video-transformers | This is the official implementation of the XViT paper

video-transformers is a Python library. video-transformers has no bugs, it has no vulnerabilities, it has a Permissive License and it has low support. However video-transformers build file is not available. You can download it from GitHub.

This is the official implementation of the XViT paper:. In XViT, we introduce a novel Video Transformer model the complexity of which scales linearly with the number of frames in the video sequence and hence induces no overhead compared to an image-based Transformer model. To achieve this, our model makes two approximations to the full space-time attention used in Video Transformers: (a) It restricts time attention to a local temporal window and capitalizes on the Transformer's depth to obtain full temporal coverage of the video sequence. (b) It uses efficient space-time mixing to attend jointly spatial and temporal locations without inducing any additional cost on top of a spatial-only attention model. We also show how to integrate 2 very lightweight mechanisms for global temporal-only attention which provide additional accuracy improvements at minimal computational cost. Our model produces very high recognition accuracy on the most popular video recognition datasets while at the same time is significantly more efficient than other Video Transformer models.