The video file is a specific clip from the How2Sign dataset , a large-scale multimodal collection of American Sign Language (ASL) videos designed for computer vision research. Primary Research Paper
Research focusing on multimodal models and longitudinal study designs. BFH03_03.mp4
This paper introduces the dataset containing over 80 hours of instructional videos, including the BFH (Body-Face-Hands) keypoint annotations mentioned in your file name. You can access more information via the How2Sign Project Page . Dataset Context The video file is a specific clip from
The foundational paper for this dataset, which describes its collection, annotation, and metadata, is: which describes its collection
Other related research, such as the , also uses a BFH subset for evaluating the accuracy of 3D human meshes.
Authors: Amanda Duarte, et al. Venue: CVPR 2021