[Paper] PSp-Transformer: A Transformer with Data-level Probabilistic Sparsity for Action Representation Learning-Reference-Cited by-同舟云学术

[Paper] PSp-Transformer: A Transformer with Data-level Probabilistic Sparsity for Action Representation Learning

Published:2024 Issue:1 Volume:12 Page:123-132
ISSN:2186-7364
Container-title:ITE Transactions on Media Technology and Applications
language:en
Short-container-title:MTA

Author:

Zhou Jiaxin¹,Komuro Takashi¹

Affiliation:

1. Graduate School of Science and Engineering, Saitama University

Publisher

Institute of Image Information and Television Engineers

Subject

Computer Graphics and Computer-Aided Design,Media Technology,Signal Processing

Link

https://www.jstage.jst.go.jp/article/mta/12/1/12_123/_pdf

Reference47 articles.

1. 1) J.Carreira and A.Zisserman : “Quo vadis, action recognition? a new model and the kinetics dataset”, Proceedings of the IEEE onference on computer vision and pattern Recognition, pp.6299-6308 (2017)

2. 2) K.He, X.Zhang, S.Ren and J.Sun : “Deep residual learning for image recognition”, Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770-778 (2016)

3. 3) X.Wang, R.Girshick, A.Gupta, K.He : “Non-local neural networks”, Proceedings of the IEEE conference on computer vision and pattern recognition, pp.7794-7803 (2018)

4. 4) A.Vaswani, N.Shazeer, N.Parmar, J.Uszkoreit, L.Jones, A.Gomez, L.Kaiser and I.Polosukhin : “Attention is all you need”, Proceedings of the advances in neural information processing systems, vol.30 (2017)

5. 5) A.Dosovitskiy, L.Beyer, A.Kolesnikov, D.Weissenborn, X.Zhai, T.Unterthiner, M.Dehghani, M.Minderer, G.Heigold, S.Gelly, J.Uszkoreit and N.Houlsby : “An image is worth 16x16 words: transformers for image recognition at scale”, Proceedings of the international conference on learning representations (2021)