Chain-of-Thought Guided Multi-Modal Object Re-Identification

With the rise of visual-language models, multi-modal ReID retrieves specific targets by integrating different spectra and textual descriptions. Existing methods merely adopt descriptive representation learning for image-text, ignoring the relationships among the intrinsic logical hierarchies of semantic features. Since Chain-of-Thought (CoT) can provide textual logical context and enhance semantic perception in large-model reasoning, we propose CoT-ReID, a CoT-guided framework that injects the Multi-modal Large Language Models (MLLMs) reasoning into multi-modal ReID. Specifically, we simulate human-like joint visiontext logical decision-making, leveraging CoT textual logical reasoning to guide visual feature learning at the early, late and decision-making levels: we first embed the semantic reversion of CoT hierarchical reasoning into visual features to calibrate bottom-level features and highlight visual hierarchical reasoning, then take CoT hierarchical reasoning text as an anchor condition to constrain the consistency of visual cross-modal semantics, and finally embed logically reasoned text attribute features into multi-modal decision-making via CoT's hierarchical reasoning to provide logical support for selecting discriminative identity features. By constructing CoT textual benchmarks and our proposed modules, our framework generates more robust multi-modal features in complex scenarios, and comprehensive experiments on four datasets (RGBNT100, MSVR310, WMVeID863, RGBNT201) demonstrate the superiority of our method over state-of-the-art approaches.