Traditional Visual Grounding (VG) predominantly relies on textual descriptions to localize objects, a paradigm that inherently struggles with linguistic ambiguity and often ignores non-verbal deictic cues prevalent in real-world interactions. In natural egocentric engagements, hand-pointing combined with speech forms the most intuitive referring mechanism. To bridge this gap, we introduce EgoPoint-Ground, the first large-scale multimodal dataset dedicated to egocentric deictic visual grounding. Comprising over \textbf{15k} interactive samples in complex scenes, the dataset provides rich, multi-grained annotations including hand-target bounding box pairs and dense semantic captions. We establish a comprehensive benchmark for hand-pointing referring expression resolution, evaluating a wide spectrum of mainstream Multimodal Large Language Models (MLLMs) and state-of-the-art VG architectures. Furthermore, we propose SV-CoT, a novel baseline framework that reformulates grounding as a structured inference process, synergizing gestural and linguistic cues through a Visual Chain-of-Thought paradigm. Extensive experiments demonstrate that SV-CoT achieves an $\textbf{11.7\%}$ absolute improvement over existing methods, effectively mitigating semantic ambiguity and advancing the capability of agents to comprehend multimodal physical intents. The dataset and code will be made publicly available.

翻译：传统视觉定位(Visual Grounding, VG)主要依赖文本描述来定位目标，这一范式本质上难以处理语言歧义，且往往忽略现实交互中普遍存在的非语言指向线索。在自然的自我中心互动中，手势指向与语音结合构成了最直观的指代机制。为弥补这一空白，我们提出了EgoPoint-Ground——首个专门用于自我中心指向视觉定位的大规模多模态数据集。该数据集包含复杂场景中超过**1.5万**个交互样本，提供丰富且多粒度的标注，包括手-目标边界框配对和密集语义描述。我们为手势指向指代表达消解建立了全面基准，评估了主流多模态大语言模型(MLLMs)及先进VG架构的广泛范围。此外，我们提出了SV-CoT，一种新颖的基线框架，将定位重新表述为结构化推理过程，通过视觉思维链(Visual Chain-of-Thought)范式协同手势与语言线索。大量实验表明，SV-CoT相比现有方法实现了**11.7%**的绝对提升，有效缓解了语义歧义，并提升了智能体理解多模态物理意图的能力。数据集和代码将公开提供。