StreamingCoT：面向流式视频问答中时间动态与多模态思维链推理的数据集
StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA
AI总结：
针对现有VideoQA数据集难捕捉答案时间演化、缺推理标注的问题，研究提出首个流式视频问答时间演化推理数据集StreamingCoT，含动态分层标注与显式推理链生成范式，为流式视频理解等研究提供基础。
摘要：
流式视频应用的快速发展，要求多模态模型具备更强的时间动态理解与复杂推理能力。然而，当前视频问答（VideoQA）数据集存在两大关键局限：1）静态标注机制无法捕捉时间视频流中答案的演化特性；2）缺少显式推理过程标注，限制了模型的可解释性与逻辑演绎能力。为解决这些挑战，我们推出了StreamingCoT，这是首个专门为流式VideoQA中的时间演化推理及多模态思维链（Chain-of-Thought, CoT）任务设计的数据集。我们的框架首先搭建了动态分层标注架构，生成每秒级的密集描述，通过相似度融合构建具有时间依赖性的语义片段，并搭配受时间演化模式约束的问答对。我们进一步提出了显式推理链生成范式：通过关键帧语义对齐提取时空对象，利用大语言模型推导基于对象状态转移的推理路径，并经人工验证确保逻辑一致性。该数据集为推进流式视频理解、复杂时间推理及多模态推理研究奠定了基础。我们的StreamingCoT及其构建工具包可通过https://github.com/Fleeting-hyh/StreamingCoT获取。
英文摘要：
The rapid growth of streaming video applications demands multimodal models with enhanced capabilities for temporal dynamics understanding and complex reasoning. However, current Video Question Answering (VideoQA) datasets suffer from two critical limitations: 1) Static annotation mechanisms fail to capture the evolving nature of answers in temporal video streams, and 2) The absence of explicit reasoning process annotations restricts model interpretability and logical deduction capabilities. To address these challenges, We introduce StreamingCoT, the first dataset explicitly designed for temporally evolving reasoning in streaming VideoQA and multimodal Chain-of-Thought (CoT) tasks. Our framework first establishes a dynamic hierarchical annotation architecture that generates per-second dense descriptions and constructs temporally-dependent semantic segments through similarity fusion, paired with question-answer sets constrained by temporal evolution patterns. We further propose an explicit reasoning chain generation paradigm that extracts spatiotemporal objects via keyframe semantic alignment, derives object state transition-based reasoning paths using large language models, and ensures logical coherence through human-verified validation. This dataset establishes a foundation for advancing research in streaming video understanding, complex temporal reasoning, and multimodal inference. Our StreamingCoT and its construction toolkit can be accessed at https://github.com/Fleeting-hyh/StreamingCoT.
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。
