Multi-view Action Recognition via Directed Gromov-Wasserstein Discrepancy

arXiv:2405.01337v1 Announce Type: new
Abstract: Action recognition has become one of the popular research topics in computer vision. There are various methods based on Convolutional Networks and self-attention mechanisms as Transformers to solve both spatial and temporal dimensions problems of action recognition tasks that achieve competitive performances. However, these methods lack a guarantee of the correctness of the action subject that the models give attention to, i.e., how to ensure an action recognition model focuses on the proper action subject …

abstract action recognition arxiv attention attention mechanisms become computer computer vision convolutional cs.cv dimensions however networks performances popular recognition research self-attention solve spatial tasks temporal topics transformers type via view vision