MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification

NeurIPSSpotlight2025

Authors: Yingying Feng, Jie Li, Jie Hu, Yukang Zhang, Lei Tan, Jiayi Ji
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

The challenge of inconsistent modalities in real-world applications presents significant obstacles to effective object re-identification (ReID)

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

← All NeurIPS 2025 Spotlight papers · Browse the whole archive