面向过程感知教学视频分析的协同弱监督视频相关性学习
Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis
AI总结：
针对教学视频相关性分析依赖昂贵步骤级标注的问题，提出含协同步骤挖掘与帧-步对齐模块的CPA弱监督框架，在序列验证等任务中验证了其准确可解释的分析效果。
摘要：
视频相关性学习（VCL）旨在分析视频间的关系，已在各类通用视频任务中得到广泛研究与应用。然而，由于教学视频固有的过程化时间结构，将VCL应用于教学视频仍颇具挑战。具体而言，过程知识对教学视频的精准相关性分析至关重要，但当前的过程学习方法严重依赖步骤级标注，这类标注成本高昂且难以规模化。为解决该问题，我们提出了名为Collaborative Procedure Alignment（协同过程对齐，CPA）的弱监督框架，用于教学视频的过程感知相关性学习。该框架包含两个核心模块：协同步骤挖掘与帧-步对齐。协同步骤挖掘模块利用帧间的语义与时间相似性，实现配对视频的同步且一致的步骤分割。基于识别出的步骤，帧-步对齐模块执行跨视频的帧与步骤之间的对齐，对齐结果可作为两个视频间相关性距离的度量。我们在两个不同的教学视频任务中实例化了该框架：序列验证与动作质量评估。大量实验验证了我们的方法在为教学视频提供准确且可解释的相关性分析方面的有效性。
英文摘要：
Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to their intrinsic procedural temporal structure. Specifically, procedural knowledge is critical for accurate correlation analyses on instructional videos. Nevertheless, current procedure-learning methods heavily rely on step-level annotations, which are costly and not scalable. To address this problem, we introduce a weakly supervised framework called Collaborative Procedure Alignment (CPA) for procedure-aware correlation learning on instructional videos. Our framework comprises two core modules: collaborative step mining and frame-to-step alignment. The collaborative step mining module enables simultaneous and consistent step segmentation for paired videos, leveraging the semantic and temporal similarity between frames. Based on the identified steps, the frame-to-step alignment module performs alignment between the frames and steps across videos. The alignment result serves as a measurement of the correlation distance between two videos. We instantiate our framework in two distinct instructional video tasks: sequence verification and action quality assessment. Extensive experiments validate the effectiveness of our approach in providing accurate and interpretable correlation analyses for instructional videos.
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。
