侯赛辉
基本信息
职称:中级 (硕士生导师)
研究方向:计算机视觉、模式识别
电子邮箱:housaihui@bnu.edu.cn
个人简介
主要从事步态识别、增量学习等方面的研究。目前已在TPAMI、TIFS、TNNLS和CVPR、ICCV、ECCV等期刊和会议发表27篇论文,其中CCF-A类会议(含ECCV)和IEEE Trans期刊23篇,第一作者和通讯作者16篇,Google引用次数超过1900次(截至2023年10月31日)。申明专利20余项,主持国家自然科学基金青年基金1项和中央高校基本科研业务费专项资助项目1项,参与国家自然科学基金重点项目、面上项目以及多个企业横向合作项目。
教育背景
2014年—2019年 中国科学技术大学信息科学技术学院,控制科学与工程专业,博士
2017年—2018年 香港中文大学信息工程系,MMLab,Research Assistant
2010年—2014年 中国科学技术大学信息科学技术学院,自动化专业,学士
工作经历
2021年至今 365BET体育投注官网 讲师
2019年—2021年 中国科学院自动化研究所 博士后
主持和参加的科研项目
1. 国家自然科学基金委员会青年项目,基于自监督学习的步态识别泛化能力研究,2023-01-01 至 2025-12-31,主持。
2. 中央高校基本科研业务费专项资助项目,基于剪影集合的步态识别可解释性研究,2021-10-01 至 2023-9-30,主持。
3. 国家自然科学基金委员会面上项目,无人机视角步态识别研究,2023-01-01 至 2026-12-31,参与。
主要学术成果
代表性会议论文(截至2023年10月31日)
[1] Yang Fu, Shibei Meng, Saihui Hou#, Xuecai Hu, Yongzhen Huang# , GPGait: Generalized Pose-based Gait Recognition, in IEEE Conference on Computer Vision (ICCV), 2023. (CCF A类,计算机视觉顶级会议,共同通讯)
[2] Weijia Li*, Saihui Hou*, Chunjie Zhang, Chunshui Cao, Xu Liu, Yongzhen Huang, Yao Zhao, An In-depth Exploration of Person Re-identification And Gait Recognition in Cloth-Changing Conditions, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023. (CCF A类,计算机视觉顶级会议,共同一作)
[3] Chao Fan, Junhao Liang, Chuanfu Shen, Saihui Hou, Yongzhen Huang, Shiqi Yu, OpenGait: Revisiting Gait Recognition Toward Better Practicality, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023.(CCF A类,计算机视觉顶级会议,3 Strong Accept)
[4] Jilong Wang, Saihui Hou, Yan Huang, Chunshui Cao, Xu Liu, Yongzhen Huang, Liang Wang, Causal Intervention for Sparse-View Gait Recognition, ACM International Conference on Multimedia (ACM MM), 2023.(CCF A类,计算机视觉顶级会议)
[5] Zengbin Wang, Saihui Hou, Man Zhang, Xu Liu, Chunshui Cao, Yongzhen Huang, Shibiao Xu, LandmarkGait: Intrinsic Human Parsing for Gait Recognition, ACM International Conference on Multimedia (ACM MM), 2023.(CCF A类,计算机视觉顶级会议)
[6] Junhao Liang, Chao Fan, Saihui Hou, Chuanfu Shen, Yongzhen Huang, and Shiqi Yu. Gaitedge: Beyond plain end-to-end gait recognition for better practicality. In in European Conference on Computer Vision (ECCV) 2022. (CCF B类,计算机视觉顶级会议)
[7] Saihui Hou, Chunshui Cao, Xu Liu, and Yongzhen Huang, Gait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition, in European Conference on Computer Vision (ECCV) 2020. (CCF B类,计算机视觉顶级会议)
[8] Chao Fan, Yunjie Peng, Chunshui Cao, Xu Liu, Saihui Hou, Jiannan Chi, Yongzhen Huang, Qing Li, and Zhiqiang He, GaitPart: Temporal Part-Based Model for Gait Recognition, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020. (CCF A类,计算机视觉顶级会议)
[9] Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, and Dahua Lin, Learning a Unified Classifier Incrementally via Rebalancing, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019. (CCF A类,计算机视觉顶级会议)
[10] Saihui Hou, and Zilei Wang, Weighted Channel Dropout for Regularization of Deep Convolutional Neural Network, in AAAI Conference on Artificial Intelligence (AAAI) 2019. (CCF A类,人工智能顶级会议)
[11] Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, and Dahua Lin, Lifelong Learning via Progressive Distillation and Retrospection, in European Conference on Computer Vision (ECCV) 2018. (CCF B类,计算机视觉顶级会议)
[12] Jiafan Zhuang, Saihui Hou, Zilei Wang, and Zheng-Jun Zha, Towards Human-Level License Plate Recognition, in European Conference on Computer Vision (ECCV) 2018. (CCF B类,计算机视觉顶级会议)
[13] Saihui Hou, Xu Liu and Zilei Wang, DualNet: Learn Complementary Features for Image Recognition, in IEEE Conference on Computer Vision (ICCV), 2017. (CCF A类,计算机视觉顶级会议)
[14] Saihui Hou, Yushan Feng and Zilei Wang, VegFru: A Domain-Specific Dataset for Fine-grained Visual Categorization, in IEEE Conference on Computer Vision (ICCV), 2017. (CCF A类,计算机视觉顶级会议)
代表性期刊论文(截至2023年10月31日)
[1] Chao Fan, Saihui Hou, Jilong Wang, Yongzhen Huang, and Shiqi Yu, Learning Gait Representation from Massive Unlabelled Walking Videos: A Benchmark, in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023. (IEEE Trans系列,CCF A类,SCI一区)
[2] Yu Guo, Yu Zhao, Saihui Hou, Cong Wang, and Xiaohua Jia, Verifying in the Dark: Verifiable Machine Unlearning by Using Invisible Backdoor Triggers, in IEEE Transactions on Information Forensics and Security (TIFS), 2023. (IEEE Trans系列,CCF A类,SCI一区,通讯作者)
[3] Xu Song, Saihui Hou, Yan Huang, Chunshui Cao, Xu Liu, Yongzhen Huang, Caifeng Shan, Gait Attribute Recognition: A New Benchmark for Learning Richer Attributes from Human Gait Patterns, in IEEE Transactions on Information Forensics and Security (TIFS), 2023. (IEEE Trans系列,CCF A类,SCI一区)
[4] Aoqi Li, Saihui Hou#, Qingyuan Cai, Yang Fu, and Yongzhen Huang#, Gait Recognition with Drones: A Benchmark, in IEEE Transactions on Multimedia (TMM), 2023. (IEEE Trans系列,CCF B类,SCI一区,共同通讯)
[5] Zengbin Wang, Saihui Hou, Man Zhang , Xu Liu, Chunshui Cao, Yongzhen Huang,GaitParsing: Human Semantic Parsing for Gait Recognition, in IEEE Transactions on Multimedia (TMM), 2023. (IEEE Trans系列,CCF B类,SCI一区)
[6] Saihui Hou, Chao Fan, Chunshui Cao, Xu Liu, Yongzhen Huang, A Comprehensive Study on the Evaluation of Silhouette-based Gait Recognition, in IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM) 2022. (IEEE Trans系列,生物特征识别顶级期刊)
[7] Saihui Hou, Xu Liu, Chunshui Cao, and Yongzhen Huang, Gait Quality Aware Network: Towards the Interpretability of Silhouette-based Gait Recognition, in IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022.(IEEE Trans系列,CCF-B类,SCI一区,人工智能顶级期刊)
[8] Saihui Hou, Xu Liu, Chunshui Cao, and Yongzhen Huang, Set Residual Network for Silhouette-based Gait Recognition, in IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM) 2021.(IEEE Trans系列,生物特征识别顶级期刊)
[9] Zilei Wang, Dao Xiang, Saihui Hou, and Feng Wu, Background Driven Salient Object Detection, in IEEE Transactions on Multimedia (TMM), 2016. (IEEE Trans系列,CCF B类,SCI一区)
奖励与荣誉
1. 2022年,入选北京市科协青年人才托举工程
2. 2019年,获中国科学院院长奖优秀奖
3. 2019年,获中国科学技术大学优秀博士论文
4. 2016年,获研究生国家奖学金 (Top 5%)
5. 2014年,获中国科学技术大学优秀毕业生
6. 2013年,获本科生国家奖学金 (Top 5%)
学术与社会服务
1. 中国图象图形学学会机器视觉专委会委员
2. 为TPAMI、IJCV、TIP以及CVPR、ICCV、ECCV等多个顶级期刊和会议审稿
招生说明
每年招收1-2名硕士研究生,欢迎符合以下条件的同学报考。
a) 对计算机视觉感兴趣,有明确的目标和规划,对自己有清楚的认识。
b) 有好奇心和求知欲,富于探索精神,碰到挫折能够以正确的心态面对。
c) 有扎实的英语、数学和编程基础,至少熟练掌握一门编程语言。