研究人员推出 VideoSearch-R1，一个旨在改进视频检索与推理的新型代理框架。该系统通过迭代方式与视频搜索引擎交互，采用一种称为软查询精炼 (SQR) 的技术，在连续潜在空间中调整搜索查询。该框架使用组相对策略优化 (GRPO) 进行训练，并在视频语料库时刻检索 (VCMR) 基准测试中展现出最先进的性能，与传统的基于文本的查询精炼相比，所需的生成令牌更少。 AI
影响 这项研究通过改进查询的精炼和处理方式，有望带来更高效、更准确的视频搜索和分析系统。
排序理由 该集群描述了一篇关于视频检索与推理的新型框架和技术的新研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.00446v1 Announce Type: cross Abstract: As video corpora continue to expand in both scale and task complexity, there is increasing demand for approaches that retrieve relevant videos from large-scale corpora (inter-video reasoning) and subsequently perform fine-grained,…
As video corpora continue to expand in both scale and task complexity, there is increasing demand for approaches that retrieve relevant videos from large-scale corpora (inter-video reasoning) and subsequently perform fine-grained, query-conditioned tasks (intra-video reasoning) w…
VideoSearch-R1 is an agentic framework that iteratively retrieves videos and refines search queries using continuous latent space refinement and policy optimization for improved video moment retrieval and temporal grounding.