081203-计算机应用技术

人工智能
视频大数据分析与理解

2000-09--2005-07   中国科学院研究生院   博士研究生
1997-09--2000-03   河北工业大学   硕士研究生
1993-09--1997-06   河北工业大学   学士

   

2023-01~现在, 鹏城实验室, 视觉智能研究所所长，研究员
2019-05~2023-01,鹏城实验室, 视觉智能研究所所长，副研究员
2019-02~2019-05,北京大学深圳研究生院, 特聘研究员
2014-08~2015-08,伦敦玛丽女王大学, 访问学者
2005-07~2019-02,北京理工大学, 讲师
2000-09~2005-07,中国科学院研究生院, 博士研究生
1997-09~2000-03,河北工业大学, 硕士研究生
1993-09~1997-06,河北工业大学, 学士

2021-12-01-今,IEEE Digital Retina Systems Working Group(3161 WG)工作组 Chair, 工作组组长
2021-06-01-今,中国计算机学会多媒体专委会执行委员, 执行委员
2020-10-19-今,中国图象图形学学会交通视频专委会委员, 交通视频委员
2019-06-01-今,新一代人工智能 产业技术创新战略联盟 AI 标准工作组“数字视网膜系统”专题组组长, 组长、联合组长

   

（1） 中国电子学会科技进步奖, 一等奖, 部委级, 2022
（2） 国家技术发明奖, 二等奖, 国家级, 2017
（3） 中国电子学会科学技术奖, 一等奖, 部委级, 2015

（ 1 ） 分布式训练方法、装置、智能终端及计算机可读存储介质, 2022, 第 1 作者, 专利号: CN114035938A

（ 2 ） 一种生成车道级仿真路网的方法、设备及存储介质, 2022, 第 4 作者, 专利号: CN113887321A

（ 3 ） 一种面向人眼观看和视觉分析联合优化的图像压缩方法, 2021, 第 3 作者, 专利号: CN113840145A

（ 4 ） 一种视频异常检测方法、装置、终端及存储介质, 2021, 第 3 作者, 专利号: CN113780128A

（ 5 ） 一种神经网络数据处理方法、装置、设备及存储介质, 2021, 第 3 作者, 专利号: CN113780539A

（ 6 ） 溢出感知的量化模型训练方法、装置、介质及终端设备, 2021, 第 4 作者, 专利号: CN113780549A

（ 7 ） 大规模多机多卡预训练方法、系统、设备及服务器集群, 2021, 第 3 作者, 专利号: CN113723552A

（ 8 ） 一种视觉大模型分布式训练方法及系统, 2021, 第 3 作者, 专利号: CN113723443A

（ 9 ） 局部特征耦合全局表征的图像分类方法, 2021, 第 3 作者, 专利号: CN113239981A

（ 10 ） 一种用于大规模视觉计算系统的节点协同选择方法, 2021, 第 1 作者, 专利号: CN112954269A

（ 11 ） 目标检测方法、装置、智能终端及计算机可读存储介质, 2021, 第 3 作者, 专利号: CN112926599A

（ 12 ） 一种基于数字视网膜系统的通信方法, 2021, 第 2 作者, 专利号: CN112929351A

（ 13 ） 一种基于多摄像机的车辆追踪方法, 2021, 第 1 作者, 专利号: CN112884815A

（ 14 ） 一种大规模视觉计算系统中有效节点动态遴选方法, 2021, 第 1 作者, 专利号: CN112822450A

（ 15 ） 一种用于感知系统构建的前端节点优化选择方法, 2021, 第 1 作者, 专利号: CN112822451A

（ 16 ） 一种可伸缩视觉计算系统, 2021, 第 2 作者, 专利号: CN112804188A

（ 17 ） 一种交通预测方法、智能终端及计算机可读存储介质, 2021, 第 1 作者, 专利号: CN112766551A

（ 18 ） 一种行人多目标跟踪方法、装置、智能终端及存储介质, 2021, 第 2 作者, 专利号: CN112750147A

（ 19 ） 一种获取车流信息的方法、终端及存储介质, 2021, 第 2 作者, 专利号: CN112562315A

（ 20 ） 一种自标定式多车道级交通流量检测方法及电子设备, 2021, 第 2 作者, 专利号: CN112530159A

（ 21 ） 一种交通事故检测方法、存储介质及设备, 2021, 第 3 作者, 专利号: CN112487961A

（ 22 ） 一种基于规则与学习的交通场景异常目标检测方法, 2021, 第 3 作者, 专利号: CN112464749A

（ 23 ） 一种车辆跟踪方法、装置、智能终端及存储介质, 2021, 第 5 作者, 专利号: CN112435276A

（ 24 ） 一种基于视频的车牌数据脱敏方法、存储介质及服务器, 2021, 第 5 作者, 专利号: CN112347853A

（ 25 ） 一种车牌脱敏方法、终端及存储介质, 2021, 第 5 作者, 专利号: CN112215063A

（ 26 ） 一种基于视觉的车辆碰撞检测方法、智能终端及存储介质, 2021, 第 4 作者, 专利号: CN112200131A

（ 27 ） 一种基于自动搜索与知识蒸馏的神经网络剪枝的压缩算法, 2019, 第 4 作者, 专利号: CN110175628A

（ 28 ） 基于深度学习的车牌检测与识别方法和装置, 2018, 第 1 作者, 专利号: CN108830213A

（ 29 ） 基于卷积神经网络的车辆属性识别方法与装置, 2017, 第 1 作者, 专利号: CN106778583A

（ 30 ） 背景帧的码率控制方法和装置, 2017, 第 1 作者, 专利号: CN106658027A

（ 31 ） 一种基于RGB对比图像与目标形状的烟雾检测方法, 2013, 第 1 作者, 专利号: CN103020628A

（ 32 ） 基于非均衡时序的监控视频异常事件检测方法, 2013, 第 1 作者, 专利号: CN102938078A

   

（1） Self-Supervised Tracking via Target-Aware Data Synthesis, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 通讯作者
（2） PolarPose: Single-Stage Multi-Person Pose Estimation in Polar Coordinates, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 第 2 作者
（3） TransWeaver: Weave Image Pairs for Class Agnostic Common Object Detection, IEEE Transactions on Image Processing, 2023, 
（4） Towards Bridged Vision and Language: Learning Cross-modal Knowledge Representation for Relation Extraction, IEEE Transactions on Circuits and Systems for Video Technology, 2023, 
（5） MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023, 第 4 作者
（6） Recovering Generalization via Pre-training-like Knowledge Distillation for Out-of-Distribution Visual Question Answering, IEEE Transactions on Multimedia, 2023, 
（7） Generative Data Free Model Quantization with Knowledge Matching for Classification, IEEE Transactions on Circuits and Systems for Video Technology, 2023, 
（8） Robust and Hierarchical Spatial Relation Analysis for Traffic Forecasting, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 第 5 作者
（9） KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, 
（10） AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, 
（11） Isolation and impartial aggregation: A paradigm of incremental learning without interference, Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 第 4 作者
（12） DCR-ReID: Deep Component Reconstruction for Cloth-Changing Person Re-Identification, IEEE Transactions on Circuits and Systems for Video Technology, 2023, 第 1 作者
（13） Dilateformer: Multi-scale dilated transformer for visual recognition, IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 
（14） Spatial-Temporal Graph Network for Video Crowd Counting, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 通讯作者
（15） Conformer: Local features coupling global representations for recognition and detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 第 1 作者
（16） Unlearnable clusters: Towards label-agnostic unlearnable examples, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, 
（17） WDMNet: Modeling diverse variations of regional wind speed for multi-step predictions, NEURAL NETWORKS, 2023, 第 8 作者
（18） Egocentric Early Action Prediction via Multimodal Transformer-based Dual Action Prediction, IEEE Transactions on Circuits and Systems for Video Technology, 2023, 
（19） Digging out Discrimination Information from Generated Samples for Robust Visual Question Answering, Findings of the Association for Computational Linguistics: ACL 2023, 2023, 第 2 作者
（20） CIGAR: Cross-Modality Graph Reasoning for Domain Adaptive Object Detection, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, 第 1 作者
（21） Recurrent Fine-Grained Self-Attention Network for Video Crowd Counting, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, 
（22） 基于数据生成的类别均衡联邦学习, Class-Balanced Federated Learning Based on Data Generation, 计算机学报, 2023, 第 4 作者
（23） Large-scale multi-modal pre-trained models: A comprehensive survey, Machine Intelligence Research, 2023, 
（24） Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 第 5 作者
（25） Integrally Pre-Trained Transformer Pyramid Networks, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, 
（26） Classification of single-view object point clouds, PATTERN RECOGNITION, 2023, 第 5 作者
（27） Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain, Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 第 5 作者
（28） Weakly Supervised Video Anomaly Detection via Self-Guided Temporal Discriminative Transformer, IEEE TRANSACTIONS ON CYBERNETICS, 2022, 第 7 作者
（29） Unsupervised domain adaptation via distilled discriminative clustering, PATTERN RECOGNITION, 2022, 第 2 作者
（30） Hierarchical graph embedded pose regularity learning via spatio-temporal transformer for abnormal behavior detection, Proceedings of the 30th ACM International Conference on Multimedia, 2022, 
（31） Self-Supervised Attentive Generative Adversarial Networks for Video Anomaly Detection, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 第 6 作者
（32） Span-based Audio-Visual Localization, ACM International Conference on Multimedia, 2022, 第 3 作者
（33） Semi-supervised Crowd Counting via Density Agency, 2022, 第 4 作者
（34） Optimized separable convolution: Yet another efficient convolution operator, AI OPEN, 2022, 第 3 作者
（35） Multi-attribute object detection benchmark for smart city, MULTIMEDIA SYSTEMS, 2022, 第 1 作者
（36） Abnormal Event Detection Using Deep Contrastive Learning for Intelligent Video Surveillance System, IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 第 6 作者
（37） Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance, European Conference on Computer VisionEuropean Conference on Computer Vision, 2022, 第 5 作者
（38） ECCNAS: Efficient Crowd Counting Neural Architecture Search, ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2022, 第 5 作者
（39） M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, 第 8 作者
（40） Mixed supervision for instance learning in object detection with few-shot annotation, Proceedings of the 30th ACM International Conference on Multimedia, 2022, 
（41） Fine-Grained Object Classification via Self-Supervised Pose Alignment, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, 通讯作者
（42） Intergranular Corrosion Resistance of Stainless Steel Coating with Ultralow Dilution Rates Manufactured by Tungsten Arc Welding Technology, JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE, 2022, 第 1 作者
（43） Identifying the kind behind SMILES-anatomical therapeutic chemical classification using structure-only representations, BRIEFINGS IN BIOINFORMATICS, 2022, 第 5 作者
（44） A survey of crowd counting and density estimation based on convolutional neural network, NEUROCOMPUTING, 2022, 第 6 作者
（45） PanGu-$\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation, ARXIV, 2021, 第 35 作者
（46） Diverse part attentive network for video-based person re-identification, PATTERN RECOGNITION LETTERS, 2021, 第 7 作者
（47） Learning Scalable lY-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, 第 4 作者
（48） Learning to Share in Multi-Agent Reinforcement Learning, ICLR 2022 Workshop on Gamification and Multiagent Solutions, 2021, 第 3 作者
（49） Dynamic Attention Guided Multi-Trajectory Analysis for Single Object Tracking, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 第 5 作者
（50） Progressive Feature Enhancement for Person Re-Identification, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 第 2 作者
（51） Hierarchically and cooperatively learning traffic signal control, Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 第 2 作者
（52） Reducing Image Compression Artifacts for Deep Neural Networks, 2021 Data Compression Conference (DCC), 2021, 第 4 作者
（53） Tracking by Joint Local and Global Search: A Target-aware Attention based Approach, 2021, 第 4 作者
（54） Attribute-aware feature encoding for object recognition and segmentation, IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 第 2 作者
（55） Contrastive Neural Architecture Search with Neural Architecture Comparators, PROCEEDINGS OF THE IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, 2021, 第 6 作者
（56） Direct Measure Matching for Crowd Counting, ARXIV, 2021, 第 6 作者
（57） MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking, ARXIV, 2021, 第 5 作者
（58） Tracking by Joint Local and Global Search: A Target-Aware Attention-Based Approach, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 通讯作者
（59） VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows, ARXIV, 2021, 第 7 作者
（60） AAformer: Auto-Aligned Transformer for Person Re-Identification, 2021, 第 4 作者
（61） Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark, 文 PROCEEDINGS OF THE IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, 2021, 第 5 作者
（62） Conformer: Local Features Coupling Global Representations for Visual Recognition, PROCEEDINGS OF THE IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, 2021, 第 5 作者
（63） Abnormal Event Detection Using Deep Contrastive Learning for Intelligent Video Surveillance System, Ieee Transactions on Industrial Informatics, 2021, 第 6 作者
（64） Self-Supervision-Augmented Deep Autoencoder for Unsupervised Visual Anomaly Detection, IEEE Transactions on Cybernetics, 2021, 第 7 作者
（65） Towards End-to-End Image Compression and Analysis with Transformers, 2021, 第 5 作者
（66） Towards effective deep transfer via attentive feature alignment, NEURAL NETWORKS, 2021, 第 3 作者
（67） Adaptive Spatial Pyramid Constraint for Hyperspectral Image Classification With Limited Training Samples, Ieee Transactions on Geoscience and Remote Sensing, 2021, 通讯作者
（68） Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings, 2021 IEEE INTERNATIONAL CONFERENCE ON DATA MINING, 2021, 第 3 作者
（69） Digital Retina: A Way to Make the City Brain More Efficient by Visual Coding, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 第 6 作者
（70） Bidirectional Posture-Appearance Interaction Network for Driver Behavior Recognition, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 通讯作者
（71） Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection, ARXIV, 2021, 第 3 作者
（72） Learning Scalable $\ell_\infty$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression, 2021, 第 4 作者
（73） Learning Compact Networks via Similarity-aware Channel Pruning, THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020), 2020, 第 4 作者
（74） Large Batch Optimization for Object Detection: Training COCO in 12 Minutes, ECCV, 2020, 
（75） Prune it Yourself: Automated Pruning by Multiple Level Sensitivity, THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020), 2020, 第 3 作者
（76） Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations, Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 第 2 作者
（77） P-ODN: Prototype-based Open Deep Network for Open Set Recognition, SCIENTIFIC REPORTS, 2020, 第 3 作者
（78） An Asymmetric Modeling for Action Assessment, ECCV2020, 2020, 第 2 作者
（79） Adaptation-Oriented Feature Projection for One-Shot Action Recognition, IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 第 4 作者
（80） Large Batch Optimization for Object Detection: Training COCO in 13 Minutes, ECCV2020, 2020, 第 2 作者
（81） 基于视觉的车辆异常行为检测综述, Vision-Based Abnormal Vehicle Behavior Detection:A Survey, 模式识别与人工智能, 2020, 第 4 作者
（82） Compositional Few-Shot Recognition with Primitive Discovery and Enhancing, 2020, 第 5 作者
（83） Modular Graph Attention Network for Complex Visual Relational Reasoning, 15th Asian Conference on Computer Vision, 2020, 通讯作者
（84） Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos, 2020, 第 6 作者
（85） Anonymous Model Pruning for Compressing Deep Neural Networks, THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020), 2020, 第 6 作者
（86） R-SiamNet: ROI-Align Pooling Baesd Siamese Network for Object Tracking, THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020), 2020, 第 2 作者
（87） End-Edge-Cloud Collaborative System: A Video Big Data Processing and Analysis Architecture, THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020), 2020, 第 2 作者
（88） Can Categories and Attributes Be Learned in a Multi-Task Way?, IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 通讯作者
（89） Efficient and Fast Coefficient Sign Inference for Video Coding, 2019 DATA COMPRESSION CONFERENCE (DCC), 2019, 第 3 作者
（90） Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning, 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, 第 4 作者
（91） Bi-directional Re-ranking for Person Re-identification, 2019 2ND IEEE CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2019), 2019, 第 3 作者
（92） Deep Transfer Learning for Person Re-identification, 2018 IEEE FOURTH INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM), 2018, 通讯作者
（93） Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 第 4 作者
（94） Cross-Domain Adversarial Feature Learning for Sketch Re-identification, PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, 通讯作者
（95） SFCM: LEARN A POOLING KERNEL FOR WEAKLY SUPERVISED OBJECT LOCALIZATION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018, 通讯作者
（96） Fast Compressed Domain Copy Detection with Motion Vector Imaging, IEEE 1ST CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2018), 2018, 第 5 作者
（97） ODN: OPENING THE DEEP NETWORK FOR OPEN-SET ACTION RECOGNITION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018, 通讯作者
（98） TEMPORAL ATTENTIVE NETWORK FOR ACTION RECOGNITION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018, 通讯作者
（99） Multi-Pose Learning based Head-Shoulder Re-identification, IEEE 1ST CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2018), 2018, 通讯作者
（100） ATTRIBUTE DRIVEN ZERO-SHOT CLASSIFICATION AND SEGMENTATION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018), 2018, 通讯作者
（101） HIERARCHICAL TEMPORAL MEMORY ENHANCED ONE-SHOT DISTANCE LEARNING FOR ACTION RECOGNITION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018, 通讯作者
（102） DEEP HASHING WITH MIXED SUPERVISED LOSSES FOR IMAGE SEARCH, 2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2017, 第 4 作者
（103） Sequential Deep Trajectory Descriptor for Action Recognition With Three-Stream CNN, IEEE TRANSACTIONS ON MULTIMEDIA, 2017, 第 3 作者
（104） Rate-Performance-Loss Optimization for Inter-Frame Deep Feature Coding From Videos, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 第 4 作者
（105） Exploiting Multi-Grain Ranking Constraints for Precisely Searching Visually-similar Vehicles, 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, 第 3 作者
（106） Learning long-term dependencies for action recognition with a biologically-inspired deep network, 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, 第 3 作者
（107） DEEP HASHING WITH MULTI-TASK LEARNING FOR LARGE-SCALE INSTANCE-LEVEL VEHICLE SEARCH, 2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2017, 第 3 作者
（108） A FAST SKIP AND DIRECTION ADAPTIVE SEARCH ALGORITHM FOR SUB-PIXEL MOTION ESTIMATION ON HEVC, 2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2017, 第 3 作者
（109） Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles, 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, 通讯作者
（110） Unsupervised Cross-Dataset Transfer Learning for Person Re-identification, 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, 通讯作者
（111） Fixed-point Gaussian Mixture Model for analysis-friendly surveillance video coding, COMPUTER VISION AND IMAGE UNDERSTANDING, 2016, 第 3 作者
（112） CNN vs. SIFT for Image Retrieval: Alternative or Complementary?, MM'16: PROCEEDINGS OF THE 2016 ACM MULTIMEDIA CONFERENCE, 2016, 通讯作者
（113） Joint Learning of Semantic and Latent Attributes, COMPUTER VISION - ECCV 2016, PT IV, 2016, 通讯作者
（114） Unsupervised Cross-Dataset Transfer Learning for Person Re-identification, 2016, 第 5 作者
（115） CNUSVM: Hybrid CNN-Uneven SVM Model for Imbalanced Visual Learning, 2016 IEEE SECOND INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM), 2016, 第 2 作者
（116） LEARNING DEEP TRAJECTORY DESCRIPTOR FOR ACTION RECOGNITION IN VIDEOS USING DEEP NEURAL NETWORKS, 2015 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO (ICME), 2015, 通讯作者
（117） Swiss-System Based Cascade Ranking for Gait-Based Person Re-identification, PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2015, 第 3 作者
（118） Robust multiple cameras pedestrian detection with multi-view Bayesian network, PATTERN RECOGNITION, 2015, 第 3 作者
（119） Detecting Rare Actions and Events from Surveillance Big Data with Bag of Dynamic Trajectories, 2015 1ST IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM), 2015, 通讯作者
（120） A Refined Object Detection Method Based on HTM, 2014 IEEE VISUAL COMMUNICATIONS AND IMAGE PROCESSING CONFERENCE, 2014, 第 3 作者
（121） WAVELET BASED SMOKE DETECTION METHOD WITH RGB CONTRAST-IMAGE AND SHAPE CONSTRAIN, 2013 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP 2013), 2013, 通讯作者
（122） PAIR-WISE EVENT DETECTION USING CUBIC FEATURES AND SEQUENCE DISCRIMINANT LEARNING, 2013 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME 2013), 2013, 第 3 作者
（123） A CODING UNIT CLASSIFICATION BASED AVC-TO-HEVC TRANSCODING WITH BACKGROUND MODELING FOR SURVEILLANCE VIDEOS, 2013IEEEINTERNATIONALCONFERENCEONVISUALCOMMUNICATIONSANDIMAGEPROCESSINGIEEEVCIP2013, 2013, 第 4 作者
（124） A SYSTEM BASED ON SEQUENCE LEARNING FOR EVENT DETECTION IN SURVEILLANCE VIDEO, 2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013), 2013, 第 6 作者
（125） Selective Eigenbackground for Background Modeling and Subtraction in Crowded Scenes, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2013, 通讯作者
（126） Selective Eigenbackground for Background Modeling and Subtraction in Crowded Scenes, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2013, 通讯作者
（127） Single and Multiple View Detection, Tracking and Video Analysis in Crowded Environments, 2012, 第 5 作者
（128） Multi-camera Pedestrian Detection with Multi-view Bayesian Network Model, 2012, 第 2 作者
（129） SELECTIVE EIGENBACKGROUNDS METHOD FOR BACKGROUND SUBTRACTION IN CROWED SCENES, 2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011, 第 2 作者
（130） ESUR: A SYSTEM FOR EVENTS DETECTION IN SURVEILLANCE VIDEO, 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, 通讯作者
（131） KernelRank: Exploiting Semantic Linkage Kernels for Relevant Pages Finding, KernelRank: Exploiting Semantic Linkage Kernels for Relevant Pages Finding, 电子学报：英文版, 2009, 第 1 作者
（132） 纯音乐与语音-音乐混合片段的高准确识别方法, Recognition of Pure Music from Speech Sound-Music Mixed Part of Audio Signal, 北京理工大学学报, 2009, 第 4 作者
（133） KernelRank: Exploiting Semantic Linkage Kernels for Relevant Pages Finding, CHINESE JOURNAL OF ELECTRONICS, 2009, 通讯作者
（134） A new algorithm for remotely sensed image texture classification and segmentation, INTERNATIONAL JOURNAL OF REMOTE SENSING, 2004, 
（135） A region based image matching method with regularized SAR model, ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2004, PT 1, PROCEEDINGS, 2004, 
（136） A regularized simultaneous autoregressive model for texture classification, Proceedings of the 2003 IEEE International Symposium on Circuits and Systems, 2003, 第 1 作者
（137） A new method for classification and segmentation of the textured images, Picture Coding Symposium, 2003, 第 1 作者
（138） Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN, 第 3 作者
（139） Joint Network based Attention for Action Recognition, 第 3 作者
（140） Multi-Proxy Feature Learning for Robust Fine-Grained Visual Recognition, PATTERN RECOGNITION, 第 2 作者

   

（ 1 ） 面向社会公共安全的多维度跨平台视频智能关联与理解, 负责人, 国家任务, 2021-01--2024-12
（ 2 ） 可敏捷定制的智能视觉处理器及系统应用, 负责人, 地方任务, 2020-01--2023-01
（ 3 ） 全域多维度协同与持续进化的云网协同智能系统, 负责人, 其他, 2021-06--2023-06
（ 4 ） 全面支持国家AI标准体系的深度学习开源框架, 负责人, 国家任务, 2022-01--2024-12
（ 5 ） 面向规模视觉处理的开放计算框架研究及系统应用, 负责人, 地方任务, 2021-03--2023-03
（ 6 ） 脑眼融合的智能感知计算技术与平台, 负责人, 其他, 2023-07--2025-06