Open-o3-Video: 基于显式时空证据的视频推理
Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
AI总结：
本文提出Open-o3-Video，通过显式时空证据提升视频推理的可追溯性与可验证性，基于STGR数据集和冷启动强化学习策略，在V-STAR基准上取得SOTA性能，并支持置信度感知的测试时扩展。
摘要：
大多数视频推理模型仅生成文本推理轨迹，无法指示关键证据出现的时间和位置。近期的OpenAI-o3模型在图像证据中心推理中受到广泛关注，但将其扩展到视频更具挑战性，因为需要在动态场景中联合时间跟踪和空间定位。我们引入Open-o3-Video，非代理框架通过突出关键时间戳、对象和边界框，将显式时空证据整合到视频推理中，使推理过程可追溯且可验证。为实现此能力，我们首先构建高质量的STGR数据集，提供统一的时空监督，这在现有资源中缺失。我们进一步采用冷启动强化学习策略，结合特别设计的奖励，共同促进回答准确性、时间对齐和空间精度。在V-STAR基准上，Open-o3-Video取得SOTA性能，比Qwen2.5-VL基线提升mAM 14.4%和mLGM 24.2%，并在多种视频理解基准上表现一致。除了准确性，Open-o3-Video生成的 grounded 推理轨迹支持置信度感知的测试时扩展，提高回答可靠性。
英文摘要：
Most video reasoning models only generate textual reasoning traces without indicating when and where key evidence appears. Recent models such as OpenAI-o3 have sparked wide interest in evidence-centered reasoning for images, yet extending this ability to videos is more challenging due to the need for joint temporal tracking and spatial localization across dynamic scenes. We introduce Open-o3-Video, a non-agent framework that integrates explicit spatio-temporal evidence into video reasoning by highlighting key timestamps, objects, and bounding boxes, making the reasoning process traceable and verifiable. To enable this capability, we first construct high-quality datasets STGR that provide unified spatio-temporal supervision, which is absent in existing resources. We further adopt a cold-start reinforcement learning strategy with specially designed rewards that jointly encourage answer accuracy, temporal alignment, and spatial precision. On the V-STAR benchmark, Open-o3-Video achieves state-of-the-art performance, improving mAM by 14.4% and mLGM by 24.2% over the Qwen2.5-VL baseline, and shows consistent gains across a range of video understanding benchmarks. Beyond accuracy, the grounded reasoning traces produced by Open-o3-Video support confidence-aware test-time scaling, improving answer reliability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
