{"ID":2923627,"CreatedAt":"2026-06-02T04:05:25.881865328Z","UpdatedAt":"2026-06-04T13:12:39.622923895Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.02321","arxiv_id":"2606.02321","title":"Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning","abstract":"Recent advances in large vision-language models have expanded video retrieval from simple text-based search to more flexible scenarios, where users may specify the desired result through both visual examples and textual instructions. In the CVPR 2026 Reason-Aware Composed Video Retrieval Challenge, the system is required to retrieve a target video according to a reference video and a modification instruction. To address this task, we develop Visual Representation-Guided Video-LLM Reasoning for Training-Free Composed Video Retrieval. Our framework first uses frozen DINOv3 models to obtain a compact set of visually relevant candidates, and then applies large vision-language models to evaluate whether each candidate satisfies the modification instruction. A final reasoning-based refinement is further performed on the top candidates to improve the first-ranked prediction. Without training, our system achieves 48.78 Recall@1 and 51.48 Recall@5 on the test set. Future work may further improve retrieval accuracy through stronger video-LLMs and detailed integration between visual representations and language reasoning.","short_abstract":"Recent advances in large vision-language models have expanded video retrieval from simple text-based search to more flexible scenarios, where users may specify the desired result through both visual examples and textual instructions. In the CVPR 2026 Reason-Aware Composed Video Retrieval Challenge, the system is requir...","url_abs":"https://arxiv.org/abs/2606.02321","url_pdf":"https://arxiv.org/pdf/2606.02321v1","authors":"[\"Yang Liu\",\"Qianqian Xu\",\"Peisong Wen\",\"Siran Dai\",\"Qingming Huang\"]","published":"2026-06-01T14:35:23Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}