Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Video Swin Transformer

About

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. The locality of the proposed video architecture is realized by adapting the Swin Transformer designed for the image domain, while continuing to leverage the power of pre-trained image models. Our approach achieves state-of-the-art accuracy on a broad range of video recognition benchmarks, including on action recognition (84.9 top-1 accuracy on Kinetics-400 and 86.1 top-1 accuracy on Kinetics-600 with ~20x less pre-training data and ~3x smaller model size) and temporal modeling (69.6 top-1 accuracy on Something-Something v2). The code and models will be made publicly available at https://github.com/SwinTransformer/Video-Swin-Transformer.

Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, Han Hu• 2021

Related benchmarks

TaskDatasetResultRank
Action RecognitionNTU RGB+D 120 (X-set)
Accuracy92.1
661
Action RecognitionNTU RGB+D 60 (Cross-View)
Accuracy96.6
575
Action RecognitionSomething-Something v2 (val)
Top-1 Accuracy69.6
535
Action RecognitionKinetics-400
Top-1 Acc84.9
413
Action RecognitionSomething-Something v2
Top-1 Accuracy69.6
341
Action RecognitionSomething-Something v2 (test)
Top-1 Acc69.6
333
Action RecognitionUCF101 (test)--
307
Action RecognitionNTU RGB-D Cross-Subject 60
Accuracy93.4
305
Action RecognitionHMDB51 (test)--
249
Action RecognitionKinetics 400 (test)
Top-1 Accuracy84.9
245
Showing 10 of 114 rows
...

Other info

Code

Follow for update