Research

Paper

AI LLM March 13, 2026

Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering

Authors

Yura Choi, Roy Miles, Rolandos Alexandros Potamias, Ismail Elezi, Jiankang Deng, Stefanos Zafeiriou

Abstract

Understanding and answering questions based on a user's pointing gesture is essential for next-generation egocentric AI assistants. However, current Multimodal Large Language Models (MLLMs) struggle with such tasks due to the lack of gesture-rich data and their limited ability to infer fine-grained pointing intent from egocentric video. To address this, we introduce EgoPointVQA, a dataset and benchmark for gesture-grounded egocentric question answering, comprising 4000 synthetic and 400 real-world videos across multiple deictic reasoning tasks. Built upon it, we further propose Hand Intent Tokens (HINT), which encodes tokens derived from 3D hand keypoints using an off-the-shelf reconstruction model and interleaves them with the model input to provide explicit spatial and temporal context for interpreting pointing intent. We show that our model outperforms others in different backbones and model sizes. In particular, HINT-14B achieves 68.1% accuracy, on average over 6 tasks, surpassing the state-of-the-art, InternVL3-14B, by 6.6%. To further facilitate the open research, we will release the code, model, and dataset. Project page: https://yuuraa.github.io/papers/choi2026egovqa

Metadata

arXiv ID: 2603.12533
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-13
Fetched: 2026-03-16 06:01

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.12533v1</id>\n    <title>Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering</title>\n    <updated>2026-03-13T00:23:38Z</updated>\n    <link href='https://arxiv.org/abs/2603.12533v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.12533v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Understanding and answering questions based on a user's pointing gesture is essential for next-generation egocentric AI assistants. However, current Multimodal Large Language Models (MLLMs) struggle with such tasks due to the lack of gesture-rich data and their limited ability to infer fine-grained pointing intent from egocentric video. To address this, we introduce EgoPointVQA, a dataset and benchmark for gesture-grounded egocentric question answering, comprising 4000 synthetic and 400 real-world videos across multiple deictic reasoning tasks. Built upon it, we further propose Hand Intent Tokens (HINT), which encodes tokens derived from 3D hand keypoints using an off-the-shelf reconstruction model and interleaves them with the model input to provide explicit spatial and temporal context for interpreting pointing intent. We show that our model outperforms others in different backbones and model sizes. In particular, HINT-14B achieves 68.1% accuracy, on average over 6 tasks, surpassing the state-of-the-art, InternVL3-14B, by 6.6%. To further facilitate the open research, we will release the code, model, and dataset. Project page: https://yuuraa.github.io/papers/choi2026egovqa</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-13T00:23:38Z</published>\n    <arxiv:comment>Accepted to CVPR 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Yura Choi</name>\n    </author>\n    <author>\n      <name>Roy Miles</name>\n    </author>\n    <author>\n      <name>Rolandos Alexandros Potamias</name>\n    </author>\n    <author>\n      <name>Ismail Elezi</name>\n    </author>\n    <author>\n      <name>Jiankang Deng</name>\n    </author>\n    <author>\n      <name>Stefanos Zafeiriou</name>\n    </author>\n  </entry>"
}