2025
Semantic-Aware Late-Stage Supervised Contrastive Learning for Fine-Grained Action Recognition.
IEEE Trans. Circuits Syst. Video Technol., June, 2025
Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation.
CoRR, June, 2025
Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG.
CoRR, May, 2025
R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning.
CoRR, April, 2025
The Mirage of Performance Gains: Why Contrastive Decoding Fails to Address Multimodal Hallucination.
CoRR, April, 2025
Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference.
CoRR, March, 2025
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models.
CoRR, March, 2025
Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization.
Neural Networks, 2025
Context Sensitive Network for weakly-supervised fine-grained temporal action localization.
Neural Networks, 2025
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
GCD: Advancing Vision-Language Models for Incremental Object Detection via Global Alignment and Correspondence Distillation.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025
Protecting Model Adaptation from Trojans in the Unlabeled Data.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025
Exploring Vacant Classes in Label-Skewed Federated Learning.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025
Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025
2024
Federated Local Compact Representation Communication: Framework and Application.
Mach. Intell. Res., December, 2024
Learning Lightweight Dynamic Kernels With Attention Inside via Local-Global Context Fusion.
IEEE Trans. Neural Networks Learn. Syst., July, 2024
Comprehensive Relation Modelling for Image Paragraph Generation.
Mach. Intell. Res., April, 2024
RISTRA: Recursive Image Super-Resolution Transformer With Relativistic Assessment.
IEEE Trans. Multim., 2024
Weakly supervised temporal action localization with actionness-guided false positive suppression.
Neural Networks, 2024
Restoration towards decomposition: A simple approach for domain generalization.
Inf. Sci., 2024
Towards Compatible Fine-tuning for Vision-Language Model Updates.
CoRR, 2024
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment.
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Can We Trust the Unlabeled Target Data? Towards Backdoor Attack and Defense on Model Adaptation.
CoRR, 2024
Not all Minorities are Equal: Empty-Class-Aware Distillation for Heterogeneous Federated Learning.
CoRR, 2024
DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024
Learning Energy-Based Models for 3D Human Pose Estimation.
Proceedings of the International Joint Conference on Neural Networks, 2024
Probabilistic Contrastive Learning for Domain Adaptation.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024
Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Delve into Source and Target Collaboration in Semi-supervised Domain Adaptation for Semantic Segmentation.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2024
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Semantic-Guided Robustness Tuning for Few-Shot Transfer Across Extreme Domain Shift.
Proceedings of the Computer Vision - ECCV 2024, 2024
Efficient Active Domain Adaptation for Semantic Segmentation by Selecting Information-Rich Superpixels.
Proceedings of the Computer Vision - ECCV 2024, 2024
Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024
A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
2023
Improve Temporal Action Proposals using Hierarchical Context.
Pattern Recognit., August, 2023
Learning complementary semantic information for zero-shot recognition.
Signal Process. Image Commun., July, 2023
A super-resolution strategy for mass spectrometry imaging via transfer learning.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Nat. Mac. Intell., June, 2023
Few-shot learning with unsupervised part discovery and part-aligned similarity.
Pattern Recognit., 2023
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification.
CoRR, 2023
Improving Zero-Shot Generalization for CLIP with Synthesized Prompts.
CoRR, 2023
Semantic Prompt for Few-Shot Image Recognition.
CoRR, 2023
AdaptGuard: Defending Against Universal Attacks for Model Adaptation.
CoRR, 2023
Exploiting Semantic Attributes for Transductive Zero-Shot Learning.
CoRR, 2023
Video Semantic Segmentation with Inter-Frame Feature Fusion and Inner-Frame Feature Refinement.
CoRR, 2023
Semi-supervised Domain Adaptation via Joint Contrastive Learning with Sensitivity.
Proceedings of the 31st ACM International Conference on Multimedia, 2023
Sparse Sharing Relation Network for Panoptic Driving Perception.
Proceedings of the 31st ACM International Conference on Multimedia, 2023
Exploiting Low-confidence Pseudo-labels for Source-free Object Detection.
Proceedings of the 31st ACM International Conference on Multimedia, 2023
Unleashing the Potential of Adjacent Snippets for Weakly-supervised Temporal Action Localization.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2023
Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain Adaptation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Preparing the Future for Continual Semantic Segmentation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Notice of Removal: Exploiting Semantic Attributes for Transductive Zero-Shot Learning.
Proceedings of the IEEE International Conference on Acoustics, 2023
Noise-Robust Semi-Supervised Learning for Distantly Supervised Relation Extraction.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Boundary-enhanced Co-training for Weakly Supervised Semantic Segmentation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
SimpleNet: A Simple Network for Image Anomaly Detection and Localization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Actionness Inconsistency-Guided Contrastive Learning for Weakly-Supervised Temporal Action Localization.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
Leveraging Sub-class Discimination for Compositional Zero-Shot Learning.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
Exploit Domain-Robust Optical Flow in Domain Adaptive Video Semantic Segmentation.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
2022
Combining 2D texture and 3D geometry features for Reliable iris presentation attack detection using light field focal stack.
IET Biom., September, 2022
Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds.
IEEE Trans. Intell. Transp. Syst., 2022
Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations.
CoRR, 2022
Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization.
CoRR, 2022
Low-confidence Samples Matter for Domain Adaptation.
CoRR, 2022
Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022
Semantic-enhanced Graph Voxelization for Pillar-based 3D Detection from Point Clouds.
Proceedings of the 25th IEEE International Conference on Intelligent Transportation Systems, 2022
Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring.
Proceedings of the International Conference on Machine Learning, 2022
Collaborating Domain-Shared and Target-Specific Feature Clustering for Cross-domain 3D Action Recognition.
Proceedings of the Computer Vision - ECCV 2022, 2022
Continual Semantic Segmentation via Structure Preserving and Projected Feature Alignment.
Proceedings of the Computer Vision - ECCV 2022, 2022
Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations.
Proceedings of the Computer Vision - ECCV 2022, 2022
Semi-Supervised Video Semantic Segmentation with Inter-Frame Feature Reconstruction.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
2021
Meta-USR: A Unified Super-Resolution Network for Multiple Degradation Parameters.
IEEE Trans. Neural Networks Learn. Syst., 2021
Video Semantic Segmentation With Distortion-Aware Feature Correction.
IEEE Trans. Circuits Syst. Video Technol., 2021
Parallel Point Clouds: Hybrid Point Cloud Generation and 3D Model Enhancement via Virtual-Real Integration.
Remote. Sens., 2021
Separated smooth sampling for fine-grained image classification.
Neurocomputing, 2021
5th Place Solution for VSPW 2021 Challenge.
CoRR, 2021
Probability Contrastive Learning for Domain Adaptation.
CoRR, 2021
Multi-level Discriminator and Wavelet Loss for Image Inpainting with Large Missing Area.
Proceedings of the Pattern Recognition and Computer Vision - 4th Chinese Conference, 2021
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images.
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021
RPN Prototype Alignment for Domain Adaptive Object Detector.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Iris Normalization Beyond Appr-Circular Parameter Estimation.
Proceedings of the Biometric Recognition - 15th Chinese Conference, 2021
Efficient License Plate Recognition via Holistic Position Attention.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021
Learning Intact Features by Erasing-Inpainting for Few-shot Classification.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021
2020
Proportional-Fair Multi-User Scalable Layered Wireless Video Streaming Powered by Energy Harvesting.
IEEE Trans. Veh. Technol., 2020
High-fidelity View Synthesis for Light Field Imaging With Extended Pseudo 4DCNN.
IEEE Trans. Computational Imaging, 2020
Adaptive and azimuth-aware fusion network of multimodal local features for 3D object detection.
Neurocomputing, 2020
Image Inpainting with Contrastive Relation Network.
Proceedings of the 25th International Conference on Pattern Recognition, 2020
Polynomial Regression Network for Variable-Number Lane Detection.
Proceedings of the Computer Vision - ECCV 2020, 2020
Joint Adversarial Learning for Domain Adaptation in Semantic Segmentation.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
Progressive Boundary Refinement Network for Temporal Action Detection.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
2019
Dense 3D-Convolutional Neural Network for Person Re-Identification in Videos.
ACM Trans. Multim. Comput. Commun. Appl., 2019
Software-Defined Multimedia Streaming System Aided By Variable-Length Interval In-Network Caching.
IEEE Trans. Multim., 2019
Compressed-Domain Highway Vehicle Counting by Spatial and Temporal Regression.
IEEE Trans. Circuits Syst. Video Technol., 2019
Feedback Convolutional Neural Network for Visual Localization and Segmentation.
IEEE Trans. Pattern Anal. Mach. Intell., 2019
Pillar in Pillar: Multi-Scale and Dynamic Feature Extraction for 3D Object Detection in Point Clouds.
CoRR, 2019
Densely Supervised Hierarchical Policy-Value Network for Image Paragraph Generation.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
Learning a Unified Classifier Incrementally via Rebalancing.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
Weighted Channel Dropout for Regularization of Deep Convolutional Neural Network.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019
2018
Dynamic Resource Allocation and Layer Selection for Scalable Video Streaming in Femtocell Networks: A Twin-Time-Scale Approach.
IEEE Trans. Commun., 2018
Object detection via deeply exploiting depth information.
Neurocomputing, 2018
Towards Human-Level License Plate Recognition.
Proceedings of the Computer Vision - ECCV 2018, 2018
End-to-End View Synthesis for Light Field Imaging with Pseudo 4DCNN.
Proceedings of the Computer Vision - ECCV 2018, 2018
Lifelong Learning via Progressive Distillation and Retrospection.
Proceedings of the Computer Vision - ECCV 2018, 2018
CCNet: Cluster-Coordinated Net for Learning Multi-agent Communication Protocols with Reinforcement Learning.
Proceedings of The 10th Asian Conference on Machine Learning, 2018
SMC: Single-Stage Multi-location Convolutional Network for Temporal Action Detection.
Proceedings of the Computer Vision - ACCV 2018, 2018
Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018
2017
Background-Driven Salient Object Detection.
IEEE Trans. Multim., 2017
Salient object detection via saliency bias and diffusion.
Multim. Tools Appl., 2017
Action recognition with low observational latency via part movement model.
Multim. Tools Appl., 2017
Improving human action recognitionby temporal attention.
Proceedings of the 2017 IEEE International Conference on Image Processing, 2017
DualNet: Learn Complementary Features for Image Recognition.
Proceedings of the IEEE International Conference on Computer Vision, 2017
VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization.
Proceedings of the IEEE International Conference on Computer Vision, 2017
Learning the Frame-2-Frame Ego-Motion for Visual Odometry with Convolutional Neural Network.
Proceedings of the Computer Vision - Second CCF Chinese Conference, 2017
2016
A simple and robust super resolution method for light field images.
Proceedings of the 2016 IEEE International Conference on Image Processing, 2016
Highway Vehicle Counting in Compressed Domain.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
Deeply Exploit Depth Information for Object Detection.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2016
Stacked Overcomplete Independent Component Analysis for Action Recognition.
Proceedings of the Computer Vision - ACCV 2016, 2016
2015
Collaborative Linear Coding for Robust Image Classification.
Int. J. Comput. Vis., 2015
Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015
2014
Autogrouped Sparse Representation for Visual Analysis.
IEEE Trans. Image Process., 2014
Salient Object Detection via Saliency Spread.
Proceedings of the Computer Vision - ACCV 2014 Workshops, 2014
2013
Image Classification via Object-Aware Holistic Superpixel Selection.
IEEE Trans. Image Process., 2013
Linear Distance Coding for Image Classification.
IEEE Trans. Image Process., 2013
Multi-class learning from class proportions.
Neurocomputing, 2013
2012
Purposive Hidden-Object-Game: Embedding Human Computation in Popular Game.
IEEE Trans. Multim., 2012
Auto-Grouped Sparse Representation for Visual Analysis.
Proceedings of the Computer Vision - ECCV 2012, 2012
2010
Scene aware smooth playout control for portable media players over random VBR channels.
IEEE Trans. Consumer Electron., 2010
A relaxing bandwidth smoothing schedule for transmitting prerecorded VBR video in periodic network.
Multim. Syst., 2010
Markov Decision Process Model for Path Selection Algorithm on Multi-Business System with Services Composition.
J. Convergence Inf. Technol., 2010
2009
Generalized PCRTT Offline Bandwidth Smoothing Based on SVM and Systematic Video Segmentation.
IEEE Trans. Multim., 2009
Calculating Minimum Buffer Requirement of Constant Rate Transmission Scheme Based on SVM.
Proceedings of the Ninth IEEE International Conference on Computer and Information Technology, 2009
2005
A Fast Online SVM Algorithm for Variable-Step CDMA Power Control.
Proceedings of the Advances in Natural Computation, First International Conference, 2005