The naming convention "BFH" typically refers to keypoints, which are high-resolution 2D or 3D skeletal data extracted from RGB videos. In the How2Sign dataset:
are specialized subsets that include these detailed pose estimations for use in tasks like sign language translation and human pose regression. BFH03_03.mp4
The foundational paper for this dataset, which describes its collection, annotation, and metadata, is: The naming convention "BFH" typically refers to keypoints,
Research focusing on multimodal models and longitudinal study designs. which describes its collection
Related Research at BFH (Bern University of Applied Sciences)
Specialized methods using Multi-Channel MKL for detecting characteristics in video sequences. How2Sign Dataset
If your query refers to the specifically, they produce significant research in applied machine intelligence and video analysis: