Abstract
Due to the lengthy computing time for optical flow, recent works have proposed to use the correlation operation as an alternative approach to extracting motion features. Although using correlation operations shows significant improvement with negligible FLOPs, it introduces much more latency per FLOP than convolution operations and increases noticeable latency as a larger searching patch is applied. Nonetheless, shrinking the searching patch in correlation operation is doomed to degrade its performance owing to the inability to capture larger displacements. In this paper, we propose an effective and low-latency Multi-Scale Motion-Aware (MSMA) module. It uses smaller searching patches at different scales for efficiently extracting motion features from large displacements. It can be installed into and generalizes well on different CNN backbones. When installed into TSM ResNet-50, the MSMA module introduces \(\approx \) 17.6% more latency on NVIDIA Tesla V100 GPU, yet, it achieves state-of-the-art performance on Something-Something V1 & V2 and Diving-48.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anderson, C.H., Bergen, J.R., Burt, P.J., Ogden, J.M.: Pyramid methods in image processing. RCA Eng. 29(6), 33–41 (1984)
Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lučić, M., Schmid, C.: VIVIT: a video vision transformer. In: ICCV (2021)
Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML (2021)
Burt, P.J., Adelson, E.H.: The Laplacian pyramid as a compact image code. IEEE Trans. Commun. 31(4), 532–540 (1983)
Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600 (2018)
Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)
Chen, C.R., Fan, Q., Mallinar, N., Sercu, T., Feris, R.S.: Big-little net: an efficient multi-scale feature representation for visual and speech recognition. In: ICLR (2019)
Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: MARS: motion-augmented RGB stream for action recognition. In: CVPR (2019)
Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: CVPR (2020)
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)
Denton, E.L., Chintala, S., Szlam, A., Fergus, R.: Deep generative image models using a Laplacian pyramid of adversarial networks. In: NeurIPS (2015)
Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 16 words: transformers for image recognition at scale. In: ICLR (2021)
Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV (2015)
Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: CVPR (2018)
Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV (2019)
Feng, Y., Liang, Z., Liu, H.: Efficient deep learning for stereo matching with larger image patches. In: CISP-BMEI (2017)
Goyal, R., et al.: The “something something” video database for learning and evaluating visual common sense. In: ICCV (2017)
Haoqi, F., et al.: Multiscale vision transformers. In: ICCV (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local relation networks for image recognition. In: ICCV (2019)
Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646–661. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_39
Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: evolution of optical flow estimation with deep networks. In: CVPR (2017)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
Ji, S., Xu, W., Yang, M., Yu, K.: 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221–231 (2013)
Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: STM: spatiotemporal and motion encoding for action recognition. In: ICCV (2019)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM. 60, 84–90 (2017)
Kwon, H., Kim, M., Kwak, S., Cho, M.: MotionSqueeze: neural motion feature learning for video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 345–362. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_21
Kwon, H., Kim, M., Kwak, S., Cho, M.: Learning self-similarity in space and time as generalized motion for video action recognition. In: ICCV (2021)
Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: TEA: temporal excitation and aggregation for action recognition. In: CVPR (2020)
Li, Y., Li, Y., Vasconcelos, N.: RESOUND: towards action recognition without representation bias. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 520–535. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_32
Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: ICCV (2019)
Lin, T., et al.: Feature pyramid networks for object detection. In: CVPR (2017)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Liu, X., Lee, J., Jin, H.: Learning video representations from correspondence proposals. In: CVPR (2019)
Liu, Z., et al.: Teinet: towards an efficient architecture for video recognition. In: AAAI (2020)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_8
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)
Ng, J.Y., Choi, J., Neumann, J., Davis, L.S.: Actionflownet: learning motion representation for action recognition. In: WACV (2018)
Parmar, N., Ramachandran, P., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. In: NeurIPS (2019)
Piergiovanni, A.J., Ryoo, M.S.: Representation flow for action recognition. In: CVPR (2019)
Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: ICCV (2017)
Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: CVPR (2018)
Shi, X., Chen, Z., Wang, H., Yeung, D., Wong, W., Woo, W.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: NeurIPS (2015)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurIPS (2014)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Stroud, J.C., Ross, D.A., Sun, C., Deng, J., Sukthankar, R.: D3D: distilled 3d networks for video action recognition. In: WACV (2020)
Sun, D., Yang, X., Liu, M., Kautz, J.: PWC-net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)
Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)
Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.: Optical flow guided feature: a fast and robust motion representation for video action recognition. In: CVPR (2018)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)
Taylor, G.W., Fergus, R., LeCun, Y., Bregler, C.: Convolutional learning of spatio-temporal features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 140–153. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15567-3_11
Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: ICCV (2015)
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR (2018)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)
Wang, H., Tran, D., Torresani, L., Feiszli, M.: Video modeling with correlation networks. In: CVPR (2020)
Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: CVPR (2021)
Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20–36. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_2
Wang, X., Girshick, R.B., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)
Weng, J., et al.: Temporal distinct representation learning for action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 363–378. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58571-6_22
Xiang, X., Zhai, M., Zhang, R., Lv, N., El-Saddik, A.: Optical flow estimation using spatial-channel combinational attention-based pyramid networks. In: ICIP (2019)
Xu, J., Ranftl, R., Koltun, V.: Accurate optical flow via direct cost volume processing. In: CVPR (2017)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: NeurIPS (2014)
Yun, S., Han, D., Chun, S., Oh, S.J., Yoo, Y., Choe, J.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: ICCV (2019)
Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74936-3_22
Zbontar, J., LeCun, Y.: Stereo matching by training a convolutional neural network to compare image patches. J. Mach. Learn. Res. 17, 2287–2318 (2016)
Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: CVPR (2021)
Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: ICLR (2018)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)
Zhao, Y., Xiong, Y., Lin, D.: Recognize actions by disentangling components of dynamics. In: CVPR (2018)
Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: AAAI (2020)
Zhu, Y., Lan, Z., Newsam, S.D., Hauptmann, A.G.: Hidden two-stream convolutional networks for action recognition. In: ACCV (2018)
Zolfaghari, M., Singh, K., Brox, T.: ECO: efficient convolutional network for online video understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 713–730. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_43
Acknowledgments
This research is co-sponsored by ITRI and Ministry of Science and Technology (MoST). This work is also financially supported by “Center for Open Intelligent Connectivity” of “Higher Education Sprout Project” of NYCU and MOE, Taiwan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Peng, HW., Tseng, YC. (2023). Multi-scale Motion-Aware Module for Video Action Recognition. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13806. Springer, Cham. https://doi.org/10.1007/978-3-031-25075-0_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-25075-0_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25074-3
Online ISBN: 978-3-031-25075-0
eBook Packages: Computer ScienceComputer Science (R0)