分解与迁移：思维链提示增强的对齐用于开放词表时序动作检测
Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection
利用大语言模型的思维链推理将动作标签分解为阶段级描述，并通过文本引导的前景过滤和自适应阶段对齐实现细粒度视觉-文本匹配，为开放词表时序动作检测提供可迁移的语义先验。
原文依据 leverages the chain-of-thought (CoT) reasoning ability of large language models to automatically decompose action labels into coherent phase-level descriptions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论开放词表时序动作检测（OV-TAD）旨在对未修剪视频中的动作片段进行分类和定位，且类别在训练中未见过。先前方法仅依赖标签级语义与视觉特征之间的全局对齐，不足以从已见类别向未见类别迁移时序一致的视觉知识。为此，我们提出阶段分解与对齐（PDA）框架，实现细粒度动作模式学习以有效迁移先验知识。具体地，我们首先引入思维链提示语义分解（CSD）模块，利用大语言模型的思维链（CoT）推理能力，自动将动作标签分解为连贯的阶段级描述，模拟人类认知过程。然后，引入文本注入前景过滤（TIF）模块，利用阶段级语义线索自适应地为每个阶段过滤动作相关片段，生成语义对齐的视觉表示。此外，我们提出自适应阶段对齐（APA）模块，执行阶段级视觉-文本匹配，并自适应地聚合各阶段的对齐结果以进行最终预测。这种自适应阶段对齐有助于捕捉可迁移的动作模式，并显著增强对未见动作的泛化能力。在两个OV-TAD基准上的大量实验证明了所提方法的优越性。
英文原文摘要 1479 字符
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features, which is insufficient to transfer temporal consistent visual knowledge from seen to unseen classes. To address this, we propose a Phase-wise Decomposition and Alignment (PDA) framework, which enables fine-grained action pattern learning for effective prior knowledge transfer. Specifically, we first introduce the CoT-Prompting Semantic Decomposition (CSD) module, which leverages the chain-of-thought (CoT) reasoning ability of large language models to automatically decompose action labels into coherent phase-level descriptions, emulating human cognitive processes. Then, Text-infused Foreground Filtering (TIF) module is introduced to adaptively filter action-relevant segments for each phase leveraging phase-wise semantic cues, producing semantically aligned visual representations. Furthermore, we propose the Adaptive Phase-wise Alignment (APA) module to perform phase-level visual-textual matching, and adaptively aggregates alignment results across phases for final prediction. This adaptive phase-wise alignment facilitates the capture of transferable action patterns and significantly enhances generalization to unseen actions. Extensive experiments on two OV-TAD benchmarks demonstrated the superiority of the proposed method.