LAHands

Description

LAHands is an annotation dataset for studying hand-centered visual attention in natural scenes. It extends the existing gaze-following datasets GazeFollow, ChildPlay, and VideoAttentionTarget with Looking-at-Hands (LAHands) annotations, building on VSGaze person identities and head bounding boxes. The LAHands task determines whether a person's gaze is directed toward a particular hand or toward an object held or actively manipulated by that hand. The annotations associate gazers with candidate hands and provide labels for gazer–hand pairs, enabling the training and evaluation of models that jointly reason about gaze, hands, and hand interactions with objects.

Reference

If you use this dataset, please cite the following publication:

@inproceedings{haidar2026looking,
  title     = {Looking at Hands: A New Benchmark for Hand-Centered Gaze Understanding},
  author    = {Haidar, Nawal and Mukherjee, Anirban and Odobez, Jean-Marc},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
  year      = {2026}
}