王耀威-中国科学院大学-UCAS
[中文]
[English]
教育背景
工作经历
专利与奖励
出版信息
科研活动
基本信息
王耀威 男 博导 鹏城实验室电子邮件： wangyw@pcl.ac.cn通信地址： 广东省深圳市南山区兴科一街 2 号鹏城实验室邮政编码：
招生信息
招生专业
081203-计算机应用技术
招生方向
视频分析理解，视频大数据挖掘，机器学习，系统智能
教育背景
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
工作经历
工作简历
2019-05~现在, 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2009-01~现在, 北京大学数字媒体技术研究所, 客座副研究员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
社会兼职
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
专利与奖励
奖励信息
（1）&nbsp国家技术发明奖,&nbsp二等奖,&nbsp国家级,&nbsp2017（2）&nbsp中国电子学会科学技术奖,&nbsp一等奖,&nbsp部委级,&nbsp2015
专利成果
（ 1 ）&nbsp局部特征耦合全局表征的图像分类方法,&nbsp2021,&nbsp第 3 作者,&nbsp专利号: CN113239981A（ 2 ）&nbsp一种基于多摄像机的车辆追踪方法,&nbsp2021,&nbsp第 1 作者,&nbsp专利号: CN112884815A（ 3 ）&nbsp一种获取车流信息的方法、终端及存储介质,&nbsp2021,&nbsp第 2 作者,&nbsp专利号: CN112562315A（ 4 ）&nbsp一种自标定式多车道级交通流量检测方法及电子设备,&nbsp2021,&nbsp第 2 作者,&nbsp专利号: CN112530159A（ 5 ）&nbsp一种交通事故检测方法、存储介质及设备,&nbsp2021,&nbsp第 3 作者,&nbsp专利号: CN112487961A（ 6 ）&nbsp一种基于规则与学习的交通场景异常目标检测方法,&nbsp2021,&nbsp第 3 作者,&nbsp专利号: CN112464749A（ 7 ）&nbsp一种车辆跟踪方法、装置、智能终端及存储介质,&nbsp2021,&nbsp第 5 作者,&nbsp专利号: CN112435276A（ 8 ）&nbsp一种车牌脱敏方法、终端及存储介质,&nbsp2021,&nbsp第 5 作者,&nbsp专利号: CN112215063A（ 9 ）&nbsp一种基于视觉的车辆碰撞检测方法、智能终端及存储介质,&nbsp2021,&nbsp第 4 作者,&nbsp专利号: CN112200131A（ 10 ）&nbsp基于卷积神经网络的车辆属性识别方法与装置,&nbsp2019,&nbsp第 1 作者,&nbsp专利号: CN106778583B（ 11 ）&nbsp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,&nbsp2019,&nbsp第 4 作者,&nbsp专利号: CN110175628A（ 12 ）&nbsp背景帧的码率控制方法和装置,&nbsp2019,&nbsp第 1 作者,&nbsp专利号: CN106658027B（ 13 ）&nbsp一种基于RGB对比图像与目标形状的烟雾检测方法,&nbsp2013,&nbsp第 1 作者,&nbsp专利号: CN103020628A（ 14 ）&nbsp基于非均衡时序的监控视频异常事件检测方法,&nbsp2013,&nbsp第 1 作者,&nbsp专利号: CN102938078A
出版信息
发表论文
（1） ECCNAS: Efficient Crowd Counting Neural Architecture Search, ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2022, 第 5 作者（2） Fine-Grained Object Classification via Self-Supervised Pose Alignment, 2022, 通讯作者（3） A survey of crowd counting and density estimation based on convolutional neural network, NEUROCOMPUTING, 2022, 第 6 作者（4） Self-Supervision-Augmented Deep Autoencoder for Unsupervised Visual Anomaly Detection, IEEE Transactions on Cybernetics, 2021, 第 7 作者（5） Towards End-to-End Image Compression and Analysis with Transformers, 2021, 第 5 作者（6） Towards effective deep transfer via attentive feature alignment, NEURAL NETWORKS, 2021, 第 3 作者（7） Adaptive Spatial Pyramid Constraint for Hyperspectral Image Classification With Limited Training Samples, Ieee Transactions on Geoscience and Remote Sensing, 2021, 通讯作者（8） Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings, 2021 IEEE International Conference on Data Mining, 2021, 第 3 作者（9） 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（10） Bidirectional Posture-Appearance Interaction Network for Driver Behavior Recognition, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 通讯作者（11） Learning Scalable $\ell_\infty$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression, 2021, 第 4 作者（12） 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（13） Diverse part attentive network for video-based person re-identification, PATTERN RECOGNITION LETTERS, 2021, 第 7 作者（14） Dynamic Attention Guided Multi-Trajectory Analysis for Single Object Tracking, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 第 5 作者（15） Progressive Feature Enhancement for Person Re-Identification, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 第 2 作者（16） Hierarchically and cooperatively learning traffic signal control, Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 第 2 作者（17） Tracking by Joint Local and Global Search: A Target-aware Attention based Approach, 2021, 第 4 作者（18） Reducing Image Compression Artifacts for Deep Neural Networks, 2021 Data Compression Conference (DCC), 2021, 第 4 作者（19） Attribute-aware feature encoding for object recognition and segmentation, IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 第 2 作者（20） 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（21） 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（22） AAformer: Auto-Aligned Transformer for Person Re-Identification, 2021, 第 4 作者（23） Abnormal Event Detection Using Deep Contrastive Learning for Intelligent Video Surveillance System, Ieee Transactions on Industrial Informatics, 2021, 第 6 作者（24） 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（25） Conformer: Local Features Coupling Global Representations for Visual Recognition, Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, 第 5 作者（26） Learning Compact Networks via Similarity-aware Channel Pruning, THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020), 2020, 第 4 作者（27） Large Batch Optimization for Object Detection: Training COCO in 12 Minutes, ECCV, 2020, （28） 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（29） Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations, Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 第 2 作者（30） P-ODN: Prototype-based Open Deep Network for Open Set Recognition, SCIENTIFIC REPORTS, 2020, 第 3 作者（31） Adaptation-Oriented Feature Projection for One-Shot Action Recognition, IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 第 4 作者（32） An Asymmetric Modeling for Action Assessment, ECCV2020, 2020, 第 2 作者（33） Large Batch Optimization for Object Detection: Training COCO in 13 Minutes, ECCV2020, 2020, 第 2 作者（34） 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（35） Compositional Few-Shot Recognition with Primitive Discovery and Enhancing, 2020, 第 5 作者（36） Modular Graph Attention Network for Complex Visual Relational Reasoning, 15th Asian Conference on Computer Vision, 2020, 通讯作者（37） Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos, 2020, 第 6 作者（38） 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（39） Anonymous Model Pruning for Compressing Deep Neural Networks, THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020), 2020, 第 6 作者（40） 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（41） Can Categories and Attributes Be Learned in a Multi-Task Way?, IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 通讯作者（42） Efficient and Fast Coefficient Sign Inference for Video Coding, 2019 DATA COMPRESSION CONFERENCE (DCC), 2019, 第 3 作者（43） Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning, 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, 第 4 作者（44） 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（45） 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（46） Deep Transfer Learning for Person Re-identification, 2018 IEEE FOURTH INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM), 2018, 通讯作者（47） Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 第 4 作者（48） Cross-Domain Adversarial Feature Learning for Sketch Re-identification, PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, 通讯作者（49） SFCM: LEARN A POOLING KERNEL FOR WEAKLY SUPERVISED OBJECT LOCALIZATION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018, 通讯作者（50） 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（51） ODN: OPENING THE DEEP NETWORK FOR OPEN-SET ACTION RECOGNITION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018, 通讯作者（52） TEMPORAL ATTENTIVE NETWORK FOR ACTION RECOGNITION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018, 通讯作者（53） Multi-Pose Learning based Head-Shoulder Re-identification, IEEE 1ST CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2018), 2018, 通讯作者（54） ATTRIBUTE DRIVEN ZERO-SHOT CLASSIFICATION AND SEGMENTATION, 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018), 2018, 通讯作者（55） Sequential Deep Trajectory Descriptor for Action Recognition With Three-Stream CNN, IEEE TRANSACTIONS ON MULTIMEDIA, 2017, 第 3 作者（56） DEEP HASHING WITH MIXED SUPERVISED LOSSES FOR IMAGE SEARCH, 2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2017, 第 4 作者（57） Rate-Performance-Loss Optimization for Inter-Frame Deep Feature Coding From Videos, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 第 4 作者（58） Exploiting Multi-Grain Ranking Constraints for Precisely Searching Visually-similar Vehicles, 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, 第 3 作者（59） 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（60） 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（61） 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（62） 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（63） Unsupervised Cross-Dataset Transfer Learning for Person Re-identification, 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, 通讯作者（64） Fixed-point Gaussian Mixture Model for analysis-friendly surveillance video coding, COMPUTER VISION AND IMAGE UNDERSTANDING, 2016, 第 3 作者（65） CNN vs. SIFT for Image Retrieval: Alternative or Complementary?, MM'16: PROCEEDINGS OF THE 2016 ACM MULTIMEDIA CONFERENCE, 2016, 通讯作者（66） Joint Learning of Semantic and Latent Attributes, COMPUTER VISION - ECCV 2016, PT IV, 2016, 通讯作者（67） Unsupervised Cross-Dataset Transfer Learning for Person Re-identification, 2016, 第 5 作者（68） 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（69） 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（70） 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（71） Robust multiple cameras pedestrian detection with multi-view Bayesian network, PATTERN RECOGNITION, 2015, 第 3 作者（72） 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（73） A Refined Object Detection Method Based on HTM, 2014 IEEE VISUAL COMMUNICATIONS AND IMAGE PROCESSING CONFERENCE, 2014, 第 3 作者（74） 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（75） 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（76） A CODING UNIT CLASSIFICATION BASED AVC-TO-HEVC TRANSCODING WITH BACKGROUND MODELING FOR SURVEILLANCE VIDEOS, 2013 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP 2013), 2013, 第 4 作者（77） 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（78） Selective Eigenbackground for Background Modeling and Subtraction in Crowded Scenes, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2013, 通讯作者（79） Selective Eigenbackground for Background Modeling and Subtraction in Crowded Scenes, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2013, 通讯作者（80） Single and Multiple View Detection, Tracking and Video Analysis in Crowded Environments, 2012, 第 5 作者（81） Multi-camera Pedestrian Detection with Multi-view Bayesian Network Model, 2012, 第 2 作者（82） SELECTIVE EIGENBACKGROUNDS METHOD FOR BACKGROUND SUBTRACTION IN CROWED SCENES, 2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011, 第 2 作者（83） ESUR: A SYSTEM FOR EVENTS DETECTION IN SURVEILLANCE VIDEO, 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, 通讯作者（84） 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（85） 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（86） KernelRank: Exploiting Semantic Linkage Kernels for Relevant Pages Finding, CHINESE JOURNAL OF ELECTRONICS, 2009, 通讯作者（87） A new algorithm for remotely sensed image texture classification and segmentation, INTERNATIONAL JOURNAL OF REMOTE SENSING, 2004, （88） A region based image matching method with regularized SAR model, ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2004, PT 1, PROCEEDINGS, 2004, （89） A regularized simultaneous autoregressive model for texture classification, Proceedings of the 2003 IEEE International Symposium on Circuits and Systems, 2003, 第 1 作者（90） A new method for classification and segmentation of the textured images, Picture Coding Symposium, 2003, 第 1 作者（91） Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN, 第 3 作者（92） Joint Network based Attention for Action Recognition, 第 3 作者
科研活动
科研项目
（ 1 ）&nbsp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 ）&nbsp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 ）&nbsp全域多维度协同与持续进化的云网协同智能系统, 负责人, 其他任务, 2021-06--2023-06（ 4 ）&nbsp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
2013 中国科学院大学，网络信息中心.