Research map / Label-efficient and robust learning / Recognition and long-tail
Prototype Topology Consistency for Visible-Infrared Lifelong Person Re-Identification
Tan Shang, Zhijie Lu, Wuxuan Shi, He Li, Mang Ye
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a prototype topology consistency approach for visible-infrared lifelong person re-identification to keep instance-to-prototype assignment rankings stable across sequential tasks.
Problem
Visible-infrared lifelong person re-identification (VI-LReID), where a model must learn cross-modal person retrieval across sequential tasks without forgetting earlier ones; new-task gradient updates disrupt each instance's ranking over historical class prototypes.
Approach
Preserves the topology of instance-to-prototype assignment rankings over historical class prototypes during new-task learning, targeting the mechanism behind catastrophic forgetting in cross-modal lifelong ReID. Full method details are not available from the abstract.
Closest papers by meaning
- Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification (ICCV 2023 · similarity 0.90)
- Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification (ECCV 2024 · similarity 0.88)
- Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification (ECCV 2022 · similarity 0.88)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.88)
- Granular Semantic Cognition for Visible-Infrared Person Re-Identification (ECCV 2026 · similarity 0.88)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
