Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision

• URL: http://arxiv.org/abs/2603.26646v1
• Date: Fri, 27 Mar 2026 17:49:56 GMT
• Title: Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision
• Abstract summary: EgoPoint-Thought is the first large-scale multimodal dataset dedicated to egocentric deictic visual grounding.<n>It provides rich, multi-grained annotations including hand-target bounding box pairs and dense semantic captions.<n>We propose SV-CoT, a novel baseline framework that reformulates grounding as a structured inference process.
• Score: 13.21187394955871
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following [59.53720386342017]
  We propose a unified vision-language framework that adapts foundational Vision-Language Models for scalable multi-person gaze reasoning.<n>By modeling all individuals, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning.
  arXiv  Detail & Related papers  (2026-05-26T00:08:06Z)
• Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation [52.8308168727975]
  Seg-Agent is a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning.<n>Our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement.<n>Various-LangSeg is a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks.
  arXiv  Detail & Related papers  (2026-05-13T03:36:44Z)
• Open-Vocabulary Semantic Segmentation Network Integrating Object-Level Label and Scene-Level Semantic Features for Multimodal Remote Sensing Images [29.41047187424905]
  We propose TSMNet, a text supervised multi-modal open vocabulary semantic segmentation network.<n>Unlike conventional multi-modal segmentation frameworks, TSMNet introduces a dual-branch text encoder to extract both scene-level semantic and object-level label information.<n>Results demonstrate that TSMNet achieves superior segmentation accuracy while exhibiting robust generalization capabilities.
  arXiv  Detail & Related papers  (2026-04-27T07:23:36Z)
• Perception-Aware Multimodal Spatial Reasoning from Monocular Images [57.42071289037214]
  spatial reasoning from monocular images is essential for autonomous driving.<n>Current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception.<n>We propose a perception-aware multimodal reasoning framework that equipsVLMs with explicit object-centric grounding ability.
  arXiv  Detail & Related papers  (2026-03-07T02:05:12Z)
• Beyond Language Modeling: An Exploration of Multimodal Pretraining [125.34714978184638]
  We provide empirical clarity through controlled, from-scratch pretraining experiments.<n>We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision.<n>We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language.
  arXiv  Detail & Related papers  (2026-03-03T18:58:00Z)
• Revisiting Multi-Task Visual Representation Learning [52.93947931352643]
  We introduce MTV, a principled multi-task visual pretraining framework.<n>We leverage high-capacity "expert" models to synthesize dense, structured pseudo-labels at scale.<n>Our results demonstrate that MTV achieves "best-of-both-worlds" performance.
  arXiv  Detail & Related papers  (2026-01-20T11:59:19Z)
• Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments [0.0]
  This work proposes a vision-language integration framework that unifies pre-trained visual encoders and large language models.<n>The proposed system achieves up to 18% improvement in top-1 accuracy and notable gains in semantic coherence metrics.
  arXiv  Detail & Related papers  (2025-10-29T01:16:21Z)
• Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models [57.357091028792325]
  Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment.<n>We propose a novel constrained prompt enhancement (CPE) method to improve visual-textual alignment.<n>Our approach consists of two key components: Topology-Guided Synonymous Semantic Generation (TGSSG) and Category-Agnostic Discriminative Region Selection (CADRS)
  arXiv  Detail & Related papers  (2025-08-24T15:45:22Z)
• GoViG: Goal-Conditioned Visual Navigation Instruction Generation [69.79110149746506]
  We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to autonomously generate precise and contextually coherent navigation instructions.<n>GoViG exclusively leverages raw egocentric visual data, substantially improving its adaptability to unseen and unstructured environments.
  arXiv  Detail & Related papers  (2025-08-13T07:05:17Z)
• MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models [19.241274582769037]
  Multimodal Large Language Models (MLLMs) have demonstrated significant advances across numerous vision-language tasks.<n>We introduce MUCAR, a novel benchmark designed explicitly for evaluating multimodal ambiguity resolution across multilingual and cross-modal scenarios.
  arXiv  Detail & Related papers  (2025-06-20T14:57:41Z)
• Aligning and Prompting Everything All at Once for Universal Visual Perception [79.96124061108728]
  APE is a universal visual perception model for aligning and prompting everything all at once in an image to perform diverse tasks. APE advances the convergence of detection and grounding by reformulating language-guided grounding as open-vocabulary detection. Experiments on over 160 datasets demonstrate that APE outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-04T18:59:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.