Video-Skill-CoT：面向领域自适应视频推理的基于技能的思维链
Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
AI总结：
针对视频推理中领域技能适应难的问题，提出Video-Skill-CoT框架，自动构建技能感知的思维链监督并采用技能特定专家学习，在三个基准上持续优于强基线。
摘要：
思维链（CoT）推理的最新进展提升了复杂视频理解能力，但现有方法往往难以适应各种视频内容中的领域特定技能（如事件检测、空间关系理解、情感理解）。为解决这一问题，我们提出了Video-Skill-CoT（又称Video-SKoT），一个自动构建并利用技能感知的思维链监督信号以实现领域自适应视频推理的框架。首先，我们构建基于技能的思维链标注：从训练问题中提取领域相关的推理技能，将其聚类为共享的技能分类体系，并为每个视频-问题对创建详细的多步思维链推理依据用于训练。其次，我们引入技能特定的专家学习框架。每个专家模块专注于一部分推理技能，并使用轻量级适配器在收集的思维链监督下进行训练。我们在三个视频理解基准上证明了所提方法的有效性，其中Video-SKoT持续优于强基线方法。我们还提供了关于比较不同思维链标注流程及在多个视频领域上学到的技能的深入分析。
英文摘要：
Recent advances in Chain-of-Thought (CoT) reasoning have improved complex video understanding, but existing methods often struggle to adapt to domain-specific skills (e.g., event detection, spatial relation understanding, emotion understanding) over various video content. To address this, we propose Video-Skill-CoT (a.k.a. Video-SKoT), a framework that automatically constructs and leverages skill-aware CoT supervisions for domain-adaptive video reasoning. First, we construct skill-based CoT annotations: we extract domain-relevant reasoning skills from training questions, cluster them into a shared skill taxonomy, and create detailed multi-step CoT rationale tailored to each video-question pair for training. Second, we introduce a skill-specific expert learning framework. Each expert module specializes in a subset of reasoning skills and is trained with lightweight adapters using the collected CoT supervision. We demonstrate the effectiveness of the proposed approach on three video understanding benchmarks, where Video-SKoT consistently outperforms strong baselines. We also provide in-depth analyses on comparing different CoT annotation pipelines and learned skills over multiple video domains.
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。
