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
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works228 from public data
- 375
- 129
- 127
- 120
- 114
- 109
- Scene graph captioner: Image captioning based on structural visual representation97
This work proposes a novel framework to embed a scene graph into the structural representation, which captures the semantic concepts and the graph topology and develops the scene-graph-driven method to generate the attention graph.
- 94
- 87
- 87
- Coupled hidden conditional random fields for RGB-D human action recognition87
The extensive experiments show that the proposed model can boost the performance of human action recognition by taking advance of complementary characteristics from both RGB and depth modalities.
- 85
- CAT-DM: Controllable Accelerated Virtual Try-On with Diffusion Model82
A basic diffusion-based virtual try-on network is designed, which utilizes ControlNet to introduce additional control conditions and improves the feature extraction of garment images and demonstrates the superiority of CAT-DM against both GAN-based and diffusion-based methods in producing more real-istic images and accurately reproduced garment patterns.
- 78
- 77
- Graph-based characteristic view set extraction and matching for 3D model retrieval68
A novel method for characteristic view extraction and similarity measurement is proposed using the graph clustering method for view grouping and the random-walk algorithm is applied to adaptively update the weight of each view.
- 67
- 64
- 63
- 60
- 57
- Hierarchical multi-view context modelling for 3D object classification and retrieval55
A hierarchical multi-view context modelling method for 3D object classification and retrieval that can imitate the human need to look back and forth to identify and compare the discriminative parts of individual 3D objects based on a joint convolutional neural network and bidirectional long short-term memory network.
- 51
- Dual-level Embedding Alignment Network for 2D Image-Based 3D Object Retrieval46
This is the first unsupervised work to jointly realize cross-domain feature learning and distribution alignment in an end-to-end manner for this new task, 2D image-based 3D object retrieval.
- Human Action Recognition Based on Selected Spatio-Temporal Features via Bidirectional LSTM46
This paper proposes a novel framework that can select the discriminative part in the spatial dimension and enrich the modeling action of motion in the temporal dimension using multiple layers of a long short-term memory framework, which can learn compositional representations in space and time.
- Image-Based Virtual Try-On: A Survey45
This survey provides a comprehensive analysis of the state-of-the-art techniques and methodologies in aspects of pipeline architecture, person representation and key modules such as try-on indication, clothing warping and try-on stage in image-based virtual try-on.
- 44
- T2TD: Text-3D Generation Model Based on Prior Knowledge Guidance42
This paper proposes a novel text-3D generation model (T2TD), which aims to generate the target model based on the textual description with the aid of experiential knowledge and adopts a novel multi-layer transformer structure to progressively fuse this strongly related structure information and textual information, enhancing the final performance of the 3D generation model.
- 42
- Emotion-Based End-to-End Matching Between Image and Music in Valence-Arousal Space41
End-to-end matching between image and music based on emotions in the continuous valence-arousal (VA) space is studied, demonstrating the superiority of CDCML for emotion-based image andMusic matching as compared to the state-of-the-art approaches.
- HMNet: Hierarchical Multi-Scale Brain Tumor Segmentation Network40
This paper proposes a novel hierarchical multi-scale segmentation network (HMNet), which contains a high-resolution branch and parallel multi-resolution branches and proposes a lightweight conditional channel weighting block to reduce GPU memory and improve the efficiency of HMNet.
- 40
- 38
- 38
- Multi-modal Correlated Network for emotion recognition in speech37
A novel Multi-modal Correlated Network for emotion recognition aiming at exploiting the information from both audio and visual channels to achieve more robust and accurate detection and demonstrates the correlation information of multiple modals is crucial for automatic emotion recognition.
- Single/cross-camera multiple-person tracking by graph matching37
This work is the first to unify two kinds of tracking problems with the same framework by graph matching, and is mathematically formulated into the Rayleigh Quotients Maximization.
- Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation36
A Graph Disentangled Contrastive framework for CDR (GDCCDR) with personalized transfer by meta-networks and an adaptive parameter-free filter is proposed to gauge the significance of diverse interactions, thereby facilitating more refined disentangled representations.
- 35
- 35
- 35
- Multi-modal feature fusion based on multi-layers LSTM for video emotion recognition35
An LSTM-based model is proposed that can fully consider the relations among the utterances and also handle the multi-modal feature fusion problem in the learning process.
- 32
- Multigranular Visual-Semantic Embedding for Cloth-Changing Person Re-identification31
A novel multigranular visual-semantic embedding algorithm (MVSE) is proposed for cloth-changing person ReID, where visual semantic information and human attributes are embedded into the network, and the generalized features of human appearance can be well learned to effectively solve the problem of cloth- changing.
- 30
- 30
- MMJN: Multi-Modal Joint Networks for 3D Shape Recognition29
A novel multi-modal joint network (MMJN) for 3D shape recognition is proposed, which can consider the correlation between two different modalities to extract the robust feature vector and define the weight of differentmodalities features based on the statistic method and utilize the advantages of different modality to generate more robust feature.
- Multi-Level Policy and Reward Reinforcement Learning for Image Captioning29
This work proposes a novel multi-level policy and reward RL framework for image captioning that contains a Multi-Level Policy Network that can adaptively fuse the word- level policy and the sentence-levelpolicy for the word generation and a guidance term to bridge thepolicy and the reward for RL optimization.
- 3D object retrieval based on sparse coding in weak supervision29
This paper applies the sparse coding method in a weakly supervision manner to address 3D model retrieval and uses FDDL to learn dictionary to reconstruct query sample for retrieval.
- 28
- 28
- Semantic Consistency Guided Instance Feature Alignment for 2D Image-Based 3D Shape Retrieval27
A novel semantic consistency guided instance feature alignment network (SC-IFA), which designs two feature translators to transform the feature from one domain to another domain, and imposes the translation loss and correlation loss on the transformed features to preserve the semantic consistency.
- Multi-modal & Multi-view & Interactive Benchmark Dataset for Human Action Recognition27
This paper introduces a Multi-modal & Multi-view & Interactive (M2I) dataset, which is designed for the evaluation of the performances of human action recognition under multi-view scenario, and evaluates three representative methods for the single-view, cross view, and cross domain humanaction recognition on this dataset.
- HGAN26
A novel Holistic Generative Adversarial Network (HGAN) is proposed to solve the cross-domain feature representation problem and make the feature space of virtual characteristic view more inclined to thefeature space of the real picture.
- 26
- Convolutional deep learning for 3D object retrieval26
A feature extraction model based on convolutional neural networks (CNN) that extracts a set of 2D images from 3D model to represent each 3D object and nearest neighbor is used to compute the similarity between different 3D models in order to handle the retrieval problem.
- 3D Model Retrieval with Weighted Locality-constrained Group Sparse Coding26
This work proposes a view-based 3D model retrieval algorithm based on weighted locality-constrained group sparse coding that has demonstrated the effectiveness of the proposed method on the ETH3D model dataset.
- 25
- MV-CLIP: Multi-View CLIP for Zero-Shot 3D Shape Recognition24
This paper introduces view selection in the vision side that minimizes entropy to identify the most informative views for 3D shape and proposes hierarchical prompts combined of hand-crafted and GPT-generated prompts to refine predictions.
- 24
- 24
- Hierarchical Instance Feature Alignment for 2D Image-Based 3D Shape Retrieval24
HIFA consists of two modules, cross-modal instance feature learning and hierarchical instance feature alignment, and extensive experiments validate the superiority of HIFA for 2D image-based 3D shape retrieval task.
- SRNet: Structured Relevance Feature Learning Network From Skeleton Data for Human Action Recognition24
This paper proposes a novel data reorganizing strategy to represent the global and local structure information of human skeleton joints and proposes an end-to-end multi-dimensional CNN network to fully consider the spatial and temporal information to learn the feature extraction transform function.
- Cross-Domain 3D Model Retrieval via Visual Domain Adaption24
The proposed method can significantly outperform the most recent method for cross-domain 3D model retrieval and the champion of Shrec’16 Large-Scale 3D Shape Retrieval from ShapeNet Core55.
- 23
- Multi-Level Residual Feature Fusion Network for Thoracic Disease Classification in Chest X-Ray Images22
The proposed MLRFNet comprises two main components: a feature extractor that learns multi-scale semantic information from chest X-ray images and a multi-level residual feature classifier that refines disease-specific pathological features at spatial locations to reduce interference from irrelevant regions.
- Exposing DeepFake Videos Using Attention Based Convolutional LSTM Network22
A novel attention-based deep fake video detection method, which captures the sharp changes in terms of the facial features caused by the composite video, and utilizes the convolutional long short-term memory to extract both spatial and temporal information of DeeFake videos.
- MMFN22
MMFN is proposed, a novel multimodal fusion network for 3D shape recognition that employs correlations between the different modalities to generate a fused descriptor, which is more robust.
- Cross-view action recognition by cross-domain learning22
A novel cross-domain learning method to handle action recognition by discovering and sharing common knowledge among different video sets captured in multiple viewpoints and applying the block-wise weighted kernel function to leverage cross-view information.
- Evaluation of local spatial–temporal features for cross-view action recognition22
This paper evaluates four popular spatial-temporal features (STIP, Cuboids, MoSIFT, HoG3D) with the framework of transferable dictionary pair learning and demonstrates the superiority of this framework on cross-view human action recognition.
- 20
- 20
- 20
- 20
- Dynamic Causal Disentanglement Model for Dialogue Emotion Detection19
A Dynamic Causal Disentanglement Model is proposed, which effectively decomposes the content of dialogues and investigates the temporal accumulation of emotions, thereby enabling more precise emotion recognition.
- 19
- 18
- Efficient Spatio-Temporal Video Grounding with Semantic-Guided Feature Decomposition18
A novel Semantic-Guided Feature Decomposition based Network (SGFDN) is proposed to decompose the 3D spatio-temporal feature into 2D motions and 1D object embedding without losing much object-related semantic information, and the computational complexity in computationally expensive operations such as attention mechanisms can be effectively reduced.
- 18
- SHREC'18: RGB-D object-to-CAD retrieval18
Evaluation results show that while the RGB-D to CAD retrieval problem is indeed challenging due to incomplete RGB-D reconstructions, it can be addressed to a certain extent using deep learning techniques trained on multi-view 2D images or 3D point clouds.
- RGB-D Object-to-CAD Retrieval18
Evaluation results show that while the RGB-D to CAD retrieval problem is indeed challenging due to incomplete RGB-D reconstructions, it can be addressed to a certain extent using deep learning techniques trained on multi-view 2D images or 3D point clouds.
- 18
- 18
- TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models17
This study proposes TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation, and demonstrates its effectiveness in erasing malicious concepts while better preserving the model's original generation ability.
- 17
- 17
- MVCLN: Multi-View Convolutional LSTM Network for Cross-Media 3D Shape Recognition17
A novel Multi-view Convolutional L STM Network (MVCLN) is proposed, which utilizes the LSTM structure to extract temporal information and applies the convolutional operation to extract spatial information.
- HEp-2 cells Classification via clustered multi-task learning17
The extensive experiments on the Hep 2, cell dataset released by the HEp-2 Cells Classification contest show that the proposed method can discover and share the latent relatedness among multiple tasks and consequently augment the performance.
- 16
- 16
- Temporal-Spatial Correlation Attention Network for Clinical Data Analysis in Intensive Care Unit16
A temporal-spatial correlation attention network (TSCAN) is introduced to address various clinical characteristic prediction problems, including mortality prediction, length of stay prediction, physiologic decline detection, and phenotype classification.
- Point Cloud Adversarial Perturbation Generation for Adversarial Attacks16
This work proposes a novel framework to attack point cloud models by introducing the GAN structure, which trains a generator to produce slight point-to-point perturbations according to the sample’s raw classification, which can effectively boost the attack performance.
- 16
- 16
- Structure Causal Models and LLMs Integration in Medical Visual Question Answering15
This work proposes a causal inference framework for the MedVQA task, which effectively eliminates the relative confounding effect between the image and the question to ensure the precision of the question-answering (QA) session, and introduces a novel causal graph structure that represents the interaction between visual and textual elements.
- 15
- Triangle-Reward Reinforcement Learning15
This work argues that the XE objective is not sensitive to visual-linguistic alignment, which cannot discriminately penalize the semantic inconsistency and shrink the context gap, and proposes the Triangle-Reward Reinforcement Learning (TRRL) method, which demonstrates the superiority of TRRL on the MSCOCO dataset.
- Cross-domain semantic transfer from large-scale social media15
A cross-domain semantic modeling method for automatic image annotation for visual information from social network platforms, which leverages cross- domain datasets to discover the common knowledge of each semantic concept from UGCs and boost the performance of semantic annotation by semantic transfer.
- PAGN: perturbation adaption generation network for point cloud adversarial defense14
A novel perturbation adaption generation network for point cloud adversarial defense, which can adaptively generate adversarial point cloud samples according to the point cloud to improve the robustness of the deep learning model for the 3D model classification.
- 14
- 14
- Joint deep feature learning and unsupervised visual domain adaptation for cross-domain 3D object retrieval14
This paper proposes a joint deep feature learning and visual domain adaptation method (Deep-VDA) to solve the cross-domain 3D object retrieval problem by the end-to-end learning, benefiting from the advantages of deep learning networks.
- 2D Scene Sketch-Based 3D Scene Retrieval14
The objective of this track is to evaluate the performance of different 2D scene sketch-based 3D scene retrieval algorithms using a 2D sketch query dataset and a 3D Warehouse model dataset and suggest several future research directions to tackle this research problem.
- Subgraph learning for graph matching14
A novel approach is proposed to handle graph matching problem based on Markov Chain Monte Carlo framework that can effectively save matching pairwise under one-to-one matching constraints and also avoid the effect of outliers and deformation.
- 14
- Human Action Recognition Bases on Local Action Attributes14
This paper proposes an novel framework where introduces local action attributes to represent an action for the final human action categorization, which is no longer characterized with the motion changes in the temporal domain but the local semantic description of the action.
- Jointly Learning Multiple Sequential Dynamics for Human Action Recognition14
This work theoretically proposes the multi-task conditional random fields model and explores its application on human action recognition, and proposes the part-induced spatiotemporal action unit sequence to represent each action sample with multiple partwise sequential feature subspaces.
- 13
- My Brother Helps Me: Node Injection Based Adversarial Attack on Social Bot Detection13
This study proposes a node injection-based adversarial attack method designed to deceive bot detection models, and develops an attribute recovery module to revert the injected node embedding from the graph embedding space back to the original feature space, enabling the adversary to manipulate node perturbation effectively.
- 13
- 3D model retrieval based on multi-view attentional convolutional neural network13
A discriminative Multi-View Attentional Convolutional Neural Network, dubbed as MVA-CNN, which takes the multiple views of an shape as input and output the object category, which can discover the context among multiple views in both the visual and spatial domain.
- Effective 3D object detection based on detector and tracker13
This paper proposes a novel 3D object detection approach in real-world scenes combined RGB image based on MV-RED dataset and shows further major gains in accuracy when the training data from the target scenes is used, outperforming state-of-the-art approaches with far better efficiency.
- 3D Object Retrieval with Multimodal Views13
The evaluation results show a promising scenario about multimodal view-based 3D retrieval methods, and reveal interesting insights in dealing with multi-modal data.
- 3D shape knowledge graph for cross‐domain 3D shape retrieval12
This study presents an innovative notion, termed "geometric words", which functions as elemental constituents for representing entities through combinations, which functions as elemental constituents for representing entities through combinations in the knowledge graph.
- 12
- SVHAN: Sequential View Based Hierarchical Attention Network for 3D Shape Recognition12
This work proposes a novel sequential view based hierarchical attention network (SVHAN) for 3D shape recognition, and introduces a novel hierarchical feature aggregation module (HFAM) and a novel selective fusion module (SFM) for feature aggregation.
- MPAN: Multi-Part Attention Network for Point Cloud Based 3D Shape Retrieval12
A Multi-part attention network (MPAN) for 3D model retrieval based on point cloud is proposed, which introduces a novel self-attention mechanism to explore the correlations between different parts of point clouds and generates informative and discriminative shape descriptors.
- 12
- 11
- 11
- 11
- Self-supervised Image-based 3D Model Retrieval11
This article simultaneously optimize the adversarial adaptation for both domains based on visual features and the contrastive learning for unlabeled 3D model domain to help the feature extractor to learn discriminative feature representations.
- 11
- 11
- A comparison of methods for 3D scene shape retrieval11
A comprehensive comparison of all the above methods and an additional new retrieval methods are performed by evaluating them on the two benchmarks to solicit state-of-the-art approaches.
- The assessment of 3D model representation for retrieval with CNN-RNN networks11
The Euclidean distance is used to obtain the similarity measure between two different models for the retrieval problem and several classic 3D model retrieval and classification methods are leveraged as comparison methods in this paper.
- Hierarchical Graph Structure Learning for Multi-View 3D Model Retrieval11
An unsupervised hierarchical graph structure learning method for 3D model retrieval that can avoid the difficulty in definition and computation in the traditional high-order graph and can achieve competing performance against the most recent supervised & deep learning method.
- Mitosis event recognition and detection based on evolution of feature in time domain11
This paper presents an approach which utilized the evolution of feature in the time domain to represent the feature of mitosis and constructs the levels of motorists according to the steps of mitotic cells.
- 10
- 10
- Multi-graph Convolutional Network for Unsupervised 3D Shape Retrieval10
A novel multi-graph network (MGN) is proposed for unsupervised 3D shape retrieval, which utilizes the correlations among modalities and structural similarity between two models to guide the shape representation learning process without category information.
- Multi-scale CNNs for 3D model retrieval10
A novel multi-layer deep network structure is proposed, which owns the local and global information of a 3D object, and is used to compute the similarity between two different 3D models to complete the retrieval problem.
- Multimedia venue semantic modeling based on multimodal data10
This paper utilizes Recurrent Convolutional Networks to build the correlation between multimedia UGCs and text, and employs a graph clustering method to detect the latent multimedia topics for each venue and proposes techniques to model multimedia location topics and perform semantic-based location summarization, venue prediction and image description.
- 3D object retrieval based on Spatial+LDA model10
This paper applies LDA model for visual topics extraction and utilized the topic distribution visual feature of image to handle 3D object retrieval problem and proposes a multi-topic model to improve retrieval performance.
- Privacy-preserving Multi-source Cross-domain Recommendation Based on Knowledge Graph9
This work constructs a knowledge graph comprehensively leveraging items from multiple auxiliary domains to avoid the leakage of user privacy when user information is transferred to multiple domains, and proposes a knowledge graph-based retrieval and fusion method to transfer knowledge derived from multiple auxiliary domains.
- 3D Model Retrieval Based on a 3D Shape Knowledge Graph9
This paper introduces the concept of a geometric word that can be utilized to assemble other 3D model and constructs a 3D shape knowledge graph based on the geometric words, models and their relations, and proposes a novel graph embedding method to generate embeddings of nodes.
- Pairwise View Weighted Graph Network for View-based 3D Model Retrieval9
The pairwise view weighted graph network (abbreviated PVWGN) is proposed for view-based 3D model retrieval where non-local graph layers are embedded into the network architecture to automatically mine the intrinsic relationship among multiple views of a3D model.
- Frequency Estimator Based on Spectrum Correction and Remainder Sifting for Undersampled Real-Valued Waveforms9
This paper proposes an estimator combining spectrum correction, closed-form CRT, and a remainder sifting approach that can pick out the correct remainder between two side spectra, which ensures that the CRT achieves a valid reconstruction.
- 9
- Panorama based on multi-channel-attention CNN for 3D model recognition9
A panorama based on multi-channel-attention (MCA) CNN network for the representation of the 3D model and the attention model is used to find the unequal weights of each panorama view to generate the more robust3D model descriptor.
- Multi-guiding long short-term memory for video captioning9
A novel cell-wise ensemble, where the weight matrix of each cell of LSTM is extended to be a set of attribute-dependent and attention-dependent weight matrices, by which the guiders induce each cell optimization over time.
- 8
- CISepsis: a causal inference framework for early sepsis detection8
This method, based on causal inference, effectively removes the influence of confounding factors, significantly improving the predictive accuracy of the model and enhancing the model's generalizability, robustness, and interpretability.
- Instrumental Variable Learning for Chest X-ray Classification8
This paper focuses on the chest X-ray classification task and proposes an interpretable instrumental variable (IV) learning framework, to eliminate the spurious association and obtain accurate causal representation.
- 8
- 8
- Consistent Domain Structure Learning and Domain Alignment for 2D Image-Based 3D Objects Retrieval8
A domain alignment framework with consistent domain structure learning to reduce the large gap between 2D images and 3D objects and the experimental results demonstrate the proposed method outperforms the state-of-the-art methods.
- Causal inference model for accurate medical diagnosis in Coronary Artery Bypass Graft operation7
A novel Causal Inference Operation Risk Predictor (CIORP) is proposed that exceeds most existing methods in the internal Electronic Health Record of CABG patients, effectively predicting low cardiac output, new-onset atrial fibrillation, perioperative myocardial infarction, and cardiac arrest or ventricular fibrillation post-operation.
- 7
- A comprehensive survey on deep-learning-based visual captioning7
This paper presents a comprehensive survey of existing deep learning-based visual captioning methods, relying on the adopted mechanism and technique to narrow the semantic gap, and divides visual captioned methods into various groups.
- Multi-type decision fusion network for visual Q&A7
The novel multi-type decision fusion model, which can adaptively leverage object- and relation-level decision networks to infer the answer, is introduced.
- End-to-End Visual Domain Adaptation Network for Cross-Domain 3D CPS Data Retrieval7
An end-to-end domain adaptation framework for cross-domain 3D objects retrieval (C3DOR-Net), which learns a joint embedding space for3D objects from different domains in an end- to-end manner, and focuses on the unsupervised case when 3D Objects in the target domain are unlabeled.
- 3D models retrieval algorithm based on multimodal data7
A novel algorithm based on multimodal 3D model data to handle model retrieval problem is proposed, and a universal graph matching is employed to handle similarity measure in different modals respectively.
- Automatic report generation based on multi-modal information7
A new framework which can utilize multi-modal social media information to automatically generate related reports for users or government to demonstrate the effectiveness and the practicability of this approach is proposed.
- Quality models for venue recommendation in location-based social network7
A quality model for venue recommendation is proposed by utilizing multimedia data to predict the interested level of each venue and the weighted bipartite matching algorithm is implemented to generate the venue multimedia topics by bridging the textual information and the visual information.
- Venue Semantics: Multimedia Topic Modeling of Social Media Contents7
This paper proposes a novel multimedia topic modeling approach for extracting venue semantics from heterogeneous location-related UGCs and proposes the semantic based venue summarization, which verifies the effectiveness of the proposed framework.
- 6
- 6
- Cross-Domain 3D Model Retrieval Based On Contrastive Learning And Label Propagation6
This work proposes the consistent decision for pseudo labels of 3D models based on both the trained image classifier and label propagation and utilizes contrastive learning for fine-grained category-level alignment across domains.
- 6
- 6
- Multi-view feature extraction based on slow feature analysis6
This paper built the input data in order to guarantee it suitable for SFA mode according to structure information of3D model and employed graph matching to handle similarity measure problem between two different 3D model.
- 5
- Point‐PC: Point cloud completion guided by prior knowledge via causal inference5
The authors design a pre‐training strategy that uses contrastive learning to map incomplete shape features into the complete shape feature domain, enabling retrieval of analogous shapes from incomplete inputs, and employ backdoor adjustment to eliminate confounders.
- Causal Inference-Based Self-Supervised Cross-Domain Fundus Image Segmentation5
A Causal Self-Supervised Network (CSSN) that leverages self-supervised learning to enhance model performance and employ adversarial training and cross-domain contrastive learning to further reduce style discrepancies between domains is proposed.
- 5
- 5
- 5
- 5
- 5
- Two-Stream Network Based on Visual Saliency Sharing for 3D Model Recognition5
The experimental result on two public datasets, ModelNet40 and ShapeNetCore55, demonstrates the correlation information of multiple views is crucial for view-based 3D model recognition methods and the proposed method can achieve the state-of-the-art performance on both 3D object classification and retrieval.
- View-Based 3D Model Retrieval by Joint Subgraph Learning and Matching5
A joint subgraph learning & matching method (SGLM) via Markov Chain Monte Carlo (MCMC) to handle view-based 3D model retrieval problem, which effectively combine representation view extraction with similarity measure process to find the best matching result.
- Location emotion recognition for travel recommendation based on social network5
A novel multimedia location emotion recognition model is proposed to handle the problem of obtaining others’ reviews on one venue from the different social network places and output the emotion label of the given venue.
- Unsupervised Feature Learning With Graph Embedding for View-Based 3D Model Retrieval5
The proposed method utilizes both similarity and dissimilarity information to better leverage the unsupervised problem and estimates the labels which are further used for metric learning.
- Multiple Person Tracking based on Spatial-temporal Information by Global Graph Clustering5
A graph clustering method based on spatio-temporal information of moving objects for multiple person tracking using the graph shift method to handle tracklet association problem and consequently generate the completed trajectory for individual object.
- MF-GCN: Multimodal Information Fusion Using Incremental Graph Convolutional Network for Ship Behavior Anomaly Detection4
Results verify the effectiveness of the proposed MF-GCN method for robust multimodal anomaly detection and early warning in inland-waterway scenarios.
- 4
- 4
- 4
- Organ-Agents: Virtual Human Physiology Simulator via LLMs4
Organ-Agents is position as a credible, interpretable, and generalizable digital twin for precision diagnosis, treatment simulation, and hypothesis testing in critical care.
- Brain tumor image segmentation based on prior knowledge via transformer4
This work introduces the prior knowledge learned to filter the noise information and guide the final network to generate a more accurate segmentation model for brain tumor segmentation results.
- 4
- PGNet: Progressive Feature Guide Learning Network for Three-dimensional Shape Recognition4
This article proposes a novel progressive feature guide learning network (PGNet) that focuses on the correlation among multiple views and integrates multiple modalities for 3D shape recognition and proposes two information fusion schemes from visual and feature aspects.
- Visual attribute detction for pedestrian detection4
Two baseline methods are utilized to demonstrate the performance of the attribute in pedestrian detection and an evaluation protocol is proposed for researchers to evaluate pedestrian attribute classification algorithms.
- 4
- 3
- 3
- Progressive Positive Association Framework for Image and Text Retrieval3
A novel Progressive Positive Association Framework is proposed, which models association uncertainty as a normal distribution and progressively mines direct and potential positive associations according to the characteristics of the association distribution and applies KL loss constraint on cross-modal association distribution in order to enhance local semantic alignment.
- Unknown Fault Detection of Rolling Bearing Based on Similarity Mining of Stationary and Non-stationary Features3
This paper proposes a framework for bearing unknown fault detection based on stationary and non-stationary feature mining, which demonstrates its superiority over other state-of-the-art methods, resulting in a significant enhancement in accuracy.
- HMTN: Hierarchical Multi-scale Transformer Network for 3D Shape Recognition3
In HMTN, a multi-level regional transformer (MLRT) module for shape descriptor generation is proposed, which can comprehensively consider the relations of different regions and focus on the discriminative parts, which improves the effectiveness of the learned descriptors.
- Multi-View Graph Matching for 3D Model Retrieval3
A multi-view graph matching method (MVGM) for 3D model retrieval that can avoid the difficulty in the definition and computation of the traditional high-order graph and does not require a large-scale 3D dataset for model learning.
- View-based 3D model retrieval via supervised multi-view feature learning3
An effective view-based 3D model retrieval method via supervised multi-view feature learning (SMFL) via Singular Value Decomposition (SVD) algorithm, which helps to calculate the similarities between two different 3D models.
- View-Based 3D Model Retrieval via Multi-graph Matching3
A composition-based multi-graph matching method that seeks the optimal intermediate graph by diverse graph matching orders, according to the consistency of global matching, using the classic optimization method.
- Spatial Context Constrained Characteristic View Extraction for 3D Model Retrieval3
A view-based 3D model retrieval method based on spatial context constrained characteristic view extraction method that applies Bayesian model to compute the similarity between query model and candidate3D model to find the best matching 3D models.
- Causal Intervention-Based Multimodal Class-Incremental Learning Network for 3D Model Classification and Retrieval2
This work proposes a causal intervention-based multimodal class-incremental learning framework to address the stability-plasticity trade-off in 3D model classification and retrieval tasks and achieves state-of-the-art performance compared to competitive baselines.
- 2
- 2
- 2
- Point Cloud Completion Guided by Prior Knowledge via Causal Inference2
A novel approach to point cloud completion is proposed called Point-PC, which uses a memory network to retrieve shape priors and designs an e-ective causal inference model to choose missing shape information as additional geometric information to aid point cloud completion.
- 2
- Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery2
A Reinforcement Learning framework is employed to simulate the cognitive processes of humans for effectively addressing novel class discovery in the Open-set domain and enables effective control over the extent of exploration learning, ensuring the accuracy of learning in unknown data categories.
- 2
- An End-to-End Perceptual Quality Assessment Method via Score Distribution Prediction2
This paper proposes to predict the distribution of opinion scores via an end-to-end convolutional neural network based on a pre-trained ResNet with 50 layers and a novel Statistical Region-of-Interest Pooling layer is introduced for lower model complexity, which enables effective training with few datum.
- Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA1
Qualitative analyses confirm that DCI significantly enhances the interpretability and robustness of cross-modal reasoning by explicitly disentangling true causal effects from spurious cross-modal shortcuts.
- When Headlines Meet Minds: Empowering News Recommendations with Social Simulator1
Inspired by social constructionism, Social Review-aware Recommendation (SRec) is proposed, a novel framework that integrates both objective content and the social review that integrates both objective content and the social review.
- 1
- 1
- 1
- Ovarian Ultrasound Image Segmentation Algorithm with Fused Multi-Scale Features1
An innovative algorithm for ovarian ultrasound image segmentation that incorporates multi-scale features that effectively processes image data with varying scales is proposed, offering a new solution for ovarian ultrasound image segmentation.
- RJAN: Region‐based joint attention network for 3D shape recognition1
A novel architecture named region‐based joint attention network (RJAN) was proposed, which achieves state‐of‐the‐art performance in the tasks of 3D shape classification and 3D shape retrieval, which demonstrates the effectiveness of RJAN.
- Causal Disentanglement Hidden Markov Model for Fault Diagnosis1
A Causal Disentanglement Hidden Markov model (CDHM) is proposed to learn the causality in the bearing fault mechanism and thus, capture their characteristics to achieve a more robust representation.
- Principal views selection based on growing graph convolution network for multi-view 3D model recognition1
This paper focuses on the multi-view 3D model data and proposes a novel growing graph convolution network (GGCN) to handle the principal views selection problem, which can guarantee the performance of3D model representation and effectively reduce the cost time.
- Pooled time series representation for mitosis event recognition1
A new feature representation for mitotic event detection in time-lapse phase contrast microscopy image sequences of stem cell populations by keeping track of how descriptor values are changing over time and summarize them to represent appearance in the cell sequence.
- 3D model retrieval via single image based on feature mapping1
A novel 3D model retrieval algorithm by cross-modal feature mapping (CMFM), which utilize one single image as query information to address 3D models retrieval problem, and is the first method to handle3D model retreival based on one single 2D image.
- Geo-location driven image tagging via cross-domain learning1
A novel cross-domain learning method for automatic image annotation with geo-location information is proposed and the topic model-based method for popular concept extraction to adaptively construct cross- domain datasets is proposed.
- An Effective Tracking System for Multiple Object Tracking in Occlusion Scenes1
An effective multi-object tracking system which can handle the partial occlusion in the tracking process and employs the part-based model to localize the person and body parts in every frame is proposed.
- Ask4VG: Risk-Aware Question Selection for Reducing Prior-Driven Answers in Medical VQA–
Ask4VG is proposed, a label-free pilot framework for risk-aware question selection that suggests that question selection is a promising complement to response-level hallucination mitigation for reliable medical VQA.
- Learning a Normal World Model for Few-Shot Boundary-Calibrated Abnormality Detection–
It is suggested that normal-world energy can serve as an anomaly score, a graded risk measure, and a testable representation of normal system behavior under severe abnormal-label scarcity.
- Continuous-Time Transformer with Adaptive Mutation-Locking for Early Prediction of Acute Kidney Injury–
The CT-Former framework is proposed, which integrates continuous time neural networks with a transformer to preserve irregular patient trajectories without biased data imputation and establishes a transparent temporal attribution architecture that delivers exceptional predictive robustness while entirely avoiding spurious statistical correlations.
- –
- –
- –
- Causal-Transformer with Adaptive Mutation-Locking for Early Prediction of Acute Kidney Injury–
CT-Former, integrating continuous-time modeling with a Causal-Transformer, provides native clinical interpretability by establishing clear causal pathways between historical anomalies and current risk predictions, and confirms that it offers an accurate and trustworthy tool for clinical decision-making.
- Hypergraph Normal World Models for Logical Visual Anomaly Detection–
The Hypergraph Normal World Model is proposed, a normal-only detector that distills frozen DINOv2 patch tokens into patch, relation, and hypergraph statistics, and shows that high scores are driven by relation-bearing terms.
- Hypergraph normal world modeling for normal-only logical visual anomaly detection–
The Hypergraph Normal World Model is proposed, a deployment-oriented framework that distills frozen DINOv2 patch tokens into patch, relation, and hypergraph statistics and obtains the best average logical-anomaly AUROC among reproduced methods.
- Prototype Latent World Model Replay for Class-Incremental Learning–
The results suggest that prototype latent memory preserves reusable class-state distributions, rather than only fitting the current classifier, rather than only fitting the current classifier.
- –
- Multi-layers CNNs for 3D Model Retrieval–
A multi-layers CNNs (MLCNN) structure for 3D model representation is proposed and the Euclidean metric is leveraged to compute the similarity between two different 3D models to complete the retrieval problem.
- TJU-TJUT@TRECVID 2015: Surveillance Event Detection.–
An event detection system evaluated in 2015 TRECVID-SED and an interactive visual analytics system, which can enable effective rank detection results with score relations and utilize user feedbacks to improve surveillance event detection are presented.
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.