Understanding Human Hands in Contact at Internet Scale
This work addresses the need for systems that can learn from vast video data to understand human hand interactions, though it is incremental as it builds on existing hand analysis methods.
The paper tackles the problem of extracting detailed hand state information from internet videos by inferring hand location, side, contact state, and object bounding boxes, resulting in a model trained on a large-scale dataset of 131 days of footage and 100K annotated frames.
Hands are the central means by which humans manipulate their world and being able to reliably extract hand state information from Internet videos of humans engaged in their hands has the potential to pave the way to systems that can learn from petabytes of video data. This paper proposes steps towards this by inferring a rich representation of hands engaged in interaction method that includes: hand location, side, contact state, and a box around the object in contact. To support this effort, we gather a large-scale dataset of hands in contact with objects consisting of 131 days of footage as well as a 100K annotated hand-contact video frame dataset. The learned model on this dataset can serve as a foundation for hand-contact understanding in videos. We quantitatively evaluate it both on its own and in service of predicting and learning from 3D meshes of human hands.