基本信息

• 职称：副教授 (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

主要从事以人为中心的计算机视觉和多模态大模型等相关研究。目前在TPAMI、IJCV、TIFS和CVPR、ICCV、ECCV等期刊和会议发表50余篇论文，其中CCF-A/ECCV/IEEE Transactions论文47篇，第一作者和通讯作者32篇，Google引用次数4000余次。申明专利20余项，主持国家自然科学基金青年基金和中央高校基本科研业务费专项资助项目，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。获中国科学技术大学优秀博士论文和中国科学院院长奖优秀奖，入选2023-2025北京市科协青年人才托举工程。

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

• 2024年至今     北京师范大学人工智能学院，副教授

• 2021年—2024年   北京师范大学人工智能学院，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

• 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。

• 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。

• 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

代表性期刊论文（最新成果参见个人主页https://housaihui.cn/）

[1] Shibei Meng, Yang Fu, Saihui Hou, Xuecai Hu, Chunshui Cao, Xu Liu, Yongzhen Huang, From FastPoseGait to GPGait++: Bridging the Past and Future for Pose-based Gait Recognition, in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, CCF-A), 2025.

[2] Chao Fan, Saihui Hou, Junhao Liang, Chuanfu Shen, Jingzhe Ma, Dongyang Jin, Yongzhen Huang, Shiqi Yu, OpenGait: A Comprehensive Benchmark Study for Gait Recognition Towards Better Practicality, in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, CCF-A), 2025.

[3] Jilong Wang, Saihui Hou, Xianda Guo, Yan Huang, Yongzhen Huang, Tianzhu Zhang, Liang Wang, GaitC3I: Robust Cross-Covariate Gait Recognition via Causal Intervention, in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.

[4] Xuqian Ren, Shaopeng Yang, Saihui Hou, Chunshui Cao, Xu Liu, Yongzhen Huang, Unsupervised Gait Recognition with Selective Fusion, in IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM), 2025.

[5] Saihui Hou, Zengbin Wang, Man Zhang, Chunshui Cao, Xu Liu, Yongzhen Huang, Edge-Oriented Adversarial Attack for Deep Gait Recognition, in International Journal of Computer Vision (IJCV, CCF-A), 2024.

[6] Saihui Hou, Xuecai Hu, Chunshui Cao, Xu Liu, Yongzhen Huang, Adaptive Knowledge Transfer for Weak-Shot Gait Recognition, in IEEE Transactions on Information Forensics and Security (TIFS, CCF-A), 2024.

[7] Panjian Huang, Saihui Hou, Chunshui Cao, Xu Liu, Xuecai Hu, and Yongzhen Huang, Integral Pose Learning via Appearance Transfer for Gait Recognition, in IEEE Transactions on Information Forensics and Security (TIFS, CCF-A), 2024.

[8] Saihui Hou, Panjian Huang, Xu Liu, Chunshui Cao, Yongzhen Huang, Cloth-Imbalanced Gait Recognition via Hallucination, in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.

[9] Yu Guo, Yu Zhao, Saihui Hou, Cong Wang, Xiaohua Jia, Verifying in the Dark: Verifiable Machine Unlearning by Using Invisible Backdoor Triggers, in IEEE Transactions on Information Forensics and Security (TIFS, CCF-A), 2023.

[10] 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.

[11] 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, CCF-A), 2023.

[12] Chao Fan, Saihui Hou, Jilong Wang, Yongzhen Huang, Shiqi Yu, Learning Gait Representation from Massive Unlabelled Walking Videos: A Benchmark, in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, CCF-A), 2023.

[13] Aoqi Li, Saihui Hou, Qingyuan Cai, Yang Fu, Yongzhen Huang, Gait Recognition with Drones: A Benchmark, in IEEE Transactions on Multimedia (TMM), 2023.

[14] 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.

[15] Saihui Hou, Xu Liu, Chunshui Cao, 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.

[16] Saihui Hou, Xu Liu, Chunshui Cao, Yongzhen Huang, Set Residual Network for Silhouette-based Gait Recognition, in IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM), 2021.

[17] Zilei Wang, Dao Xiang, Saihui Hou, Feng Wu, Background Driven Salient Object Detection, in IEEE Transactions on Multimedia (TMM), 2016.

代表性会议论文

[1] Wenpeng Lang, Saihui Hou, Yongzhen Huang, Beyond Sparse Keypoints: Dense Pose Modeling for Robust Gait Recognition, in ACM International Conference on Multimedia (ACM MM, CCF-A), 2025.

[2] Shibei Meng, Saihui Hou, Yang Fu, Xuecai Hu, Junzhou Huang, Yongzhen Huang, Seeing from Magic Mirror: Contrastive Learning from Reconstruction for Pose-based Gait Recognition, in ACM International Conference on Multimedia (ACM MM, CCF-A), 2025.

[3] Yuan Liu, Saihui Hou, Saijie Hou, Jiabao Du, Shibei Meng, Yongzhen Huang, OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning, in IEEE/CVF Conference on Computer Vision (ICCV, CCF-A), 2025.

[4] Saihui Hou, Panjian Huang, Zengbin Wang, Yuan Liu, Zeyu Li, Man Zhang, Yongzhen Huang, OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization, in IEEE/CVF Conference on Computer Vision (ICCV, CCF-A), 2025.

[5] Panjian Huang, Saihui Hou, Junzhou Huang, Yongzhen Huang, Learning A Unified Template for Gait Recognition, in IEEE/CVF Conference on Computer Vision (ICCV, CCF-A), 2025.

[6] Zengbin Wang, Saihui Hou, Junjie Li, Xu Liu, Chunshui Cao, Yongzhen Huang, Siye Wang, Man Zhang, Gait-X: Exploring X modality for Generalized Gait Recognition, in IEEE/CVF Conference on Computer Vision (ICCV, CCF-A), 2025.

[7] Shaopeng Yang, Jilong Wang, Saihui Hou, Xu Liu, Chunshui Cao, Liang Wang, Yongzhen Huang, Bridging Gait Recognition and Large Language Models Sequence Modeling, in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2025.

[8] Chenye Wang, Saihui Hou, Aoqi Li, Qingyuan Cai, Yongzhen Huang, RA-GAR: A Richly Annotated Benchmark for Gait Attribute Recognition, in AAAI Conference on Artificial Intelligence (AAAI, CCF-A), 2024.

[9] Aoqi Li, Saihui Hou, Chenye Wang, Qingyuan Cai, Yongzhen Huang, AerialGait: Bridging Aerial and Ground Views for Gait Recognition, in ACM International Conference on Multimedia (ACM MM, CCF-A), 2024.

[10] Jilong Wang, Saihui Hou, Yan Huang, Chunshui Cao, Xu Liu, Yongzhen Huang, Tianzhu Zhang, Liang Wang, Free Lunch for Gait Recognition: A Novel Relation Descriptor, in European Conference on Computer Vision (ECCV), 2024.

[11] Yang Fu, Saihui Hou, Shibei Meng, Xuecai Hu, Chunshui Cao, Xu Liu, Yongzhen Huang, Cut out the Middleman: Revisiting Pose-based Gait Recognition, in European Conference on Computer Vision (ECCV), 2024.

[12] Panjian Huang, Yunjie Peng, Saihui Hou, Chunshui Cao, Xu Liu, Zhiqiang He, Yongzhen Huang, Occluded Gait Recognition with Mixture of Experts: An Action Detection Perspective, in European Conference on Computer Vision (ECCV), 2024.

[13] Qingyuan Cai, Xuecai Hu, Saihui Hou, Li Yao, Yongzhen Huang, Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser, in AAAI Conference on Artificial Intelligence (AAAI, CCF-A), 2023.

[14] Zengbin Wang, Saihui Hou, Man Zhang, Xu Liu, Chunshui Cao, Yongzhen Huang, Peipei Li, Shibiao Xu, QAGait: Revisit Gait Recognition From a Quality Perspective, in AAAI Conference on Artificial Intelligence (AAAI, CCF-A), 2023.

[15] Zengbin Wang, Saihui Hou, Man Zhang, Xu Liu, Chunshui Cao, Yongzhen Huang, Shibiao Xu, LandmarkGait: Intrinsic Human Parsing for Gait Recognition, in ACM International Conference on Multimedia (ACM MM, CCF-A), 2023.

[16] Jilong Wang, Saihui Hou, Yan Huang, Chunshui Cao, Xu Liu, Yongzhen Huang, Liang Wang, Causal Intervention for Sparse-View Gait Recognition, in ACM International Conference on Multimedia (ACM MM, CCF-A), 2023.

[17] Yang Fu, Shibei Meng, Saihui Hou, Xuecai Hu, Yongzhen Huang, GPGait: Generalized Pose-based Gait Recognition, in IEEE/CVF Conference on Computer Vision (ICCV, CCF-A), 2023.

[18] 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/CVF Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2023.

[19] Junhao Liang, Chao Fan, Saihui Hou, Chuanfu Shen, Yongzhen Huang, Shiqi Yu, GaitEdge: Beyond plain end-to-end gait recognition for better practicality, in European Conference on Computer Vision (ECCV), 2022.

[20] Saihui Hou, Chunshui Cao, Xu Liu, Yongzhen Huang, Gait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition, in European Conference on Computer Vision (ECCV), 2020.

[21] Saihui Hou, Zilei Wang, Weighted Channel Dropout for Regularization of Deep Convolutional Neural Network, in AAAI Conference on Artificial Intelligence (AAAI, CCF-A), 2019.

[22] Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, Dahua Lin, Learning a Unified Classifier Incrementally via Rebalancing, in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2019.

[23] Jiafan Zhuang, Saihui Hou, Zilei Wang, Zheng-Jun Zha, Towards Human-Level License Plate Recognition, in European Conference on Computer Vision (ECCV), 2018.

[24] Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, Dahua Lin, Lifelong Learning via Progressive Distillation and Retrospection, in European Conference on Computer Vision (ECCV), 2018.

[25] Saihui Hou, Yushan Feng, Zilei Wang, VegFru: A Domain-Specific Dataset for Fine-grained Visual Categorization, in IEEE Conference on Computer Vision (ICCV, CCF-A), 2017.

[26] Saihui Hou, Xu Liu, Zilei Wang, DualNet: Learn Complementary Features for Image Recognition, in IEEE Conference on Computer Vision (ICCV, CCF-A), 2017.

奖励与荣誉

• 2022年，入选北京市科协青年人才托举工程

• 2019年，获中国科学院院长奖优秀奖

• 2019年，获中国科学技术大学优秀博士论文

• 2016年，获研究生国家奖学金 (Top 5%)

• 2014年，获中国科学技术大学优秀毕业生

• 2013年，获本科生国家奖学金 (Top 5%)

学术与社会服务

• 中国图象图形学学会机器视觉专委会委员

• 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2-3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。