无需训练，用视觉特征引导大模型推理，实现精准视频组合检索
Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning
- 用冻结的DINOv3提取视觉候选，再用大模型判断是否符合修改指令
- 在测试集上达48.78 Recall@1和51.48 Recall@5，无需训练即可达成高精度
- 适合需要快速部署、无标注数据场景下的视频检索应用
大型视觉语言模型的进展使视频检索从简单的文本搜索扩展到更灵活的场景，用户可通过视觉示例和文本指令共同指定目标结果。在CVPR 2026的可解释组合视频检索挑战中，系统需根据参考视频和修改指令检索目标视频。为此，我们提出无需训练的视觉表征引导视频大模型推理框架。该框架首先利用冻结的DINOv3模型获取一组紧凑的视觉相关候选视频，随后通过大型视觉语言模型评估每个候选是否满足修改指令。对排名靠前的候选进行基于推理的进一步优化，以提升最优预测结果。该方法无需训练，在测试集上取得48.78 Recall@1和51.48 Recall@5的性能表现。未来工作可借助更强的视频-大模型及视觉表征与语言推理的深度融合，进一步提升检索准确率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。