic events by a set of meaningful ''event components'' with the spatio-temporal constraints to solve the problem of high-level understanding of video sequence.
- 44
- A Prior Guided Wavelet-Spatial Dual Attention Transformer Framework for Heavy Rain Image Restoration44
- AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results43
This paper introduces the real image Super-Resolution challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020, and gauges the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.
- Cost-Effective Object Detection: Active Sample Mining With Switchable Selection Criteria43
By developing a principled active sample mining (ASM) framework, it is demonstrated that cost-effective mining samples from these unlabeled majority data are a key to train more powerful object detectors while minimizing user effort.
- Visual Question Reasoning on General Dependency Tree43
A novel reasoning network called Adversarial Composition Modular Network (ACMN), capable of building an interpretable VQA system that gradually dives the image cues following a question-driven reasoning route and makes global reasoning by incorporating the learned knowledge of all attention modules in a principled manner.
- 43
- 43
- Unsupervised Domain Adaptive Salient Object Detection through Uncertainty-Aware Pseudo-Label Learning42
This paper proposes to learn saliency from synthetic but clean labels, which naturally has higher pixel-labeling quality without the effort of manual annotations, and outperforms the existing state-of-the-art deep unsupervised SOD methods on several benchmark datasets, and is even comparable to fully-supervised ones.
- 42
- ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection41
An effective coefficient scaling framework ScaleLong is proposed that scales the coefficients of LSC in UNet and better improves the training stability of UNet.
- 41
- Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition41
This work proposes a novel framework that unifies template retrieval and sentence generation to handle both common and rare abnormality while ensuring the semantic coherency among the detected medical terms, and exploits hybrid-knowledge co-reasoning.
- Layout-Graph Reasoning for Fashion Landmark Detection41
The first Fine-grained Fashion Landmark Dataset (FFLD) containing 200k images annotated with at most 32 key-points for 13 clothes types is contributed and extensive experiments on two public fashion landmark datasets demonstrate the superiority of the model.
- 40
- VideoQA in the Era of LLMs: An Empirical Study39
This work conducts a timely and comprehensive study of Video-LLMs’ behavior in VideoQA, aiming to elucidate their success and failure modes, and provide insights towards more human-like video understanding and question answering.
- Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition39
This work develops a novel adversarial meta sampling (AMS) approach to improve MML-ASR, and demonstrates the applicability of AMS to other low-resource speech tasks and transfer learning ASR approaches.
- Face Hallucination by Attentive Sequence Optimization with Reinforcement Learning39
A novel attention-aware face hallucination (Attention-FH) framework is developed, which recurrently learns to attend a sequence of patches and performs facial part enhancement by fully exploiting the global interdependency of the image.
- Painterly animation using video semantics and feature correspondence39
An interactive system that stylizes an input video into a painterly animation using a rich set of example-based brush strokes and proposes a series of novel teniques to reduce the scintillation effects.
- Layered graph matching by composite cluster sampling with collaborative and competitive interactions39
- Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs38
This work proposes to employ multiple intelligent agents to work collaboratively in a reasoning-and-consensus paradigm for elevated reasoning faithfulness and to increase faithfulness and causality for knowledge-based reasoning.
- Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction38
A novel neural network framework termed cross-modal message propagation network (CMMPNet) is introduced, which fully benefits the complementary different modal data (i.e., aerial images and crowdsourced trajectories), and outperforms current state-of-the-art methods by large margins.
- DARI: Distance Metric and Representation Integration for Person Verification37
This work proposes an end-to-end learning framework called DARI, i.e. Distance metric And Representation Integration, and validates the effectiveness of DARI in the challenging task of person verification.
- 37
- 36
- Motion-transformer36
A novel transformer-based model called Motion-Transformer is proposed to sufficiently capture the temporal dependencies via self-supervised pre-training on the sequence of human action to outperforms previous state-of-the-art methods.
- 36
- 36
- Depthwise Nonlocal Module for Fast Salient Object Detection Using a Single Thread35
A novel depthwise nonlocal module (DNL) is proposed, which implicitly models contrast via harvesting intrachannel and interchannel correlations in a self-attention manner and achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
- Facial Landmark Machines: A Backbone-Branches Architecture With Progressive Representation Learning35
This paper proposes a novel cascaded backbone-branches fully convolutional neural network (BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings and confirms that high-quality facial landmarks localized with the proposed network can also improve the precision and recall of face detection.
- 35
- Towards Real-World Burst Image Super-Resolution: Benchmark and Method34
A large-scale real-world burst super-resolution dataset, i.e., RealBSR, is established to explore the faithful reconstruction of image details from multiple frames and a Federated Burst Affinity network (FBAnet) is introduced to investigate non-trivial pixel-wise displacements among images under real- world image degradation.
- Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-Identification34
A novel Multi-Stage Spatial-Temporal Aggregation Transformer with two novel designed proxy embedding modules to address the critical issue of extracting local attributes and global identity information for the person re-identification task.
- Towards Quantifiable Dialogue Coherence Evaluation34
Experimental results show that the model trained by QuantiDCE presents stronger correlations with human judgements than the other state-of-the-art metrics.
- Object categorization with sketch representation and generalized samples34
This framework for object categorization via sketch graphs that incorporate shape and structure information is presented, a hierarchical structure that combines the reconfigurability of a stochastic context free grammar with the constraints of a Markov random field with state-of-the-art performance.
- 34
- ODMixer: Fine-Grained Spatial-Temporal MLP for Metro Origin-Destination Prediction33
This work learns traffic evolution from the perspective of all OD pairs and proposes a fine-grained spatial-temporal MLP architecture for metro OD prediction, namely ODMixer, which has double-branch structure and involves the Channel Mixer, the Multi-view Mixer, and the Bidirectional Trend Learner.
- Learning Patch-Based Dynamic Graph for Visual Tracking33
This work aims to learn a more robust object representation for visual tracking that outperforms the state-of-the-art tracking methods on two standard benchmarks, i.e., OTB100 and NUS-PRO.
- Deep Structured Scene Parsing by Learning with Image Descriptions33
This paper proposes a deep architecture consisting of a convolutional neural network extracting the image representation for pixelwise object labeling and a recursive neural network discovering the hierarchical object structure and the inter-object relations and decomposes each sentence into a semantic tree.
- An expressive deep model for human action parsing from a single image33
This paper proposes to develop an expressive deep model to naturally integrate human layout and surrounding contexts for higher level action understanding from still images, and outperforms the state-of-the-art approaches.
- 32
- Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima31
This paper analyzes multimodal recommender systems from the novel perspective of flat local minima and proposes a concise yet effective gradient strategy called Mirror Gradient (MG), which can implicitly enhance the model's robustness during the optimization process, mitigating instability risks arising from multimodal information inputs.
- Contrastive Transformer Learning With Proximity Data Generation for Text-Based Person Search31
A simple yet effective dual Transformer model for text-based person search that achieves state-of-the-art performance without any special design for local feature alignment or side information is proposed and a proximity data generation (PDG) module is proposed to automatically produce more diverse data for cross-modal training.
- Unsupervised Multi-View Clustering by Squeezing Hybrid Knowledge From Cross View and Each View31
A new multi-view clustering method, low- rank subspace multi- view clustering based on adaptive graph regularization, and two new data matrix decomposition models are constructed into a unified optimization model to preserve the internal structural features of the data.
- A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning31
To improve the efficiency of HMC, a new regime to automatically control the length of trajectories is proposed, which allows the algorithm to move with adaptive step sizes along the search direction at different positions and revisit the reason for high computational cost of adversarial training under the view of MCMC and design a new generative method called Contrastive Adversarial Training (CAT).
- 31
- Spatial–Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation30
This work proposes a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial co-occurrence and temporal transition correlations into the multi-head cross-attention mechanism to learn more representative relationship representations.
- Marker-less registration based on template tracking for augmented reality30
An efficient markerless registration algorithm is presented for both outdoor and indoor AR system, and a marker-less AR system is described using this algorithm, and the system architecture and working flow are also proposed.
- 30
- Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration29
This paper introduces the Multi-Label Confidence Calibration (MLCC) task, aiming to provide well-calibrated confidence scores in multi-label scenarios, and proposes the Dynamic Correlation Learning and Regularization (DCLR) algorithm, which leverages multi-grained semantic correlations to better model semantic confusion for adaptive regularization.
- AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition29
This work explores the correlations among the action units and facial expressions, and devise an AU-Expression Knowledge Constrained Representation Learning (AUE-CRL) framework to learn the AU representations without AU annotations and adaptively use representations to facilitate facial expression recognition.
- 29
- 29
- DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment28
DiffCloth is introduced, a diffusion-based pipeline for cross-modal garment synthesis and manipulation, which empowers diffusion models with flexible compositionality in the fashion domain by structurally aligning the cross-modal semantics.
- OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup28
This work finds that the occlusions can be simulated by a novel semantically-guided mixup module, which can generate semantic-specific occluded images that work together with the try-on images to facilitate training a de-occlusiontry-on (DOC-VTON) framework.
- Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation28
A Dynamic Reinforced Instruction Attacker (DR-Attacker), which learns to mislead the navigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps, is proposed.
- Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition28
This work introduces Wav-BERT, a cooperative acoustic and linguistic representation learning method to fuse and utilize the contextual information of speech and text and significantly outperforms the existing approaches and achieves state-of-the-art performance on low-resource speech recognition.
- DreamArtist: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter27
This work proposes a simple yet effective framework, namely DreamArtist, which adopts a novel positive-negative prompt-tuning learning strategy on the pre-trained diffusion model, and it has shown to well handle the trade-off between the accurate controllability and fidelity of image generation with only one reference example.
- YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multibranch Feature Interaction27
YOLO-LLTS, an end-to-end real-time traffic sign detection algorithm specifically designed for low-light environments, achieves state-of-the-art performance and deployment on edge devices confirms its real-time applicability and effectiveness.
- VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction27
This work proposes VTON 360, a novel 3D VTON method that addresses the open challenge of achieving high-fidelity VTON that supports any-view rendering, and leverages the equivalence between a 3D model and its rendered multi-view 2D images to reformulate 3D VTON as an extension of 2D VTON that ensures 3D consistent results across multiple views.
- NiteDR: Nighttime Image De-Raining With Cross-View Sensor Cooperative Learning for Dynamic Driving Scenes27
The proposed Cross-View Cooperative Learning (CVCL) approach addresses the gap in the utilization of existing rain removal algorithms in specific low-light conditions and holds promise for extending the application of image de-raining and image fusion methods to computer vision tasks.
- Derivation and Preclinical Characterization of CYT-303, a Novel NKp46-NK Cell Engager Targeting GPC327
CYT-303 was highly potent and effective in mediating NK cell-redirected cytotoxicity against multiple HCC tumor cell lines and tumor spheroids and can reverse the dysfunction induced in NK cells following repeated rounds of serial killing of tumors.
- Masked Images Are Counterfactual Samples for Robust Fine-Tuning27
A novel fine-tuning method is proposed, which uses masked images as counterfactual samples that help improve the robustness of the fine- Tuning model, surpassing previous methods on the OOD performance.
- 27
- 27
- A Deep Joint Learning Approach for Age Invariant Face Verification27
A new deep Convolutional Neural Network model for age-invariant face verification, which can learn features, distance metrics and threshold simultaneously simultaneously is proposed, which outperforms other state-of-the-art methods on MORPH-II database.
- Cross-modal Causal Relation Alignment for Video Question Grounding26
A novel VideoQG framework named Cross-modal Causal Relation Alignment (CRA) is proposed, to eliminate spurious correlations and improve the causal consistency between question-answering and video temporal grounding.
- 26
- Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition26
An Adaptive Global-Local Representation Learning and Selection (AGLRLS) framework that incorporates global-local adversarial adaptation and semantic-aware pseudo label generation to enhance the learning of domain-invariant and discriminative feature representation during training and during inference.
- 26
- 25
- LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts25
This paper achieves accurate complex scene generation by proposing a semantically controllable Layout-AWare diffusion model, termed LAW-Diffusion, which introduces a spatial dependency parser to encode the location-aware semantic coherence across objects as a layout embedding and produces a scene with perceptually harmonious object styles and contextual relations.
- 25
- Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution25
This paper proposes an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera, and improves the model transferability from the source domain to the target.
- Parallel nonparametric binarization for degraded document images25
This work develops a CUDA well-suited parallel algorithm of Sauvola's method and implements it on Kepler GPUs with CUDA 5.0, showing that the proposed method outperforms the state-of-the-art methods.
- Real-World Image Super-Resolution by Exclusionary Dual-Learning24
This paper proposes a method, Real-World image Super-Resolution by Exclusionary Dual-Learning (RWSR-EDL) to address the feature diversity in perceptual- and L1- based cooperative learning and develops a noise-guidance data collection strategy to addressed the training time consumption in multiple datasets optimization.
- Kalman Normalization: Normalizing Internal Representations Across Network Layers24
A novel normalization method, called Kalman Normalization (KN), is presented, which treats all the layers in a network as a whole system, and estimates the statistics of a certain layer by considering the distributions of all its preceding layers, mimicking the merits of Kalman Filtering.
- Learning to Segment Human by Watching YouTube24
A very-weakly supervised learning framework for human segmentation task, where only an imperfect human detector is available along with massive weakly-labeled YouTube videos, and reaches a new state-of-the-art performance on the human segmentsation task.
- A Causality-Aware Paradigm for Evaluating Creativity of Multimodal Large Language Models23
The results show that while most LLMs exhibit constrained creativity, the performance gap between LLMs and humans is not insurmountable, and suggest that LoTbench better aligns with human cognitive theories, highlighting cognition as a critical foundation in the early stages of creativity and enabling the bridging of diverse concepts.
- InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction23
InfiniteWorld is introduced, a unified and scalable simulator for general vision-language robot interaction built on Nvidia Isaac Sim that integrates a series of improvements in generation-driven 3D asset construction, Real2Sim, automated annotation framework, and unified 3D asset processing.
- ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning23
The ID-Aligner framework, a general feedback learning framework to enhance ID-T2I performance, introduces identity consistency reward fine-tuning to utilize the feedback from face detection and recognition models to improve generated identity preservation and proposes identity aesthetic reward fine-tuning.
- Road Network-Guided Fine-Grained Urban Traffic Flow Inference23
This work proposes a novel road-aware traffic flow magnifier (RATFM) that explicitly exploits the prior knowledge of road networks to fully learn the road- aware spatial distribution of fine-grained traffic flow.
- 23
- 23
- Place-centric Visual Urban Perception with Deep Multi-instance Regression23
Results with comparisons showed that the proposed method can clearly outperform the alternative perception methods and more importantly, is capable of generating region-level safety scores to facilitate interpretations of the perception process.
- Character proposal network for robust text extraction23
A character proposal network (CPN) is designed by taking advantage of the high capacity and fast computing of fully convolutional network (FCN), which simultaneously predicts character-ness scores and refines the corresponding locations.
- 23
- 22
- Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift22
This work addresses the ranking correlation problem to the supernet training consistency shift, including feature shift and parameter shift, using a nontrivial supernet-∏ model, called ∏-NAS, which runs in an unsupervised manner, which can search for more transferable architectures.
- Neural Task Planning With AND–OR Graph Representations22
A knowledge and–or graph (AOG) for task description, which hierarchically represents a task as atomic actions, is introduced and can produce many valid samples that effectively facilitate training of the model for semantic task planning.
- 22
- 22
- Crowd counting via scale-communicative aggregation networks21
A scale-communicative aggregation network (SCANet) for crowd counting that contains different streams of convolutional neural networks, and a multi-scale structural similarity metric along with Euclidean distance is introduced for optimizing the quality of generated density maps.
- 21
- 21
- Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection21
A reconfigurable model to recognize and detect multiclass (or multiview) objects with large variation in appearance and achieves state-of-the-arts performance is proposed.
- HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation20
This work proposes a novel paradigm, Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation (HyCoRec), which aims to alleviate the Matthew effect in conversational recommendation.
- 20
- Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection20
This work proposes an adaptive pseudo labeling strategy, which can assign thresholds to classes with respect to their “hardness”, and devise a joint feature-level and prediction-level consistency learning pipeline for transferring the information of the teacher model to the student model that achieves state-of-the-art performance.
- 20
- 20
- FANet: Quality-Aware Feature Aggregation Network for RGB-T Tracking.20
A novel deep network architecture "quality-aware Feature Aggregation Network (FANet)" is proposed to achieve quality-aware aggregations of both hierarchical features and multimodal information for robust online RGB-T tracking.
- RGB-D Scene Labeling with Long Short-Term Memorized Fusion Model.20
This paper addresses the problem of semantic labeling of RGB-D scenes by developing a novel Long Short-Term Memorized Fusion (LSTM-F) Model that captures and fuses contextual information from multiple channels of photometric and depth data, and incorporating this model into deep convolutional neural networks (CNNs) for end-to-end training.
- Adaptive Scene Category Discovery With Generative Learning and Compositional Sampling20
This paper investigates a general framework to discover categories of unlabeled scene images according to their appearances by treating each image as a graph vertex and defining the probabilistic model of graph partition by accumulating the generative models of all separated categories.
- Example-based Automatic Portraiture20
A new approach for automatically generating a life-like portrait from a frontal face image by employing Inhomogeneous Markov Random Field Model and a non-parametric sampling scheme to capture the complex statistical characteristics of face image and corresponding artist drawing.
- Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior19
The proposed Diff-Mosaic data augmentation method effectively alleviates the challenge of diversity and realism of data augmentation methods via diffusion prior, and introduces an enhancement network called Pixel-Prior, which generates highly coordinated and realistic Mosaic images by harmonizing pixels.
- Dual-perspective semantic-aware representation blending for multi-label image recognition with partial labels19
A dual-perspective semantic-aware representation blending (DSRB) that blends multi-granularity category-specific semantic representation across different images, from instance and prototype perspective respectively, to transfer information of known labels to complement unknown labels.
- 19
- 19
- 19
- 19
- CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond18
This paper proposes an infrared-visible fusion framework based on Multi-View Augmentation that significantly enhances the reliability and stability of IVIF tasks in practical applications and improves robustness and generalization of models.
- VisDiaHalBench: A Visual Dialogue Benchmark For Diagnosing Hallucination in Large Vision-Language Models18
A novel visual dialogue hallucination evaluation benchmark that investigates the hallucination problem of LVLMs when given long-term misleading textual history and differs from previous hallucination benchmarks in the following three points.
- Multi-label image recognition with attentive transformer-localizer module18
A novel attentive transformer-localizer (ATL) module is applied to progressively localize the attentive regions from the convolutional feature maps in a proposal-free manner, and the LSTM network sequentially predicts label scores for the localized regions and updates the parameters of the ATL module while capturing the global dependencies among these regions.
- Deductive Learning for Weakly-Supervised 3D Human Pose Estimation via Uncalibrated Cameras18
This paper proposes a Deductive Weakly-Supervised Learning (DWSL) for 3D human pose machine that introduces deductive reasoning to make an inference for the human pose from a view to another and develops a reconstruction loss to demonstrate what the model learns and infers is reliable.
- 18
- Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer18
This work proposes a graph reasoning and transfer learning framework, named “Graphonomy,” which incorporates human knowledge and label taxonomy into the intermediate graph representation learning beyond local convolutions, and applies it to two relevant but different image understanding research topics.
- 18
- Unsupervised Domain Adaptation: An Adaptive Feature Norm Approach.18
A non-parametric Adaptive Feature Norm AFN approach, which is independent of the association between label spaces of the two domains and demonstrates that adapting feature norms of source and target domains to achieve equilibrium over a large range of values can result in significant domain transfer gains.
- Deep Boosting: Joint feature selection and analysis dictionary learning in hierarchy18
A deep boosting framework based on layer-by-layer joint feature boosting and dictionary learning that provides the potential to build very deep architectures and outperforms existing state-of-the-art approaches.
- DreamFuse: Adaptive Image Fusion with Diffusion Transformer17
This work introduces DreamFuse, a novel approach based on the Diffusion Transformer (DiT) model, to generate consistent and harmonious fused images with both foreground and background information, and demonstrates that this method outperforms state-of-the-art approaches across multiple metrics.
- All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents17
A large-scale unified ARIO dataset, comprising approximately 3 million episodes collected from 258 series and 321,064 tasks, is presented, representing a significant step towards bridging the gaps of existing data resources.
- 17
- 17
- 17
- Knowledge-guided recurrent neural network learning for task-oriented action prediction17
A temporal And-Or graph (AOG) for task description is introduced, which hierarchically represents a task into atomic actions and can produce many valid samples that effectively facilitate training the model for task-oriented action prediction.
- 17
- 17
- Content-Aware Hierarchical Representation Selection for Cross-View Geo-Localization16
This work designs a Content-Aware Hierarchical Representation Selection (CA-HRS) module, which can be seamlessly integrated into current deep networks to facilitate CVGL and can obtain obvious performance improvement over current competing algorithms.
- 16
- Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition16
This work proves that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness, compared to the existing image recognition pipeline that only tunes the weights regardless of the architecture.
- Lightweight adversarial network for salient object detection16
A lightweight adversarial network is proposed for salient object detection, which simultaneously improves the accuracy and efficiency by enforcing higher-order spatial consistency via adversarial training and lowering the computational cost through lightweight bottleneck blocks, respectively.
- 16
- 16
- 3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians15
The 3DAffordSplat dataset is presented, the first large-scale, multi-modal dataset tailored for 3DGS-based affordance reasoning, and AffordSplatNet is introduced, a novel model specifically designed for affordance reasoning using 3DGS representations.
- VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling15
A one-shot adaptation framework that recalibrates visual representations through lightweight, learnable updates that reveals substantial untapped robustness in pretrained VLA models and demonstrates that targeted, minimal visual adaptation is sufficient to restore viewpoint generalization.
- Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation15
This work proposes to learn content and emotion priors as guidance augmented with contrastive learning to learn decoupled content and emotion representation via an innovative Contrastive Decoupled Representation Learning (CDRL) algorithm.
- RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation15
RoBridge maintains the declarative skill of VLM and unleashes the procedural skill of reinforcement learning, effectively bridging the gap between cognition and execution in robotic systems, offering a new paradigm for general robotic manipulation.
- 15
- Discovering similar Chinese characters in online handwriting with deep convolutional neural networks15
This paper proposes an algorithm by leveraging CNN confidence for discovering similar character pairs/sets by applying a deep CNN to output the top ranked candidates and the corresponding confidence scores, followed by an accumulating and averaging procedure.
- Contextualized Trajectory Parsing with Spatio-Temporal Graph15
A novel representation spatiotemporal graph in which graph nodes express the motion primitives, each representing a short sequence of small-size patches over consecutive images, and every two neighbor nodes are linked with either a positive edge or a negative edge to describe their collaborative or exclusive relationship of belonging to the same object trajectory.
- 15
- Salient object detection based on regions15
The experimental results show that the new approach of salient object detection using region-based representation outperforms other four state-of-the-arts methods with regard to precision, recall and F-measure.
- Diversity Matters: User-Centric Multi-Interest Learning for Conversational Movie Recommendation14
A novel paradigm, User-Centric Multi-Interest Learning for Conversational Movie Recommendation (CoMoRec), aiming to learn multiple user interests to improve result diversity for movie recommendations, achieves a new state-of-the-art performance and the superiority of improving recommendation diversity in the CRS.
- 14
- 14
- A Retrospect to Multi-prompt Learning across Vision and Language14
The recent constant modality gap phenomenon is extended to learnable prompts and then, the superiority of vision-language transfer with multi-prompt augmentation with multi-prompt augmentation is justified, empirically and theoretically.
- 14
- 14
- Scene Graph to Image Synthesis via Knowledge Consensus13
This paper delves into the causality of the adversarial generation process, and reason out a new principle to realize a simultaneous semantic disentanglement with an alignment on target and model distributions, named knowledge consensus, which determines a new graph-to-image generation framework.
- ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and Multispectral Data Fusion13
A novel adversarial automatic data augmentation (DA) framework ADASR is proposed that automatically optimizes and augments HSI-MSI sample pairs to enrich data diversity for HSI/MSI fusion.
- On fast simulation of dynamical system with neural vector enhanced numerical solver13
This work introduces a deep learning-based corrector called Neural Vector (NeurVec), which can compensate for integration errors and enable larger time step sizes in simulations, and has the potential to establish a new paradigm for fast-solving differential equations based on deep learning.
- Towards Causality-Aware Inferring: A Sequential Discriminative Approach for Medical Diagnosis13
A progressive assurance agent is proposed, which includes the dual processes accounting for symptom inquiry and disease diagnosis respectively, which can improve upon the out-of-distribution generalization significantly and possesses the advantage of transportability.
- Progressively diffused networks for semantic visual parsing13
This work proposes Progressively Diffused Networks (PDNs) to deal with complex semantic parsing tasks and demonstrates the effectiveness of PDNs to substantially improve the performances of existing LSTM-based models.
- Learning deep representations for semantic image parsing: a comprehensive overview13
Three aspects of the progress of research on semantic image parsing are summarized, i.e., category-level semantic segmentation, instance-levelSemantic image parsing, and beyond segmentation.
- 13
- 13
- Scaling Up Single Image Dehazing Algorithm by Cross-Data Vision Alignment for Richer Representation Learning and Beyond12
This work proposes a novel method of cross-data vision alignment for richer representation learning to improve the existing dehazing methodology and presents a new pipeline for large-scale training in the dehazing task.
- Rethinking Generalizable Infrared Small Target Detection: A Real-Scene Benchmark and Cross-View Representation Learning12
This article introduces an ISTD framework enhanced by domain adaptation, and proposes the cross-view Top-K fusion strategy, which integrates target information with diverse background features, enhancing the model’s ability to extract critical data characteristics.
- 12
- 12
- 12
- 12
- Open Set Domain Adaptation By Novel Class Discovery12
Self-supervised Class-Discovering Adapter (SCDA) is proposed that attempts to achieve Open Set Domain Adaptation by gradually discovering those implicit classes, then incorporating them to restructure the classifier and update the domain-adaptive features iteratively.
- Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp12
A concise yet powerful method to construct Continuous Transition, which exploits the trajectory information by exploiting the potential transitions along the trajectory and synthesizes new transitions for training by linearly interpolating the consecutive transitions.
- 12
- Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning12
This paper's extensive experiments on standard image classification benchmarks demonstrate that the proposed framework is capable of effectively mining from large-scale unlabeled images, which boosts image classification performance and achieves promising results compared with other semi-supervised learning methods.
- 12
- Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI11
Embodied Arena is presented, a comprehensive, unified, and evolving evaluation platform for Embodied AI that establishes a systematic embodied capability taxonomy spanning three levels (perception, reasoning, task execution), seven core capabilities, and 25 fine-grained dimensions, enabling unified evaluation with systematic research objectives.
- Early prediction of preeclampsia from clinical, multi-omics and laboratory data using random forest model11
This study aimed to develop prediction models for early-onset preeclampsia (EPE) and late-onset preeclampsia (LPE) respectively using clinical data, metabolome and proteome analyses on plasma samples and laboratory data and identified a set of significant omics and laboratory features for PE prediction.
- 11
- FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System11
This work proposes a novel paradigm, Multi-Facet Preference Learning for Pricking Filter Bubbles in Conversational Recommender System (FacetCRS), which aims to burst filter bubbles in the conversational recommender system (CRS) through timely user-item interactions via natural language conversations.
- 11
- GTAE: Graph Transformer–Based Auto-Encoders for Linguistic-Constrained Text Style Transfer11
Graph Transformer–based Auto-Encoder is proposed, which models a sentence as a linguistic graph and performs feature extraction and style transfer at the graph level, to maximally retain the content and the linguistic structure of original sentences.
- Physical-Virtual Collaboration Graph Network for Station-Level Metro Ridership Prediction.11
This work model a metro system as graphs with various topologies and proposes a unified Physical-Virtual Collaboration Graph Network (PVCGN), which can effectively learn the complex ridership patterns from the tailor-designed graphs.
- Grammatically Recognizing Images with Tree Convolution11
A simple yet effective tree convolution (TreeConv) operation for deep neural networks that designs a generative image grammar, i.e., tree generation rule, to parse the hierarchy of internal feature maps by generating tree structures and implicitly learning the specific visual grammars for each object category.
- 11
- 11
- Local- and holistic-structure preserving image super resolution via deep joint component learning11
This work presents a new novel SR approach, which replaces the main building blocks of the classical interpolation pipeline by a flexible, content-adaptive deep neural networks to enhance the image sharpness and naturalness.
- Learning Shape Detector by Quantizing Curve Segments with Multiple Distance Metrics11
The authors' models consisting of local curve segments with multiple distance metrics are robust to the various shape deformations, and thus enable us to perform robust shape classification and detect shapes against background clutter.
- MirrorDiffusion: Stabilizing Diffusion Process in Zero-Shot Image Translation by Prompts Redescription and Beyond10
A prompt redescription mechanism is investigated to align the text prompts with latent code at each time step of the Denoising Diffusion Implicit Models (DDIM) inversion to pursue a structure-preserving reconstruction and is able to realize accurate zero-shot image translation by editing optimized text prompts and latent code.
- The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network10
The Lottery Ticket Hypothesis for Self-attention Networks is articulate and demonstrated: a full self-att attention network contains a subnetwork with sparse self-ATTention connections that can accelerate inference, reduce extra parameter increment, and maintain accuracy.
- 10
- Enhancing Prototypical Few-Shot Learning By Leveraging The Local-Level Strategy10
This paper presents a local-agnostic training strategy to avoid the discriminative location bias between the base and novel categories, a novel local-level similarity measure to capture the accurate comparison between local- level features, and aLocal-level knowledge transfer that can synthesize different knowledge transfers from the base category according to different location features.
- Image Comes Dancing With Collaborative Parsing-Flow Video Synthesis10
Results show the method substantially improves over previous approaches and is able to generate appealing and photo-realistic target videos given any input person image and the dedicated designed fusion network ensure the temporal coherence.
- 10
- CamDrop10
A new explanation of dropout is given from the perspective of optimization that it makes the upper bound of the magnitude of gradients much tighter, which leads to a more stable behavior of the gradients and effectively avoids neurons falling into the saturation region of the nonlinear activation, even when using high learning rates.
- Convolutional Memory Blocks for Depth Data Representation Learning10
A novel memory network module, called Convolutional Memory Block (CMB), is proposed, which empowers CNNs with the memory mechanism on handling depth data and is employed to develop a concise framework for predicting articulated pose from still depth images.
- SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks9
SIRI-Bench is introduced, a benchmark designed to evaluate VLMs'sructural spatial intelligence through spatial-grounded reasoning tasks, and an Automatic Scene Creation Engine is developed that employs collaborative LLM agents to translate abstract mathematical problems into faithful 3D scenes.
- Prior knowledge-guided multi-information graph convolutional network for driver drowsiness detection9
- Dual-View Data Hallucination With Semantic Relation Guidance for Few-Shot Image Recognition9
This work proposes a novel framework that exploits semantic relations to guide dual-view data hallucination for few-shot image recognition and enables generating more diverse and reasonable data samples for novel classes through effective information transfer from base classes.
- Discourse-Aware Graph Networks for Textual Logical Reasoning9
This work proposes logic structural-constraint modeling to solve the logical reasoning QA and introduces discourse-aware graph networks (DAGNs), which first construct logic graphs leveraging in-line discourse connectives and generic logic theories, then learn logic representations by end-to-end evolving the logic relations with an edge-reasoning mechanism and updating the graph features.
- Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning9
This paper presents a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents to the real world, by requiring them to learn towards deviation-robust navigation.
- 9
- Deep CockTail Networks9
A theoretical analysis towards Deep CockTail Network (DCTN), a universal and flexibly-deployed framework to address the problems of transferable deep representations for visual domain adaptation, reveals that DCTN significantly boosts classification accuracies in MSDA and performs extraordinarily to resist negative transfers across different MSDA scenarios.
- 9
- Human Centric Visual Analysis with Deep Learning9
This chapter presents a short review of the foundation of deep learning, including reinforcement learning, which has achieved great success in many applications, including computer vision, and natural language processing.
- ACFM: A Dynamic Spatial-Temporal Network for Traffic Prediction9
Two deep frameworks are developed to predict citywide short-term/long-term crowd flow by adaptively incorporating the sequential and periodic data as well as other external influences by a unified neural network called Attentive Crowd Flow Machine.
- 9
- 9
- Key Issues for AR-Based Digital Reconstruction of Yuanmingyuan Garden9
The Digital Yuanmingyuan project is designed to provide visitors with the visualization of virtual reconstructions superimposed upon the natural field of the ruins using a personal AR (Augmented Reality) system.
- 8
- DroneSR: Rethinking Few-Shot Thermal Image Super-Resolution From Drone-Based Perspective8
The method proposes a new Gaussian quantization representation learning method oriented to diffusion models that alleviates overfitting and enhances robustness of large-scale architectures under complex conditions and significantly mitigates overfitting of large-scale architectures under complex conditions.
- Self-Supervised Emotion Representation Disentanglement for Speech-Preserving Facial Expression Manipulation8
A novel framework is introduced, Self-Supervised Emotion Representation Disentanglement (SSERD), to disentangle emotion representation for accurate emotion transfer while implementing a paired data construction module to facilitate automated, photorealistic facial animations.
- 8
- 8
- Coordinate Transformer: Achieving Single-stage Multi-person Mesh Recovery from Videos8
The Coordinate transFormer (Coord-Former) is proposed, that directly models multi-person spatial-temporal relations and simultaneously performs multi-mesh recovery in an end-to-end manner and leverages a novel Coordinate-Aware Attention to preserve pixel-level spatial-temporal coordinate information.
- Simultaneous Lung Field Detection and Segmentation for Pediatric Chest Radiographs8
Experimental results demonstrate that the proposed SDSLung is capable of achieving significantly superior performance over state-of-the-art LFS methods on the authors' large-scale pediatric CXR dataset and also achieving extremely competitive results on adults’ C XR dataset.
- Attention Embedded Spatio-Temporal Network for Video Salient Object Detection8
This work proposes an attention embedded spatio-temporal network (ASTN) to adaptively exploit diverse factors that influence dynamic saliency prediction within a unified framework and develops an attentive bidirectional gated recurrent unit (AB-GRU) module to Adaptively exploit sequential feature evolution.
- 8
- Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review7
A comprehensive review of realizing the sample efficiency and generalization of RL algorithms through T-IRL and a discussion of open research directions and future trends.
- Interaction between gut microbiota and anesthesia: mechanism exploration and translation challenges focusing on the gut-brain-liver axis7
In the future, it will be necessary to integrate multiomics technologies for analyzing the tripartite interaction network of microorganisms, hosts, and drugs, as well as for promoting standardized clinical research, in order to develop individualized anesthesia management plans based on gut microbiota regulation.
- DFVO: Learning Darkness-Free Visible and Infrared Image Disentanglement and Fusion All at Once7
A Darkness-Free network is proposed to handle visible and infrared image disentanglement and fusion all at once (DFVO), which employs a cascaded multitask approach to replace the traditional two-stage cascaded training (enhancement and fusion), addressing the issue of information entropy loss caused by hierarchical data transmission.
- 7
- ASR: Attention-alike Structural Re-parameterization7
Extensive experiments conducted on several standard benchmarks demonstrate the effectiveness of ASR in generally improving the performance of existing backbone networks, attention modules, and SRP methods without any elaborated model crafting and provide experimental and theoretical evidence for the strong robustness of the proposed ASR.
- DNA Family: Boosting Weight-Sharing NAS With Block-Wise Supervisions7
This work modularizes a large search space into blocks with small search spaces and develops a family of models, namely a DNA family, that are capable of resolving multiple dilemmas of the weight-sharing NAS, such as scalability, efficiency, and multi-modal compatibility.
- 7
- Face Recognition by Coarse-to-Fine Landmark Regression with Application to ATM Surveillance7
A new authentication mode combine face recognition and basic password for ATM is explored to prevent the economic crime on ATM fundamentally and is practicable due to its high speed, good accuracy, and low storage space requirement.
- High-level representation sketch for video event retrieval7
The event sketch is proposed, a high-level event representation, to depict the dynamic properties of video events composed of actions of semantic objects, and it is shown that this representation can facilitate a novel sketch based video retrieval (SBVR) system.
- SKELETONIZATION WITH PARTICLE FILTERS7
Experimental results demonstrate that the proposed method significantly outperforms other well-known methods for skeleton computation and an extension of the method to computing skeletons of gray level images is proposed and provides promising experimental results.
- 7
- EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning6
Experimental results under both task-specific and cross-task training paradigms demonstrate the consistent superiority of EvolveNav over previous LLM-based VLN approaches on various popular benchmarks, including R2R, REVERIE, CVDN, and SOON.
- SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting6
A novel localization-based CAC approach, termed Scale-modulated Query and Localization Network (SQLNet), which fully explores the scales of exemplars in both the query and localization stages and achieves effective counting by accurately locating each object and predicting its approximate size.
- 6
- DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh6
DAGSM, a novel pipeline that generates disentangled human bodies and garments from the given text prompts, and introduces a semantic-based algorithm to achieve better human-cloth and garment-garment separation, is proposed.
- Monitoring Primitive Interactions During the Training of DNNs6
It is shown that the seemingly complex learning dynamics of a DNN can be faithfully represented as the change of a few primitive interaction patterns encoded by the DNN, and the interaction of principal feature components in intermediate-layer features is defined.
- 6
- Sim-DETR: Unlock DETR for Temporal Sentence Grounding6
A simple yet powerful baseline, SimDETR, is proposed, which extends the standard DETR with two minor modifications in the decoder layers, constraining selfattention between queries based on their semantic and positional overlap and adding query-to-frame alignment to bridge the global and local contexts.
- Exploration and Exploitation of Unlabeled Data for Open-Set Semi-supervised Learning6
This paper proposes a prototype-based clustering and identification algorithm that explores the inherent similarity and difference among samples at feature level and effectively cluster them around several predefined ID and OOD prototypes, thereby enhancing feature learning and facilitating ID/OOD identification.
- 6
- 6
- Joint semantic segmentation by searching for compatible-competitive references6
A framework for semantically segmenting a target image without tags by searching for references in an image database, where all the images are unsegmented but annotated with tags, which outperforms the state-of-the-arts approaches on the MSRC-21 database.
- 6
- An advanced subway train localization system using a vision-based kilometer marker recognition-assisted multi-sensor fusion method5
The results show that the proposed vision-aided multi-sensor fusion method can be used as an alternative to the existing wayside-transponder-based localization system to provide navigation solutions for train safe operation without relying on wayside equipment and with low cost and easy maintenance.
- 5
- 5
- 5
- Perceptual Image Enhancement by Relativistic Discriminant Learning With Cross-Scale Aggregated Representation5
An automatic method for image quality enhancement that relies on a multi-level connected generator and a pair-wise relativistic discriminator and can automatically enhance the low-quality image into a digital single lens reflex (DSLR) quality.
- 5
- Uncertainty Weight Generation Approach Based on Uncertainty Comparison Matrices5
The concepts of uncertainty comparison matrix and uncertainty weights are proposed and the uncertain variable method (UVM) is given to calculate uncertainty weights from uncertainty comparison matrices, which can be either consistent or inconsistent.
- 5
- 5
- Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation4
PhysGen (Learning Physics from Pretrained Video Generation Models), a scalable continuous and sequential world interaction framework that leverages autoregressive video generation to solve robotic manipulation tasks, is introduced.
- GraspView: Active Perception Scoring and Best-View Optimization for Robotic Grasping in Cluttered Environments4
Experiments on diverse tabletop objects demonstrate that GraspView significantly outperforms both RGB-D and single-view RGB baselines, especially under heavy occlusion, near-field sensing, and with transparent objects, highlighting GraspView as a practical and versatile alternative to RGB-D pipelines.
- 4
- 4
- Decoder-Only LLMs are Better Controllers for Diffusion Models4
The experimental results show that the enhanced text-to-image diffusion models with the adapter module are superior to the stat-of-the-art models in terms of text-to-image generation quality and reliability.
- Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs4
An axiomatic system is proposed to define and quantify the precise memorization and in-context reasoning effects used by the large language model (LLM) for language generation and shows that the clear disentanglement of memorization effects and in-context reasoning effects enables a straightforward examination of detailed inference patterns encoded by LLMs.
- 323 TALEN®-based gene edited iPSC-derived NK (iNK) cells demonstrate enhanced antitumor activity4
Induced Pluripotent Stem Cell (iPSC)-derived NK cells an oppor-tunity to generate unlimited and homogenous NK cells for allogeneic off-the-shelf therapies, and the persistence of these cells in the tumor microen-vironment.
- Instance-Level Human Parsing4
This chapter makes the first attempt to explore a detection-free part grouping network (PGN) to efficiently parse multiple people in an image in a single pass.
- 4
- 4
- Robust stroke-based video animation via layered motion and correspondence4
This paper investigates a novel approach to reduce artifacts and visual flickering in generating painterly animations from real video clips by combining motion segmentation and occlusion handing to establish accurate dense feature correspondences, which is shown to robust propagate brush strokes against complex motions and Occlusions.
- 4
- Ivan-ISTD: Rethinking Cross-Domain Heteroscedastic Noise Perturbations in Infrared Small Target Detection3
This work proposes a doubly wavelet-guided invariance learning framework (Ivan-ISTD), which learns noise invariance through self-supervised loss, thereby overcoming the limitations of distribution bias in traditional artificial noise modeling.
- One-shot Face Sketch Synthesis in-the-Wild via Generative Diffusion Prior and Instruction Tuning3
Extensive experiments demonstrate that the proposed method can convert various photos into realistic and highly consistent sketches in a one-shot context and offers greater convenience and broader applicability compared to other methods.
- Visualized load-bearing-based robot control system improves early function in femoral neck fracture patients: a randomized controlled trial focusing on outcomes after total hip arthroplasty3
It is demonstrated that a robot control system based on visualized load-bearing can effectively enhance early functional recovery after THA in a short postoperative period, making it a valuable intelligent rehabilitation system.
- ERIS: Evolutionary Real-world Interference Scheme for Jailbreaking Audio Large Models3
Evolutionary Noise Jailbreak is proposed, which utilizes a genetic al-gorithm to transform environmental noise from a passive interference into an actively optimizable attack carrier for jail-breaking LSMs.
- Geometry-Editable and Appearance-Preserving Object Compositon3
This work introduces a Disentangled Geometry-editable and Appearance-preserving Diffusion (DGAD) model that first leverages semantic embeddings to implicitly capture the desired geometric transformations and then employs a cross-attention retrieval mechanism to align fine-grained appearance features with the geometry-edited representation, facilitating both precise geometry editing and faithful appearance preservation in object composition.
- In vitro and in vivo osteogenesis of rat adipose-derived stem cells combined with calcium alginate gel scaffold induced by calcitonin gene-related peptide3
It is indicated that CGRP can induce ADSCs combined with CaAlg scaffolds to form tissue-engineered bone in vivo, with CGRP and CaAlg scaffolds showing a synergistic effect on promoting ADSC osteogenic differentiation.
- 3
- Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective3
This work assesses DBP robustness under a novel attack setting, Deterministic White-box, and pinpoint stochasticity as the main factor in DBP robustness, and shows that ADDT improves the robustness of DBP models.
- 3
- 3
- 3
- Counterfactual Balancing Feature Alignment for Few-Shot Cross-Domain Scene Parsing3
This paper considers the domain adaptation in pixels in the view of the average treatment effect (ATE) to build the connection between ATE and domain gap, and revises existing adversarial adaptation techniques by modeling the propensity score for all pixels in their contexts, for the sake of predicting which groups they belong to.
- Open-World Pose Transfer via Sequential Test-Time Adaption3
It is shown that pose transfer can be applied to open-world applications, including Tiktok reenactment and celebrity motion synthesis, and a SEquential Test-time Adaption (SETA), which greatly improves the generalization performance of current pose transfer models.
- 3
- 3
- Multi-object Video Generation from Single Frame Layouts3
A novel video generative framework capable of synthesizing global scenes with local objects, via implicit neural representations and layout motion self-inference is proposed, which is a non-trivial adaptation from image generation methods, and is new to this field.
- Human Activity Understanding3
This work investigates a novel deep structured model that adaptively decomposes an activity into temporal parts using convolutional neural networks (CNNs) and incorporates a radius-margin bound as a regularization term into the deep model, which effectively improves the generalization performance for classification.
- 3
- 3
- High-Precision Camera Localization in Scenes with Repetitive Patterns3
A high-precision multi-modal approach for localizing moving cameras with monocular videos, which has wide potentials in many intelligent applications, including robotics, autonomous vehicles, and so on is presented.
- 3
- Boosting Zero-Shot Image Classification via Pairwise Relationship Learning3
This paper proposes to exploit the pairwise relationships between test instances to increase the performance of conventional methods, e.g. direct attribute prediction (DAP), for the ZSIC problem, and introduces two different methods, a binary classification based method and a metric learning based method.
- 3
- 3
- Object Category Recognition Using Generative Template Boosting3
This framework integrates the learnable And-Or graph model, a hierarchical structure that combines the reconfigurability of a stochastic context free grammar with the constraints of a Markov random field, and samples object configurations as training templates from this generative model.
- Integration of Communication and Computational Imaging2
This work proposes a novel framework that integrates communication and computational imaging (ICCI) to break through the inherent isolation between communication and computational imaging for remote visual perception, and offers a high-efficiency solution for various real-time computer vision tasks.
- Energy-guided test-time adaptation for data shifts in multi-modal perception2
This work proposes a Energy-guided Two-stage Test-time Adaptation (Eng2TTA) framework specifically designed for multi-modal perception, which demonstrates superior robustness in multi-modal tasks, significantly outperforming state-of-the-art methods in scenarios with varying levels of modality corruption, particularly under severe distribution shifts.
- Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention Into Convolutions2
ConvFusion is proposed to replace conventional self-attention modules with Pyramid Convolution Blocks ($Delta$ ConvBlocks) and achieves performance comparable to transformer-based counterparts while reducing computational cost by 6929× and surpassing LinFusion by 5.42× in efficiency-all without compromising generative fidelity.
- Neural Scene Designer: Self-Styled Semantic Image Manipulation2
The Neural Scene Designer is introduced, a novel framework that enables photo-realistic manipulation of user-specified scene regions while ensuring both semantic alignment with user intent and stylistic consistency with the surrounding environment.
- DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition2
DART is the first framework, to the authors' knowledge, to explicitly integrate external LLM-derived relational knowledge for adaptive inter-class transfer while simultaneously performing adaptive intra-class refinement under weak supervision for OV-MLR.
- 2
- 2
- AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment2
This paper presents AnimateZoo, a zero-shot diffusion-based video generator to address this challenging cross-species animation issue, aiming to accurately produce animal animations while preserving the background, and introduces two high-quality animal video datasets featuring a wide variety of species.
- Credible Teacher for Semi-Supervised Object Detection in Open Scene2
Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels.
- Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels2
This work designs a unified framework, Category-Adaptive Label Discovery and Noise Rejection, that discovers unknown labels and rejects noisy labels for each category in an adaptive manner and proposes a novel category-adaptive threshold updating that adaptively adjusts the threshold, to avoid the time-consuming manual tuning process.
- 2
- 2
- Learning Reinforced Agents with Counterfactual Simulation for Medical Automatic Diagnosis.2
A propensity-based patient simulator (PBPS), capable of facilitating the training of MAD agents by generating informative counterfactual answers along with the disease diagnosis, and a progressive assurance agent~(P2A) trained with PBPS, which includes two separate yet cooperative branches accounting for the execution of symptom-inquiry and disease-diagnosis actions, respectively.
- 2
- Active Object Search2
This work forms a reinforcement learning framework that consists of a 3D object detector, a state controller and a cross-modal action planner to work cooperatively to find out the target object with minimal action steps for an Active Object Search task that is not explicitly addressed in the literature.
- FRAME Revisited: An Interpretation View Based on Particle Evolution2
This paper proposes an alternative Wasserstein distance in discrete time based on the conclusion that the Jordan-Kinderlehrer-Otto (JKO) discrete flow approximates KL discrete flow when the time step size tends to 0.
- The Foundation and Advances of Deep Learning2
This chapter presents a short review of the foundation of deep learning, i.e., artificial neural network, and introduces some new techniques in deep learning.
- Face Localization and Enhancement2
This chapter proposes a novel cascaded backbone-branches fully convolutional neural network (BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings and introduces the progress in face hallucination.
- 2
- 2
- 2
- Scene Parsing by Weakly Supervised Learning with Image Descriptions.2
This paper proposes a deep architecture consisting of two networks: i) a convolutional neural network extracting the image representation for pixel-wise object labeling and ii) a recursive neural network discovering the hierarchical object structure and the inter-object relations.
- Visual Tracking via Learning Dynamic Patch-based Graph Representation.2
This work learns a patch-based graph representation for visual tracking that performs well against the state-of-the-art methods on large-scale benchmark datasets and is optimized to refine the patch weights by using a novel alternating direction method of multipliers.
- 2
- Compositional models and Structured learning for visual recognition2
This special issue aims to collect recent state-of-the-art achievements on how to learn CHMs and other effective models from visual data such as images and videos for visual recognition and related problems.
- A stochastic image grammar for fine-grained 3D scene reconstruction2
Results with comparisons on public image dataset show that the stochastic grammar for fine-grained 3D scene reconstruction from a single image clearly outperforms the alternate state-of-the-art single-view reconstruction methods.
- 2
- 2
- 2
- Image retrieval based on color texture shape and relevance feedback2
Aimed at the defects existed in the traditional content-based image retrieval (CBIR) system which was mainly dependent on the single vision features, a new method for multilayer image retrieval using combined color, texture and shape features was proposed.
- OOWM: Structuring Embodied Reasoning and Planning via Object-Oriented Programmatic World Modeling1
Object-Oriented World Modeling is proposed, a novel framework that structures embodied reasoning through the lens of software engineering formalisms and significantly outperforms unstructured textual baselines in planning coherence, execution success, and structural fidelity, establishing a new paradigm for structured embodied reasoning.
- 1
- Massive Editing for Large Language Models Based on Dynamic Weight Generation1
Experiments show that the proposed MeG can significantly improve the performance of large-scale KE in terms of Reliability, Generality, and Locality metrics compared to existing knowledge editing methods, particularly with a high percentage point increase in the absolute value index for the Locality metric.
- miR-101-3p represses the migratory and invasive abilities of ovarian cancer cells1
Overexpression of miR-101-3p significantly decreased cell viability, migration, and invasion in both SKOV3 and OVCAR-3 cells, confirming that miR-101-3p acts as a tumor suppressor in ovarian cancer.
- Enhancing Visual Programming for Visual Reasoning via Probabilistic Graphs1
A directed probabilistic graph is built according to the variable dependency relationships during the VP executing process, which reconstructs the non-differentiable VP executing process into a differentiable exact probability inference process on this directed probabilistic graph, which enables the VP framework to utilize the final labels for efficient, gradient-based optimization in end-to-end supervised learning on targeted VR tasks.
- Randomness of Low-Layer Parameters Determines Confusing Samples in Terms of Interaction Representations of a DNN1
It is found that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power, and the confusing samples of a DNN, which are represented by non-generalizable interactions, are determined by its low-layer parameters.
- AngularFuse: A Closer Look at Angle-based Perception for Spatial-Sensitive Multi-Modality Image Fusion1
An angle-based perception framework for spatial-sensitive image fusion (AngularFuse), which ensures that the fused images preserve both texture intensity and correct edge orientation, and introduces an angle-aware loss, which constrains both gradient magnitude and direction simultaneously in the gradient domain.
- 1
- 1
- 1
- A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks1
The “VisualProg Distiller” is proposed, a method of supplementing and distilling process knowledge to optimize the performance of each VisualProg sub-module on decoupled visual sub-tasks, thus enhancing the overall task performance.
- 1
- 1
- 1
- 1
- Chapter 4. Graph Reasoning Networks and Applications1
Through integrating knowledge graphs into neural networks, one can collaborate feature learning and graph reasoning with the same supervised loss function and achieve a more effective and interpretable way to introduce structure constraints.
- 1
- Pedestrian Detection with RPN and Boosted Forest1
This chapter proposes a very simple but effective baseline for pedestrian detection using an RPN followed by boosted forest on shared high-resolution convolutional feature maps to show competitive accuracy and good speed.
- 1
- Human-Centric Visual Analysis: Tasks and Progress1
This chapter briefly review the tasks of human-centric visual analysis, including face detection, facial landmark localization, pedestrian detection, human segmentation, clothes parsing, etc.
- Video Instance-Level Human Parsing1
A novel Adaptive Temporal Encoding Network (ATEN) that alternatively performs temporal encoding among key frames and flow-guided feature propagation from other consecutive frames between two key frames to achieve a good balance between frame-level accuracy and time efficiency.
- 1
- 1
- Special issue on Chinese Conference on Computer Vision 20151
The topics of the accepted papers include a wide range of new advances in computer vision, including 3D Computer Vision, Action Recognition, Convolutional Neural Networks and Deep Learning, Lowlevel Vision, Image Processing Medical, Biological and Cell Microscopy, and Shape Representation.
- Human-Centric Images and Videos Analysis1
This tutorial reviews recent progresses in human-centric images and videos analysis: 1) fashion analysis: parsing, attribute prediction and retrieval; 2) action analysis: discriminative feature selection, pooling and fusion; and person verification: cross-domain person verification via learning a generalized similarity measure, and bit-scalable deep hashing with regularized similarity learning.
- Single Parameter Entropy of Uncertain Variables1
The single parameter entropy of uncertain variable is introduced, and it is shown that the supremum of uncertainty of uncertainVariable can be obtained by choosing a proper q, and several important theorems are proved.
- Channel estimate with PDP assumption and interference RS knowledge in LTE system1
Simulation results show that if user number is not more than 4, the MSE performance nearly equals to single user, that is LMMSE channel estimate can cancel orthogonal RS sequence interference implicitly.
- Object-Layout-Aware Image Retrieval for Personal Album Management1
Using automatic object localization algorithms, it is proposed to index the personal album with the object positions and scales in the 2D image plane, which can reflect their layout in 3D scene and hence be used to measure the object layout similarity.
- 1
- Uncertain Models for Bed Allocation1
The purpose of this paper is to develop a methodology for modeling sickbed allocation problems with uncertain length of stay for each patient by employing Hybrid intelligent algorithm.
- 1
- Implementation of the augmented reality on PDA1
A light and compact PDA-based augmented reality system that provided the user with a three-dimensional augmented view of the cultural heritage on the commercial PDA device and can run in the outdoor environment successfully.
- A Method of the Voice Endpoint Detection Based on Maximum of Autocorrelation Function1
The experimental results show that this method can detect the voice endpoint exactly even in a low SNR environment.
- Optimal choice of knowledge experts in enterprise's knowledge interchange system1
The objective optimal choice model of knowledge experts that minimizes the waiting probability when a person has arrived at interchange system is established and the elementary computation and analysis of an example are given.
- –
- –
- –
- –
- SMArT: A Self-Driven Multiview Architecture Leveraging Large Language Models for Time Series Forecasting–
SMArT enriches intrapatch semantics through self-supervised multiview fusion, and establishes an effective framework for TSF by integrating self-driven multiview learning with LLMs' reasoning power.
- Computationally analyzing collective responses to reconfigured misinformation: a dual-process perspective using response entropy–
The I-D Response Evaluation Model (I-D-REM), featuring a novel Response Entropy metric derived from information theory, is proposed, to quantitatively assess intuitive (I) versus deliberative (D) collective responses to RM.
- –
- In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis From Language Models to Physics–
The proposed In-Context Model Predictive Generation (ICMPG) framework bridges semantic interpretation and physical simulation while remaining flexible enough to incorporate different LLM backbones, enabling more versatile and controllable text-driven motion synthesis.
- –
- –
- –
- –
- –
- –
- –
- Accelerating Massively Distributed Deep Learning Through Efficient Pseudo-Synchronous Update Method–
This work proposes a novel adaptive exponential smoothing predicted gradient algorithm for model optimization, which can adaptively adjust the confidence coefficient of the history gradient to ensure the normal convergence of the training process.
- –
- FIRE: Fine Implicit Reconstruction Enhancement with Detailed Body Part Labels and Geometric Features–
- –
- Learning image blind denoisers without explicit noise modeling–
This paper proposed a general yet concise image blind denoising framework that can be applied to existing deep learning-based denoisers and advances in generating noise directly from the noisy images without explicitly noise modeling.
- –
- –
- –
- Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation–
A route planning method named Path Estimation and Memory Recalling (PEMR) framework that aims at fully leveraging past experience collected by the feature extractor to encourage the navigator to learn more accurate prior expert experience.
- –
- –
- –
- Look into Facial Expression Domain Adaptation: Adversarial Graph Learning and A Fair Evaluation Benchmark.–
This work develops a novel adversarial graph representation adaptation (AGRA) framework, which conducts extensive and fair evaluations on several popular benchmarks and shows that the proposed AGRA framework outperforms previous state-of-the-art methods.
- –
- Generalizing Energy-based Generative ConvNets from Particle Evolution Perspective–
This paper establishes a connection between FRAME model and dynamic physics process and provides a generalized formulation of FRAME in discrete flow with a certain metric measure from particle perspective, and presents a Generalized GCN (GGCN), which introduces a hidden space mapping strategy and employs a normal distribution as hidden space for the reference distribution.
- Self-supervised Structure-Sensitive Learning for Human Parsing–
This chapter introduces a new benchmark, “Look into Person (LIP),” that makes a significant advance in terms of scalability, diversity, and difficulty, and explores a novel self-supervised structure-sensitive learning approach that imposes human pose structures on the parsing results without requiring extra supervision.
- –
- –
- Structured Deep Learning for Pixel-level Understanding–
This tutorial reviews recent progresses for pixel-level understanding with structured deep learning, including 1) human-centric analysis: human parsing and pose estimation; 2) part-based analysis: part and face parsing; 3) weakly-supervised analysis: object localization and semantic segmentation; 4) depth estimation: stereo matching.
- –
- –
- Learning to Segment Object Proposals via Recursive Neural Networks.–
This paper presents a simple yet effective approach for segmenting object proposals via a deep architecture of recursive neural networks (RNNs), which hierarchically groups regions for detecting object candidates over scales and outperforms other existing methods in both accuracy and efficiency.
- –
- –
- –
- A NOVEL RISK MEASURE MODEL IN UNCERTAIN THEORY–
The novel risk measure model reflects the risks originate from the state uncertainty and not only reflects the decision-makers subjective attitude to risk, but also can better measure the present complex financial risk.
- –
- –
- –
- –
- Maximum Entropy Functions of Discrete Fuzzy Random Variables–
A genetic algorithm is designed to solve the general maximum entropy model for discrete fuzzy random variables with certain constraints, which is illustrated by numerical experiment.
- –
- –
- Object category recognition using boosting tree with heterogenous features–
The proposed approach integrates the Adaboost algorithm into the decision tree structure, called DB-Tree, and each tree node combines a number of weak classifiers into a strong classifier (a conditional posterior probability), which can output the overall posterior probability.
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.