HPRNet: Human Parsing Reconstruction With Non-Local Multi-Scale Perception Network for Cloth-Changing Person Re-Identification
Mingfu Xionga, Longlong Gea, Ruimin Hub, Khan Muhammadc, Sambit Bakshid e, Javier Del Serf, Xiaokang Yangg h, Bin Shengi j
- aSchool of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China
- bSchool of Cyber Science and Engineering, Wuhan University, Wuhan, China
- cDepartment of Applied Artificial Intelligence, School of Convergence, College of Computing and Informatics, Visual Analytics for Knowledge Laboratory (VIS2KNOW Lab), Sungkyunkwan University, Seoul, Republic of Korea
- dDepartment of Computer Science and Engineering, Visual Surveillance Laboratory, National Institute of Technology Rourkela, Rourkela, Odisha, India
- eDepartment of Computer Science and Engineering, Visual Surveillance Laboratory, National Institute of Technology, Rourkela, Odisha, India
- fTECNALIA, Basque Research and Technology Alliance (BRTA), Derio, Spain
- gMOE Key Laboratory of AI, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
- hSchool of Electronics, Information, and Electrical Engineering, MOE Key Laboratory of AI, Shanghai Jiao Tong University, Shanghai, China
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Cloth-changing Person Re-Identification (CC-ReID) is a challenging data modeling task that involves identifying specific pedestrians wearing different outfits. Existing methods primarily focus on altering clothing color and directly reconstructing appearance to extract features independent of the clothes. Real pedestrians differ in height, body shape, etc. Such methods are prone to losing the intrinsic information of the original sample (i.e., the person identity) owing to the absence of contextual phenomena (e.g., texture structure and local correlation), which decreases the recognition performance. To address this problem, we propose a framework called HPRNet, or ”Human Parsing Reconstruction with Non-Local Multi-Scale Perception Network,” which includes a non-local weighted multi-scale perception (NWMP) module and a parsing reconstruction exploration (PRE) module. In particular, the proposed NWMP module effectively captures the global receptive field of a sample and obtains a contextual correlation between non-neighboring pixels within the sample image. The PRE module was used to achieve a more accurate reconstruction of human body components with a clothing parsing model to better distinguish features related to or unrelated to clothes. Extensive experiments were conducted on CC-ReID public datasets (LTCC, PRCC, and CCVID) to demonstrate the effectiveness and competitiveness of the proposed method with state-of-the-art (SOTA) baselines for this complex modeling task.