Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering
This addresses a key limitation for next-generation AI assistants in understanding user gestures, though it appears incremental as it builds on existing MLLM frameworks with a novel dataset and token encoding.
The paper tackles the problem of gesture-based question answering in egocentric videos, where current models struggle with interpreting pointing gestures, and introduces the EgoPointVQA dataset and HINT method, achieving 68.1% accuracy and surpassing the state-of-the-art by 6.6%.
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