Publications
Most of my papers listed below are published in top-tier international conferences and journals in the field of computer vision, machine learning, artificial intelligence and multimedia, which are very selective with an acceptance rate in general below 25%.
2026
- KDDExploring Diffusion Models’ Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural NetworksIn Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026
- AAAIPoisoning with A Pill: Circumventing Detection in Federated LearningIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2026
2025
- ICCVStealthy Backdoor Attack in Federated Learning via Adaptive Layer-wise Gradient AlignmentIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025
- KDDHt-FLlib: A Comprehensive Heterogeneous Federated Learning Library and BenchmarkIn Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025Runner Ups for the Best Paper – Dataset and Benchmark Track
- ICMLDifferentially Private Synthetic Image Generation with Few-Shot Data and Generative APIsIn Proceedings of the International Conference on Machine Learning (ICML), 2025Spotlight
- ICMLTraining Diffusion-based Generative Models with Limited DataIn Proceedings of the International Conference on Machine Learning (ICML), 2025
- CVPRImproving the Training of Data Efficient GANs via Quality Aware Dynamic Discriminator Rejection SamplingIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
- AISTATSLearning Identifiable Structures Avoids Bias in DNN-based Supervised Causal LearningIn Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2025
- TCSVTCAMD: Context-Aware Masked Distillation for General Self-Supervised Facial Representation Pre-TrainingIEEE Transactions on Circuits and Systems for Video Technology, 2025
- TMMHierarchical Token-Aware Cross-Modality Reconstruction for Visible-Infrared Person Re-IdentificationIEEE Transactions on Multimedia, 2025
2024
- ACMMMImproving the Training of the GANs with Limited Data via Dual Adaptive Noise InjectionIn Proceedings of the ACM Multimedia Conference (ACMMM), 2024
- ECCVSkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable MasksIn Proceedings of the European Conference on Computer Vision (ECCV), 2024
- CVPRCGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient InversionIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
- CVPRAn Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated LearningIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
- VLDBOFL-W3: A One-shot Federated Learning System on Web 3.0In Proceedings of the International Conference on Very Large Databases (VLDB), 2024Demonstration Track
- ICLRBackdoor Federated Learning by Poisoning Backdoor-Critical LayersIn Proceedings of the International Conference on Learning Representations (ICLR), 2024
- AAAICheaper and Faster: Distributed Deep Reinforcement Learning with Serverless ComputingIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024
- AAAIFedTGP: Heterogeneous Federated Learning via Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive LearningIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024
- WACVImproving the Fairness of the Min-Max Game in GANs TrainingIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024Oral
- WACVImproving the Leaking of Augmentations in Data-Efficient GANs via Adaptive Negative Data AugmentationIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
- JMLRPFLlib: Personalized Federated Learning Algorithm LibraryJournal of Machine Learning Research, 2024
- TCSVTDHLA: Dynamic Hybrid Label Assignment for End-to-End Object DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2024
- TCSVTUnpaired Caricature-Visual Face Recognition via Feature Decomposition-Restoration-DecompositionIEEE Transactions on Circuits and Systems for Video Technology, 2024
- TDSSiren+: Robust Federated Learning with Proactive Alarming and Differential PrivacyIEEE Transactions on Dependable and Secure Computing, 2024
2023
- NeurIPSEliminating Domain Bias for Federated Learning in Representation SpaceIn Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2023
- ECAIInformation Bound and its Applications in Bayesian Neural NetworksIn Proceedings of the European Conference on Artificial Intelligence (ECAI), 2023
- ICCVSpatio-temporal Prompting Network for Robust Video Feature ExtractionIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023
- ICCVGPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated LearningIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023
- KDDFedCP: Separating Feature Information for Personalized Federated Learning via Conditional PolicyIn Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023
- ICMLAdversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial ExamplesIn Proceedings of the International Conference on Machine Learning (ICML), 2023Oral
- ICASSPOnline Residual-Based Key Frame Sampling with Self-Coach Mechanism and Adaptive Multi-Level Feature FusionIn Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023
- ICASSPCross-Domain Learning with Normalizing FlowIn Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023Oral
- ICASSPFlowReg: Latent Space Regularization using Normalizing Flow for Limited Samples LearningIn Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023
- AAAIFedALA: Adaptive Local Aggregation for Personalized Federated LearningIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023Oral
- MMMSelf-supervised Multi-object Tracking with Cycle-consistencyIn Proceedings of the International Conference on Multimedia Modeling (MMM), 2023
- TCBBMCAS-GP: Deep Learning-Empowered Middle Cerebral Artery Segmentation and Gate PropositionIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2023
- CSURResource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level TechniquesACM Computing Surveys, 2023
- TNNLSDiscrepancy-Guided Domain-Adaptive Data AugmentationIEEE Transactions on Neural Networks and Learning Systems, 2023† corresponding author
2022
- ECCVTDViT: Temporal Dilated Transformer for Dense Video TasksIn Proceedings of the European Conference on Computer Vision (ECCV), 2022
- ECCVEfficient One-stage Video Object Detection by Exploiting Temporal ConsistencyIn Proceedings of the European Conference on Computer Vision (ECCV), 2022
- AAAIImproving Bayesian Neural Networks by Adversarial SamplingIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022
- TPAMIRanked List Loss for Deep Metric LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022† corresponding author
- TBDTowards Ubiquitous Intelligent Computing: Heterogeneous Distributed Deep Neural NetworksIEEE Transactions on Big Data, 2022
- TDSHierarchical Satellite System Graph for Approximate Nearest Neighbor Search on Big DataACM/IMS Transactions on Data Science, 2022
- TCBBPerceptual Data Augmentation for Biomedical Coronary Vessel SegmentationIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022
- TOMMRobust Searching-based Gradient Collaborative Management in Intelligent Transportation SystemACM Transactions on Multimedia Computing, Communications, and Applications, 2022
- CADHierarchical CADNet: Learning from B\text-Reps for Machining Feature RecognitionCAD Computer Aided Design, 2022
2021
- BMVCTemporal Meta-Adaptor for Video Object DetectionIn Proceedings of the British Machine Vision Conference (BMVC), 2021Oral
- SoCCSiren: Byzantine-robust Federated Learning via Proactive AlarmingIn Proceedings of the ACM Symposium on Cloud Computing (SoCC), 2021
- ICCVSelf-Supervised Vessel Segmentation via Adversarial LearningIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021
- CISP-BMEIPositional Mask Attention for Video Sequence ModelingIn Proceedings of the International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), 2021
- ICIPFast and Accurate Scene Parsing via Bi-Direction Alignment NetworksIn Proceedings of the IEEE International Conference on Image Processing (ICIP), 2021
- IJCAIThemis: A Fair Evaluation Platform for Computer Vision CompetitionsIn Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2021
- CVPRRobust Bayesian Neural Networks by Spectral Expectation Bound RegularizationIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
- CVPRProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural NetworksIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
- ICASSPFine-Grained Pose Temporal Memory Module for Video Pose Estimation and TrackingIn Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
- AAAIMAMBA: Multi-level Aggregation via Memory Bank for Video Object DetectionIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021
- NETWORKSpaceDML: Enabling Distributed Machine Learning in Space Information NetworksIEEE Network, 2021
- TCSVTSemantic-Aware Occlusion-Robust Network for Occluded Person Re-IdentificationIEEE Transactions on Circuits and Systems for Video Technology, 2021
2020
- CADPoint Cloud Dataset Creation for Machine Learning on CAD ModelsIn Proceedings of the CAD Conference and Exhibition, 2020
- ICPRVTT: Long-term Visual Tracking with TransformersIn Proceedings of the International Conference on Pattern Recognition (ICPR), 2020Oral
- ECCVReducing Distributional Uncertainty by Mutual Information Maximisation and Transferable Feature LearningIn Proceedings of the European Conference on Computer Vision (ECCV), 2020
- ICIPImproving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GANIn Proceedings of the IEEE International Conference on Image Processing (ICIP), 2020
- IDETC/CIEGraph Representation of 3D CAD Models for Machining Feature Recognition with Deep LearningIn Proceedings of the International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC/CIE), 2020
- AAAIReinforcing Neural Network Stability with Attractor DynamicsIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020Spotlight
- AAAILearning Deep Relations to Promote Saliency DetectionIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020Oral
- NEUCOMObject-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data AugmentationNeurocomputing, 2020
- CADAPoint Cloud Dataset Creation for Machine Learning on CAD ModelsComputer-Aided Design and Applications, 2020
- ACCESSAn RSS-Based Classification of User Equipment Usage in Indoor Millimeter Wave Wireless Networks using Machine LearningIEEE Access, 2020
- NEUCOMVideo Salient Object Detection via Spatiotemporal Attention Neural NetworksNeurocomputing, 2020
2019
- ICCVObject Guided External Memory Network for Video Object DetectionIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019
- ACMMMUnsupervised Video Summarization with Attentive Conditional Generative Adversarial NetworksIn Proceedings of the ACM Multimedia Conference (ACMMM), 2019Oral
- BMVCSC-RANK: Improving Convolutional Image Captioning with Self-Critical Learning and Ranking Metric-based RewardIn Proceedings of the British Machine Vision Conference (BMVC), 2019
- CVPRRanked List Loss for Deep Metric LearningIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
- AAAIDeep Metric Learning by Online Soft Mining and Class-Aware AttentionIn Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019Oral
- WACVGAN-based Pose-aware Regulation for Video-based Person Re-identificationIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2019Oral
- WACVIEGAN: Multi-purpose Perceptual Quality Image Enhancement Using Generative Adversarial NetworkIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2019Oral
- TCSVTWeakly Supervised Salient Object Detection with Spatiotemporal Cascade Neural NetworksIEEE Transactions on Circuits and Systems for Video Technology, 2019
2018
- BIBMDeep Learning based Fetal Middle Cerebral Artery Segmentation in Large-scale Ultrasound ImagesIn Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2018
- ACMMMTracking-assisted Weakly Supervised Online Visual Object Segmentation in Unconstrained VideosIn Proceedings of the ACM Multimedia Conference (ACMMM), 2018
- ECCVDeep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental StatesIn Proceedings of the European Conference on Computer Vision (ECCV), 2018
- ICPRObject-Adaptive LSTM Network for Visual TrackingIn Proceedings of the International Conference on Pattern Recognition (ICPR), 2018
- TIPCross-view Discriminative Feature Learning for Person Re-IdentificationIEEE Transactions on Image Processing, 2018† corresponding author
2017
- ICCVAttribute-Enhanced Face Recognition with Neural Tensor Fusion NetworkIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2017Spotlight
- IMVIPA Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-IdentificationIn Proceedings of the Irish Machine Vision and Image Processing Conference (IMVIP), 2017Oral
2015
- ICCVOnline Object Tracking with Proposal SelectionIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2015
- TPAMIContextualizing Object Detection and ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
2014
- ECCVOcclusion and Motion Reasoning for Long-term TrackingIn Proceedings of the European Conference on Computer Vision (ECCV), 2014
2013
- TMMVideoPuzzle: Descriptive One-shot Video CompositionIEEE Transactions on Multimedia, 2013
2012
- CVPRHierarchical Matching with Side Information for Image ClassificationIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2012
2011
- CVPRContextualizing Object Detection and ClassificationIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2011
2008
- ICIAAnalysis of the Packet Transferring in L2CAP Layer of Bluetooth v2.x+EDRIn Proceedings of the IEEE International Conference on Information and Automation (ICIA), 2008