See What You Seek: Semantic Contextual Integration for Cloth-Changing Person Re-Identification

作     者：Han, Xiyu Zhong, Xian Huang, Wenxin Jia, Xuemei Liu, Wenxuan Yu, Xiaohan Kot, Alex Chichung 

作者机构：Wuhan University of Technology Sanya Science and Education Innovation Park Sanya572025 China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430070 China School of Computer Science and Information Engineering Hubei University Wuhan430062 China School of Computer Science Wuhan University Wuhan430072 China School of Computer Science Peking University Beijing100091 China School of Computing Macquarie University SydneyNSW2109 Australia Rapid-Rich Object Search Lab School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Semantics 

摘      要：Cloth-changing person re-identification (CC-ReID) aims to match individuals across multiple surveillance cameras despite variations in clothing. Existing methods typically focus on mitigating the effects of clothing changes or enhancing ID-relevant features but often struggle to capture complex semantic information. In this paper, we propose a novel prompt learning framework, Semantic Contextual Integration (SCI), for CC-ReID, which leverages the visual-text representation capabilities of CLIP to minimize the impact of clothing changes and enhance ID-relevant features. Specifically, we introduce Semantic Separation Enhancement (SSE) module, which uses dual learnable text tokens to separately capture confounding and clothing-related semantic information, effectively isolating ID-relevant features from distracting clothing semantics. Additionally, we develop a Semantic-Guided Interaction Module (SIM) that uses orthogonalized text features to guide visual representations, sharpening the model’s focus on distinctive ID characteristics. This integration enhances the model’s discriminative power and enriches the visual context with high-dimensional semantic insights. Extensive experiments on three CC-ReID datasets demonstrate that our method outperforms state-of-the-art techniques. The code will be released at github. Copyright © 2024, The Authors. All rights reserved.