Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval 事件

Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval arXiv:2606.00910v1 Announce Type: new Abstract: Composed Video Retrieval (CoVR) seeks the target video that results from applying a free-form textual modification to a reference video. We address the \emph{Reason-Aware} CoVR (CoVR-R) challenge at the CVPR~2026 VidLLMs workshop, where retrieval is strictly zero-shot. We present \textbf{R3-CoVR} (\emph{Reason, Retrieve, Re-rank}), a training-free pipelin