CoTasks：基于思维链的视频指令微调任务
CoTasks: Chain-of-Thought based Video Instruction Tuning Tasks
AI总结：
CoTasks框架通过将复杂视频问题分解为帧定位、实体跟踪、时空关系提取四类基础任务，以CoT式结构化监督提升视频大语言模型的组合推理能力，在NeXT-QA上显著提高多个模型的推理性能。
摘要：
尽管视频大语言模型（VideoLLMs）近期取得进展，一个关键开放挑战仍然存在：如何赋予模型以基于细粒度对象级视频理解的思维链（CoT）推理能力。现有指令微调模型（如Qwen和LLaVA系列）在高层次视频-文本对上训练，往往缺乏组合式、逐步推理所需的结构化标注。我们提出CoTasks：基于思维链的视频指令微调任务，这是一个新框架，将现有数据集（如NeXT-QA、STAR）中的复杂视频问题分解为四个实体级基础任务：帧定位、实体跟踪、空间关系提取和时间关系提取。通过将这些中间CoT式推理步骤嵌入输入，CoTasks使模型能够显式执行以对象为中心的时空推理。在NeXT-QA基准上的实验表明，CoTasks显著提升推理性能：LLaVA-video-7B的平均GPT-4评估分数提高+3.3分，Qwen2.5-VL-3B提高+17.4分，其中因果（+14.6）、时间（+10.9）和描述（+48.1）子类别提升显著。这些结果证明了CoTasks作为一种结构化CoT式监督框架在改进组合视频推理方面的有效性。
英文摘要：
Despite recent progress in video large language models (VideoLLMs), a key open challenge remains: how to equip models with chain-of-thought (CoT) reasoning abilities grounded in fine-grained object-level video understanding. Existing instruction-tuned models, such as the Qwen and LLaVA series, are trained on high-level video-text pairs, often lacking structured annotations necessary for compositional, step-by-step reasoning. We propose CoTasks: Chain-of-Thought based Video Instruction Tuning Tasks, a new framework that decomposes complex video questions of existing datasets (e.g., NeXT-QA, STAR) into four entity-level foundational tasks: frame localization, entity tracking, spatial and temporal relation extraction. By embedding these intermediate CoT-style reasoning steps into the input, CoTasks enables models to explicitly perform object-centric spatiotemporal reasoning. Experiments on the NeXT-QA benchmark show that CoTasks significantly enhance inference performance: LLaVA-video-7B improves by +3.3 points in average GPT-4 evaluation score, and Qwen2.5-VL-3B gains +17.4, with large boosts in causal (+14.6), temporal (+10.9), and descriptive (+48.1) subcategories. These results demonstrate the effectiveness of CoTasks as a structured CoT-style supervision framework for improving compositional video reasoning.
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。
