2 papers
cs.CV2026
Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
Mingyu Liu, Sihan Huang, Yijia Fan +4
Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modification without human-annotated CIR triplets. Projection-based ZS-CIR me…
cs.CV2026
Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification
Quan Zhang, Jingze Wu, Jialong Wang +3
Learning identity-discriminative representations with multi-scene generality has become a critical objective in person re-identification (ReID). However, mainstream perception-driv…