Home

/OpenGVLab/ UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

Code Link
https://github.com/OpenGVLab/UniFormerV2
Description
UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format. Code: https://github.com/OpenGVLab/UniFormerV2
Retrieved
2022/11/22
Stars
40
TOP