cross-modal 1multimodal 1person re-identification 1pseudo-label noise reduction 1semantic calibration 1structural decoupling 1survey 1unsupervised person re-identification 1visible-infrared cross-modal matching 1vision transformers 1
From the 2 of 3 linked papers with an AI index.
3 papers
cs.CV2026
Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification
Moyao Tian, Shijia Liu, Yan Yang +4
The paper proposes a framework called Structural‑Semantic Reciprocal Learning (SSRL) that uses fine‑grained body‑part features and a closed‑loop semantic calibration to improve uns…
cs.CV2026
Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification
Xiao Wang, Bing Wang, Bin Yang +3
This paper surveys the shift in person re-identification from single‑modal RGB approaches to cross‑modal and multi‑modal methods, covering tasks such as visible‑infrared, text‑imag…
cs.CV2026
Cross-Resolution Semantic Transfer for Robust Text-to-Image Retrieval in Low-Resolution Surveillance
Wenjie Qian, Bin Yang, Xiao Wang +4
Text-to-image person re-identification (TIPR) retrieves target persons using natural language descriptions. However, existing methods largely overlook resolution variance in real-w…