赋能词语：用于结构化短语和句子级时间定位的DualGround
Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding
AI总结：
针对视频时间定位中文本标记统一处理导致细粒度对齐不足的问题，提出双分支架构DualGround，分离句子级与短语级语义，在QVHighlights和Charades-STA上实现最先进性能。
摘要：
视频时间定位（VTG）旨在定位与给定自然语言查询对齐的长篇未修剪视频中的时间片段。该任务通常包含两个子任务：时刻检索（MR）和精彩片段检测（HD）。尽管近期进展得益于强大的预训练视觉-语言模型（如CLIP和InternVideo2），现有方法通常在跨模态注意力期间将所有文本标记统一处理，忽视了它们不同的语义角色。为验证这种方法的局限性，我们进行了受控实验，证明VTG模型过度依赖[EOS]驱动的全局语义，而未能有效利用词级信号，这限制了它们实现细粒度时间对齐的能力。受此局限性启发，我们提出了DualGround，一种双分支架构，通过将[EOS]标记路由到句子级路径并将词标记聚类为短语级单元进行局部定位，从而明确分离全局和局部语义。我们的方法引入了（1）标记角色感知的跨模态交互策略，以结构解耦的方式将视频特征与句子级和短语级语义对齐，以及（2）一个联合建模框架，不仅改善全局句子级对齐，还通过利用结构化短语感知上下文增强细粒度时间定位。这种设计使模型能够捕获粗粒度和局部语义，实现更具表现力和上下文感知的视频定位。DualGround在QVHighlights和Charades-STA基准上的时刻检索和精彩片段检测任务均达到最先进性能，证明了在视频-语言对齐中解耦语义建模的有效性。
英文摘要：
Video Temporal Grounding (VTG) aims to localize temporal segments in long, untrimmed videos that align with a given natural language query. This task typically comprises two subtasks: Moment Retrieval (MR) and Highlight Detection (HD). While recent advances have been progressed by powerful pretrained vision-language models such as CLIP and InternVideo2, existing approaches commonly treat all text tokens uniformly during crossmodal attention, disregarding their distinct semantic roles. To validate the limitations of this approach, we conduct controlled experiments demonstrating that VTG models overly rely on [EOS]-driven global semantics while failing to effectively utilize word-level signals, which limits their ability to achieve fine-grained temporal alignment. Motivated by this limitation, we propose DualGround, a dual-branch architecture that explicitly separates global and local semantics by routing the [EOS] token through a sentence-level path and clustering word tokens into phrase-level units for localized grounding. Our method introduces (1) tokenrole- aware cross modal interaction strategies that align video features with sentence-level and phrase-level semantics in a structurally disentangled manner, and (2) a joint modeling framework that not only improves global sentence-level alignment but also enhances finegrained temporal grounding by leveraging structured phrase-aware context. This design allows the model to capture both coarse and localized semantics, enabling more expressive and context-aware video grounding. DualGround achieves state-of-the-art performance on both Moment Retrieval and Highlight Detection tasks across QVHighlights and Charades- STA benchmarks, demonstrating the effectiveness of disentangled semantic modeling in video-language alignment.
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。
