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

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

Figures (21)

• Figure 1: Illustration of EgoPointVQA.Left: EgoPointVQA includes questions with deictic pronouns requiring gesture understanding, either identifying single pointed objects (top) or tracking multiple references across frames (bottom). Right: State-of-the-art models, including GPT-4o gpt4o and Qwen3-VL-32B qwen3technicalreport, fail to resolve the question with pointing gestures, incorrectly stating the two pots have different colors despite both being black. Zoomed circles highlight the pointed objects.
• Figure 2: Task taxonomy and examples from EgoPointVQA.EgoPointVQA includes six subsets of questions regarding the properties of a pointed object. Each example shows egocentric video frames and a question using deictic references. Tasks include reference (object identification), counting (number of same objects), spatial (location and relative depth), temporal (order of multiple gestures), attribute (object properties), and feedback (object function). All questions require resolving deictic references through visual grounding of pointing gestures. The pointed objects are highlighted with red circles for visualization purposes.
• Figure 3: Visualization of synthetic videos in EgoPointVQA. Our synthetic data covers diverse indoor scenes with various lighting conditions.
• Figure 4: EgoPointVQA generation pipeline. From a mixture of simulated and real egocentric videos, we automatically generate multiple-choice question answer pairs referring to the pointed objects in the video. The questions are made deictic so that the model should visually understand the pointing gesture to answer.
• Figure 5: EgoPointVQA statistics. Distribution of task types (charts) and common object word clouds for the (Left) training set (N=18073) and the (Right) test set (N=672).