SOURCE-LINKED INTELLIGENCE

Hypergraph-Regularized Gramian Volumes for Multimodal Retrieval

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Volume-based multimodal retrieval jointly scores a text query with a candidate's video, audio, and subtitle embeddings. While this approach captures higher-order within-candidate alignment, the score remains candidate-local, and semantically related training samples primarily serve as contrastive negatives. This work introduces Hypergraph-Regularized Gramian Volumes (HyVol), a training-time module that incorporates these semantic relations prior to evaluating the original volume loss. Document hyperedges connect the observed modalities of each candidate, whereas semantic hyperedges link candid

Read original source ↗ Open in workspace

recordType

paper

region

Global