SOURCE-LINKED INTELLIGENCE

Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gallery scale, this creates a fundamental tension: compact embeddings enable efficient, reusable search but can miss the transient actions, state changes, and subtle constraints that demand fine-grained video reasoning, whereas applying large multimodal models uniformly sacrifices scalability. To address these limitations, we propose that frozen foundation models should instead occupy complementary roles, with inference depth adapted to query diffi

Read original source ↗ Open in workspace

recordType

paper

region

Global