Cross-Modal Retrieval

Universal Unsupervised Cross-Domain Retrieval (U2CDR) framework learns semantic features to enable accurate retrieval even when category spaces differ across domains.

NeuroBOLT: Resting-state EEG-to-fMRI synthesis using multi-dimensional feature mapping.

Unaligned multimodal mixtures’ shared components are identifiable under mild conditions using a distribution-matching approach, relaxing assumptions of existing methods.

MolPhenix, a novel multi-modal model, drastically improves zero-shot molecular retrieval by leveraging a pre-trained phenomics model and a novel similarity-aware loss, achieving an 8.1x improvement ov…

PCRIL, a novel prompt contrastive recovery approach, significantly boosts cross-modal hashing accuracy, especially when dealing with incomplete labels by progressively identifying promising positive c…

Large foundation models empower visible-infrared person re-identification by enriching infrared image representations with automatically generated textual descriptions, significantly improving cross-m…

Diffusion-Inspired Truncated Sampler (DITS) revolutionizes text-video retrieval by progressively aligning embeddings and enhancing CLIP embedding space structure, achieving state-of-the-art results.

EGATH: End-to-End Graph Attention Network Hashing revolutionizes cross-modal retrieval by combining CLIP, transformers, and graph attention networks for superior semantic understanding and hash code g…