Update README.md

README.md

@@ -13,7 +13,7 @@ datasets:
 # UniFormer (video model) 
 
 UniFormer models are trained on [Kinetics](https://deepmind.com/research/open-source/kinetics) and [Something-Something](https://20bn.com/datasets/something-something) at resolution 224x224. 
-It was introduced in the paper [https://paperswithcode.com/paper/uniformer-unified-transformer-for-efficient](https://arxiv.org/abs/2201.04676) by Li et al,
+It was introduced in the paper [UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning](https://arxiv.org/abs/2201.04676) by Li et al,
 and first released in [this repository](https://github.com/Sense-X/UniFormer).