© The Author(s) 2024
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
, where 
is the number of frames that can span from 80 to 150 hpi. A sub-clip of 7 frames is constructed with the frame of interest as the central frame. These sub-clips are passed to a Transformer model to extract 512-d embeddings. The sequence of N embeddings is fed into a GRU network to output 
scores, where C is the number of classes. These scores are then converted to predictions using an HMM model.