081104-模式识别与智能系统

模式识别、计算机视觉

2019-01--2019-12   美国加州大学洛杉矶分校   公派访问学者
2002-09--2009-03   中国科学院自动化研究所   硕博连读/工学博士
1998-09--2002-07   河北工业大学   工学学士

2009-03~2010-09,新加坡南洋理工大学, Research Fellow

视频处理与分析
视频分析与处理

   

[1] 王亮, 张彰, 李达. 基于增量学习的行人属性识别模型训练方法及装置. CN: CN114724174A, 2022-07-08.

[2] 黄凯奇, 张彰, 李俊, 李达, 余铠. 基于Spark的分布式海量视频解析系统. CN: CN108683877A, 2018-10-19.

[3] 冯柏岚, 姚春凤, 黄凯奇, 张彰, 周阳. 行人属性识别与定位方法以及卷积神经网络系统. CN: CN111052126A, 2020-04-21.

[4] 黄凯奇, 张彰, 单言虎. 一种基于隐结构推理的行为识别方法. CN: CN103136540A, 2013-06-05.

[5] 王亮, 张彰, 王开业. 基于慢特征分析的暴力视频检测方法. CN: CN102902981A, 2013-01-30.

[6] 谭铁牛, 黄凯奇, 张彰, 王亮生. 一种基于轨迹序列分析和规则归纳的视频行为识别方法. CN: CN101334845A, 2008-12-31.

[7] 王亮, 张彰, 董清辉. 驾驶行为预测模型构建方法、预测方法、装置、设备和介质. CN: CN118334631A, 2024-07-12.

[8] 王亮, 张彰, 杨溢. 越野环境自动驾驶感知模型的训练及自动驾驶感知方法. CN: CN117993469A, 2024-05-07.

[9] 冯柏岚, 姚春凤, 黄凯奇, 张彰, 周阳. 行人属性识别与定位方法以及卷积神经网络系统. CN: CN111052126B, 2024-06-04.

   

（1） CSFRNet: Integrating Clothing Status Awareness for Long-Term Person Re-identification, INTERNATIONAL JOURNAL OF COMPUTER VISION, 2025, 第 3 作者
（2） MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?, International Conference on Learning Representations (ICLR) 2025, 2025, 第 10 作者  通讯作者
（3） Mitigating Catastrophic Forgetting in Online Continual Learning with Dual-Margin Contrastive Replay, IEEE Transactions on Circuits and Systems for Video Technology, 2025, 
（4） Multi-View Knowledge Guided Semantic Prototype Learning for Generalized Zero-Shot Action Recognition, IEEE Transactions on Multimedia, 2025, 第 3 作者  通讯作者
（5） MM-RLHF: The Next Step Forward in Multimodal LLM Alignment, international conference on machine learning 2025, 2025, 第 15 作者  通讯作者
（6） AdaGPAR:Generalizable Pedestrian Attribute Recognition via Test-time Adaptation, AdaGPAR:Generalizable Pedestrian Attribute Recognition via Test-time Adaptation, MACHINE INTELLIGENCE RESEARCH, 2025, 第 2 作者  通讯作者
（7） Spectral Decomposition and Adaptation for Non-stationary Time Series Anomaly Detection, Neurocomputing, 2025, 第 4 作者
（8） DAA: Amplifying Unknown Discrepancy for Test-Time Discovery, NeurIPS, 2025, 第 4 作者
（9） TimeRAF: Retrieval-Augmented Foundation Model for Zero-Shot Time Series Forecasting, IEEE Transactions on Knowledge and Data Engineering, 2025, 第 4 作者
（10） Controllable continual test-time adaptation, ICME, 2025, 第 7 作者  通讯作者
（11） Debiasing Multimodal Large Language Models via Penalization of Language Priors, arxiv, 2025, 第 7 作者
（12） Human image generation: A comprehensive survey, ACM Computing Surveys, 2024, 第 2 作者  通讯作者
（13） Pedestrian attribute recognition via spatio-temporal relationship learning for visual surveillance, ACM Transactions on Multimedia Computing, Communications and Applications, 2024, 第 4 作者
（14） Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, 第 2 作者  通讯作者
（15） Dynamic V2X Perception From Road-to-Vehicle Vision, IEEE Transactions on Intelligent Vehicles, 2024, 第 7 作者
（16） Love in Action: Gamifying Public Video Cameras for Fostering Social Relationships in Real World, 13th EAI International Conference: ArtsIT, Interactivity & Game Creation, 2024, 第 1 作者  通讯作者
（17） Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models, arxiv, 2024, 第 5 作者
（18） Human Image Generation: A Comprehensive Survey, ACM COMPUTING SURVEYS, 2024, 第 2 作者  通讯作者
（19） LogoRA: Local-Global Representation Alignment for Robust Time Series Classification, IEEE Transactions on Knowledge and Data Engineering, 2024, 第 3 作者  通讯作者
（20） Class Hierarchy Guided Generalized Few-shot Ship Detection in Remote Sensing Images, IEEE Geoscience and Remote Sensing Letters, 2024, 第 2 作者
（21） Customized meta-dataset for automatic classifier accuracy evaluation, PATTERN RECOGNITION, 2024, 第 2 作者
（22） Meta clothing status calibration for long-term person re-identification, IEEE Transactions on Image Processing, 2024, 第 3 作者
（23） Class Hierarchy Guided Generalized Few-shot Ship Detection in Remote Sensing Images, IEEE Geoscience and Remote Sensing Letters, 2024, 第 2 作者
（24） Illumination Distillation Framework for Nighttime Person Re-Identification and a New Benchmark, IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 第 2 作者
（25） Pedestrian Attribute Recognition via Spatio-temporal Relationship Learning for Visual Surveillance, ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2024, 第 4 作者
（26） Class Hierarchy-Guided Generalized Few-Shot Ship Detection in Remote Sensing Images, IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 第 2 作者
（27） Free lunch for domain adversarial training: Environment label smoothing, The Eleventh International Conference on Learning Representations (ICLR 2023), 2023, 第 4 作者
（28） Adanpc: Exploring non-parametric classifier for test-time adaptation, International Conference on Machine Learning (ICML 2023), 2023, 第 5 作者
（29） Incremental Pedestrian Attribute Recognition via Dual Uncertainty-Aware Pseudo-Labeling, IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 第 2 作者  通讯作者
（30） Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023, 第 2 作者
（31） Domain-Specific Risk Minimization for Domain Generalization, Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), 2023, 第 4 作者
（32） Learning Domain Invariant Representations for Generalizable Person Re-Identification, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 第 2 作者  通讯作者
（33） Multi-semantic Fusion Model For Generalized Zero-Shot Skeleton-Based Action Recognition, International Conference on Image and Graphics (ICIG 2023), 2023, 第 3 作者
（34） Dual-focus transfer network for zero-shot learning, NEUROCOMPUTING, 2023, 第 2 作者  通讯作者
（35） Few-shot learning with unsupervised part discovery and part-aligned similarity, PATTERN RECOGNITION, 2023, 第 2 作者  通讯作者
（36） OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling, Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 2023, 第 6 作者
（37） OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling, Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), 2023, 第 6 作者
（38） Focal and efficient IOU loss for accurate bounding box regression, NEUROCOMPUTING, 2022, 第 3 作者  通讯作者
（39） Focal and efficient IOU loss for accurate bounding box regression, NEUROCOMPUTING, 2022, 第 3 作者  通讯作者
（40） Dual-branch self-attention network for pedestrian attribute recognition, PATTERN RECOGNITION LETTERS, 2022, 第 2 作者
（41） Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022, 第 2 作者
（42） Richly Activated Graph Convolutional Network for Robust Skeleton-Based Action Recognition, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 第 2 作者  通讯作者
（43） Meta-USR: A Unified Super-Resolution Network for Multiple Degradation Parameters, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 第 2 作者  通讯作者
（44） Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition, MM 20, 2020.10.12, 第 2 作者
（45） Deep Unbiased Embedding Transfer for Zero-Shot Learning, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 第 2 作者  通讯作者
（46） Deep Fusion Feature Representation Learning With Hard Mining Center-Triplet Loss for Person Re-Identification, IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 第 3 作者
（47） Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition, 2020, 第 2 作者
（48） Multi angle optimal pattern-based deep learning for automatic facial expression recognition, PATTERN RECOGNITION LETTERS, 2020, 第 2 作者
（49） Kinematic skeleton graph augmented network for human parsing, NEUROCOMPUTING, 2020, 第 2 作者  通讯作者
（50） A Comprehensive Study on Large-Scale Person Retrieval in Real Surveillance Scenarios, 2019 16TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), 2019, 第 2 作者
（51） Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-Identification, 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 第 3 作者
（52） ISEE: An Intelligent Scene Exploration and Evaluation Platform for Large-Scale Visual Surveillance, IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2019, 第 2 作者  通讯作者
（53） MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification, PATTERN RECOGNITION, 2019, 第 2 作者  通讯作者
（54） UNSUPERVISED CROSS-DOMAIN PERSON RE-IDENTIFICATION: A NEW FRAMEWORK, 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, 第 3 作者
（55） Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons, 26th IEEE International Conference on Image Processing (ICIP), 2019, 第 2 作者
（56） Corrigendum to "MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification" Pattern Recognition 90 (2019) 436-449, PATTERN RECOGNITION, 2019, 第 2 作者  通讯作者
（57） MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification (vol 90, pg 436, 2019), PATTERN RECOGNITION, 2019, 第 2 作者  通讯作者
（58） A richly annotated pedestrian dataset for person retrieval in real surveillance scenarios, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 第 2 作者
（59） Adversarially Occluded Samples for Person Re-identification, 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, 第 3 作者
（60） Random walk-based feature learning for micro-expression recognition, PATTERN RECOGNITION LETTERS, 2018, 第 2 作者
（61） POSE GUIDED DEEP MODEL FOR PEDESTRIAN ATTRIBUTE RECOGNITION IN SURVEILLANCE SCENARIOS, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018, 第 3 作者
（62） Gestalt laws based tracklets analysis for human crowd understanding, PATTERN RECOGNITION, 2018, 第 2 作者
（63） Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization, 2017, 第 1 作者
（64） Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification, 2017, 第 1 作者
（65） Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification, 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, 第 3 作者
（66） Large-Scale Slow Feature Analysis Using Spark for Visual Object Recognition, COMPUTER VISION, PT III, 2017, 第 2 作者  通讯作者
（67） Hybrid Patch Based Diagonal Pattern Geometric Appearance Model for Facial Expression Recognition, INTELLIGENT VISUAL SURVEILLANCE (IVS 2016), 2016, 第 2 作者
（68） Joint Crowd Detection and Semantic Scene Modeling Using a Gestalt Laws-based Similarity, PROCINTERNATIONALCONFERENCEONIMAGEPROCESSINGICIP2016, 2016, 第 2 作者
（69） Hybrid patch based diagonal pattern geometric appearance model for facial expression recognition, 4th Chinese Conference on Intelligent Visual Surveillance (IVS), 2016, 第 2 作者
（70） 人的视觉行为识别研究回顾、现状及展望, Visual Human Action Recognition: History, Status and Prospects, 计算机研究与发展, 2016, 第 1 作者
（71） Joint Crowd Ddtection and Semantic Scene Modeling Using a Gestalt Laws-based Similarity, 2016, 第 2 作者
（72） ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering, 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, 第 1 作者  通讯作者
（73） Adaptive Slice Representation for Human Action Classification, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2015, 第 2 作者
（74） Learning Skeleton Stream Patterns with Slow Feature Analysis for Action Recognition, PROC. EUROPE CONFERENCE ON COMPUTER VISION WORKSHOPS, 2014, 第 3 作者
（75） Violence detection in video by slow feature analysis, 2012, 第 3 作者
（76） Baseline results for violence detection in still images, PROC. IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL-BASED SURVEILLANCE, 2012, 第 2 作者
（77） Slow Feature Analysis for Human Action Recognition, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 第 1 作者  通讯作者
（78） CONTINUUM REGRESSION FOR CROSS-MODAL MULTIMEDIA RETRIEVAL, 2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012), 2012, 第 4 作者
（79） Violence Video Detection by Discriminative Slow Feature Analysis, PATTERN RECOGNITION, 2012, 第 2 作者
（80） Interest point selection with spatio-temporal context for realistic action recognition, PROC. INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL-BASED SURVEILLANCE (AVSS) 2012, 2012, 第 3 作者
（81） Segment-Based Features for Time Series Classification, COMPUTER JOURNAL, 2012, 第 1 作者
（82） An extended grammar system for learning and recognizing complex visual events., IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 第 1 作者  通讯作者
（83） An X-T slice based method for action recognition, the IEEE International Conference on Computer Vision, 2011, 第 2 作者
（84） Multi-Thread Parsing for Recognizing Complex Events in Videos, European Conference on Computer Vision, 2008, 第 1 作者
（85） Multi-thread Parsing for Recognizing Complex Events in Videos, COMPUTER VISION - ECCV 2008, PT III, PROCEEDINGS, 2008, 第 1 作者  通讯作者
（86） Trajectory Series Analysis based Event Rule Induction for Visual Surveillance, IEEE Conference on Computer Vision and Pattern Recognition, 2007, 第 1 作者
（87） Complex activity representation and recognition by extended stochastic grammar, COMPUTER VISION - ACCV 2006, PT I, 2006, 
（88） Comparison of similarity measures for trajectory clustering in outdoor surveillance scenes, 18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, PROCEEDINGS, 2006, 第 1 作者  通讯作者
（89） Comparison of Similarity Measures for Trajectory Clustering in Outdoor Surveillance Scene, International Conference on Pattern Recognition, 2006, 第 1 作者
（90） Comprehensive Relation Modelling for Image Paragraph Generation, MACHINE INTELLIGENCE RESEARCH, 
（91） Enhancing Person Re-Identification Performance Through In Vivo Learning, IEEE TRANSACTIONS ON IMAGE PROCESSING, 第 3 作者