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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Yura, Miles, Roy, Potamias, Rolandos Alexandros, Elezi, Ismail, Deng, Jiankang, Zafeiriou, Stefanos
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910081270939648
author Choi, Yura
Miles, Roy
Potamias, Rolandos Alexandros
Elezi, Ismail
Deng, Jiankang
Zafeiriou, Stefanos
author_facet Choi, Yura
Miles, Roy
Potamias, Rolandos Alexandros
Elezi, Ismail
Deng, Jiankang
Zafeiriou, Stefanos
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2603_12533
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering
Choi, Yura
Miles, Roy
Potamias, Rolandos Alexandros
Elezi, Ismail
Deng, Jiankang
Zafeiriou, Stefanos
Computer Vision and Pattern Recognition
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
title Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.12533