SkeletonContext：面向零样本骨架动作识别的骨架侧上下文提示词学习
SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition
将大语言模型生成的上下文语义通过提示词学习注入骨架编码器，为骨骼动作识别提供实例级语义定位，可迁移到其他需要跨模态对齐的时序动作理解任务。
原文依据 we propose SkeletonContext, a prompt-based framework that enriches skeletal motion representations with language-driven contextual semantics.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论零样本骨架动作识别旨在通过语义描述从已见类别迁移知识来识别未见动作。现有方法大多在共享潜变量空间内将骨架特征与文本嵌入对齐。然而，缺乏上下文线索（如动作涉及的物体）导致骨架与语义表示之间存在固有差距，使得难以区分视觉上相似的动作。为此，我们提出 SkeletonContext，一个基于提示词的框架，通过语言驱动的上下文语义丰富骨骼运动表示。具体而言，我们引入跨模态上下文提示词模块，该模块利用预训练语言模型，在大语言模型引导下重建掩码上下文提示词。该设计有效将语言上下文迁移至骨架编码器，实现实例级语义定位并改进跨模态对齐。此外，我们加入关键部位解耦模块以解耦运动相关关节特征，确保即使在没有显式物体交互的情况下也能稳健理解动作。在多个基准上的大量实验表明，SkeletonContext 在传统和广义零样本设置下均达到最优性能，验证了其在推理上下文及区分细粒度、视觉相似动作方面的有效性。项目见：https://github.com/NingWang2049/skeletoncontext。
英文原文摘要 1533 字符
Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typically align skeleton features with textual embeddings within a shared latent space. However, the absence of contextual cues, such as objects involved in the action, introduces an inherent gap between skeleton and semantic representations, making it difficult to distinguish visually similar actions. To address this, we propose SkeletonContext, a prompt-based framework that enriches skeletal motion representations with language-driven contextual semantics. Specifically, we introduce a Cross-Modal Context Prompt Module, which leverages a pretrained language model to reconstruct masked contextual prompts under guidance derived from LLMs. This design effectively transfers linguistic context to the skeleton encoder for instance-level semantic grounding and improved cross-modal alignment. In addition, a Key-Part Decoupling Module is incorporated to decouple motion-relevant joint features, ensuring robust action understanding even in the absence of explicit object interactions. Extensive experiments on multiple benchmarks demonstrate that SkeletonContext achieves state-of-the-art performance under both conventional and generalized zero-shot settings, validating its effectiveness in reasoning about context and distinguishing fine-grained, visually similar actions. Our project is available at:https://github.com/NingWang2049/skeletoncontext.