简介

庞志奇，1998年生，准聘副教授。博士毕业于哈尔滨工业大学计算学部，师从长聘教授王春宇教授和IEEE Fellow Gaurav Sharma教授。主要研究方向为计算机视觉、图像检索、行人重识别等。以第一作者/通讯作者在NeurIPS、CVPR、ICCV、TIP、TIFS等国际顶级会议和期刊发表学术论文10余篇。

发表论文(部分)

[16] Zhiqi Pang, Lingling Zhao et al, “Image-Text Knowledge Modeling for Unsupervised Multi-Scenario Person Re-Identification,” AAAI 2026. (CCF-A 会议) 

[15] Zhiqi Pang, Lingling Zhao et al, “Robust Labeling and Invariance Modeling for Unsupervised Cross-Resolution Person Re-Identification,” IEEE Transactions on Image Processing, 2025. (中科院一区 Top, CCF-A 期刊) 

[14] Zhiqi Pang, Lingling Zhao et al, “LVLM-Driven Attribute-Aware Modeling for Visible-Infrared Person Re-Identification,” NeurIPS 2025. (CCF-A 会议) 

[13] Zhiqi Pang, Chunyu Wang et al, “Augmented and Softened Matching for Unsupervised Visible-Infrared Person Re-Identification,” ICCV 2025. (CCF-A 会议) 

[12] Zhiqi Pang, Junjie Wang et al, “Identity-Clothing Similarity Modeling for Unsupervised Clothing Change Person Re-Identification,” CVPR 2025. (CCF-A 会议) 

[11] Zhiqi Pang, Lingling Zhao et al, “Joint Augmentation and Part Learning for Unsupervised Clothing Change Person Re-Identification,” IEEE Transactions on Information Forensics and Security (TIFS), 2025. (中科院一区 Top, CCF-A 期刊, IF: 8.0) 

[10] Zhiqi Pang, Lingling Zhao, Chunyu Wang, “Dual-Resolution Fusion Modeling for Unsupervised Cross-Resolution Person Re-Identification,” ACM Multimedia 2024. (CCF-A 会议) (Oral, Top 3.97%) 

[9] Zhiqi Pang, Chunyu Wang et al, “Cross-modality hierarchical clustering and refinement for unsupervised visibleinfrared person re-identification,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023. (中科院一区 Top, CCF-B 期刊, IF: 11.1) (ESI 高被引) 

[8] Zhiqi Pang, Lingling Zhao et al, “Inter-modality similarity learning for unsupervised multi-modality person re-identification,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024. (中科院一区 Top, CCF-B 期刊, IF: 11.1) 

[7] Zhiqi Pang, Lingling Zhao et al, “Camera invariant feature learning for unsupervised person re-identification,” IEEE Transactions on Multimedia (TMM), 2023. (中科院一区 Top, CCF-B 期刊, IF: 9.7) 

[6] Zhiqi Pang, Jifeng Guo et al, “Median stable clustering and global feature distance classification for cross-domain person re-identification,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022. (中科院一区 Top, CCF-B 期刊, IF: 11.1) 

[5] Zhiqi Pang, Lingling Zhao, Chunyu Wang,  “Clothing-invariant contrastive learning for unsupervised person re-identification,” Neural Networks, 2024. (中科院二区 Top, CCF-B 期刊, IF: 6.3) 

[4] Zhiqi Pang, Chunyu Wang et al, “MIMR: modality-invariance modeling and refinement for unsupervised visible-infrared person re-identification,” Knowledge-Based Systems, 2024. (中科院一区 Top, CCF-C 期刊, IF: 7.6) 

[3] Zhiqi Pang, Chunyu Wang et al, “Reliability modeling and contrastive learning for unsupervised person re-identification,” Knowledge-Based Systems, 2023. (中科院一区 Top, CCF-C 期刊, IF: 7.6) 

[2] Zhiqi Pang, Jifeng Guo et al, “Cross-domain person re-identification by hybrid supervised and unsupervised learning,” Applied Intelligence, 2022. (中科院二区, CCF-C 期刊, IF: 3.5) 

[1] Zhiqi Pang, Jifeng Guo et al, “Biclustering collaborative learning for cross-domain person re-identification,” IEEE Signal Processing Letters (SPL), 2021. (中科院二区, CCF-C 期刊, IF: 3.9)

授权发明专利(部分)

[3] 庞志奇; 赵玲玲等, “基于可靠性建模的无监督行人重识别方法及系统”, 202211178254.3, 2023. 

[2] 王春宇; 庞志奇等, “基于模态不变性建模的无监督行人重识别方法及系统”, 202410154316.X, 2025. 

[1] 王春宇; 庞志奇等, “一种无监督跨模态行人重识别方法”, 202310148333.8, 2025.

所在团队：人工智能与媒体计算团队

团队负责人为王念滨教授。近年来，团队共承担各类项目50余项，经费总额超过3000万，在TIP、TIFS、NeurIPS、CVPR、ICCV等国际高水平期刊和会议发表论文60余篇，申请发明专利50余项。

欢迎有意愿从事人工智能、计算机视觉相关研究方向的研究生和本科生同学加入我们团队，提供GPU资源和科研指导。