超越全局对齐：通过金字塔Shapley-Taylor学习实现细粒度动语言检索
Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning
AI总结：
本文提出基于金字塔Shapley-Taylor学习的细粒度动语言检索方法，通过分层对齐捕捉局部细节与层次结构，提升检索性能。
摘要：
作为以人为中心的跨模态智能的基础任务，动语言检索旨在弥合自然语言和人类运动之间的语义鸿沟，从而实现直观的运动分析，但现有方法主要侧重于将整个运动序列与全局文本表示对齐。这种以全局为中心的范式忽视了局部运动片段与个体身体关节和文本标记之间的细粒度交互，不可避免地导致检索性能低下。为了解决这一限制，我们受到人类运动感知的金字塔过程（从关节动态到片段连贯性，最终到整体理解）的启发，提出了一种新的金字塔Shapley-Taylor（PST）学习框架，用于细粒度动语言检索。具体而言，该框架将人类运动分解为时间片段和空间身体关节，并通过逐步的关节级和片段级对齐，以金字塔的方式学习跨模态对应关系，有效捕捉了局部语义细节和层次结构关系。在多个公开基准数据集上的广泛实验表明，我们的方法显著优于最先进的方法，实现了运动片段和身体关节及其对应文本标记之间的精确对齐。本工作的代码将在接受后发布。
英文摘要：
As a foundational task in human-centric cross-modal intelligence, motion-language retrieval aims to bridge the semantic gap between natural language and human motion, enabling intuitive motion analysis, yet existing approaches predominantly focus on aligning entire motion sequences with global textual representations. This global-centric paradigm overlooks fine-grained interactions between local motion segments and individual body joints and text tokens, inevitably leading to suboptimal retrieval performance. To address this limitation, we draw inspiration from the pyramidal process of human motion perception (from joint dynamics to segment coherence, and finally to holistic comprehension) and propose a novel Pyramidal Shapley-Taylor (PST) learning framework for fine-grained motion-language retrieval. Specifically, the framework decomposes human motion into temporal segments and spatial body joints, and learns cross-modal correspondences through progressive joint-wise and segment-wise alignment in a pyramidal fashion, effectively capturing both local semantic details and hierarchical structural relationships. Extensive experiments on multiple public benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, achieving precise alignment between motion segments and body joints and their corresponding text tokens. The code of this work will be released upon acceptance.
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。
