Follow
MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition. (arXiv:2108.09322v1 [cs.CV]) http://arxiv.org/abs/2108.09322
MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition. (arXiv:2108.09322v1 [cs.CV]) http://arxiv.org/abs/2108.09322