Abstract
Due to the advantages in extracting the long-range dependencies, self-attention based transformers are widely used to model the spatio-temporal features for video classification, which achieves competitive performance compared to 3D CNNs. To reduce the computational complexity, existing methods divide the frames into patches and factorize the spatial and temporal domains. However, most existing methods globally connect the patches at the same position in different frames to extract the temporal features, and ignore the patch motion due to video objects moving, which might hurt the performance of transformers. This paper proposes a novel architecture called Motion Enhanced Video Transformer (MEViT) for video classification, which captures patch motion information via a new module named Motion self-attention. Different from existing self-attention operation on the temporal dimension, motion self-attention globally connects the query patch and the neighborhood patches in other frames along the temporal dimension when modelling the patch temporal dependencies. Furthermore, this paper also discusses how attention blocks are stacked and how to use the spatio-temporal feature to get the classification feature. Experiments on popular public datasets (including Kinetics-400/600 and Something-Something-v2) demonstrate that our MEViT model outperforms existing dominant video transformer models.
This work was supported in part by Next Generation AI Project of China No. 2018AAA0100602, in part to Dr. Liansheng Zhuang by NSFC under contract No. U20B2070 and No. 61976199, and in part to Dr. Houqiang Li by NSFC under contract No. 61836011. Li Li is with the School of data science.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lučić, M., Schmid, C.: ViViT: a video vision transformer (2021)
Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? (2021)
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13
Chen, C.F., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification (2021)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 16 words: transformers for image recognition at scale (2020)
Fan, Q., Chen, C.F.R., Kuehne, H., Pistoia, M., Cox, D.: More is less: learning efficient video representations by big-little network and depthwise temporal aggregation. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’ Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019). https://proceedings.neurips.cc/paper/2019/file/3d779cae2d46cf6a8a99a35ba4167977-Paper.pdf
Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020
Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019
Goyal, R., et al.: The “something something” video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5842–5850 (2017)
Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers (2021)
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1725–1732 (2014)
Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25. Curran Associates, Inc. (2012). https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
Laptev, I.: On space-time interest points. Int. J. Comput. Vision 64(2), 107–123 (2005)
Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: Tea: temporal excitation and aggregation for action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 909–918 (2020)
Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019
Qiu, Z., Yao, T., Ngo, C.W., Tian, X., Mei, T.: Learning spatio-temporal representation with local and global diffusion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jégou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347–10357. PMLR (2021)
Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., Jégou, H.: Going deeper with image transformers. arXiv preprint arXiv:2103.17239 (2021)
Tran, D., Wang, H., Torresani, L., Feiszl, M.: Video classification with channel-separated convolutional networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019
Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vision 103(1), 60–79 (2013)
Wang, H., Tran, D., Torresani, L., Feiszli, M.: Video modeling with correlation networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020
Wang, X., et al.: AttentionNAS: spatiotemporal attention cell search for video classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 449–465. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_27
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794–7803 (2018)
Wu, H., et al.: CVT: introducing convolutions to vision transformers (2021)
Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), September 2018
Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 803–818 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, L., Zhuang, L. (2022). MEViT: Motion Enhanced Video Transformer for Video Classification. In: Þór Jónsson, B., et al. MultiMedia Modeling. MMM 2022. Lecture Notes in Computer Science, vol 13142. Springer, Cham. https://doi.org/10.1007/978-3-030-98355-0_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-98355-0_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98354-3
Online ISBN: 978-3-030-98355-0
eBook Packages: Computer ScienceComputer Science (R0)