AI RESEARCH
COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations
arXiv CS.CV
•
ArXi:2606.04604v1 Announce Type: new Composed Image Retrieval (CIR) represents a challenging retrieval task that targets locating specific images through multimodal inputs. Despite recent progress in CIR techniques, prior approaches often overlook cases where images appear visually alike yet differ in attributes, potentially undermining both multimodal feature fusion and similarity modeling. To mitigate this limitation, we design a unified representation of cross-modal features based on attribute prototypes.