Advertisement

MotionSqueeze: Neural Motion Feature Learning for Video Understanding

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12361)

Abstract

Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information typically using optical flows extracted by a separate off-the-shelf method. As the frame-by-frame optical flows require heavy computation, incorporating motion information has remained a major computational bottleneck for video understanding. In this work, we replace external and heavy computation of optical flows with internal and light-weight learning of motion features. We propose a trainable neural module, dubbed MotionSqueeze, for effective motion feature extraction. Inserted in the middle of any neural network, it learns to establish correspondences across frames and convert them into motion features, which are readily fed to the next downstream layer for better prediction. We demonstrate that the proposed method provides a significant gain on four standard benchmarks for action recognition with only a small amount of additional cost, outperforming the state of the art on Something-Something-V1 & V2 datasets.

Keywords

Video understanding Action recognition Motion feature learning Efficient video processing 

Notes

Acknowledgements

This work is supported by Samsung Advanced Institute of Technology (SAIT), and also by Basic Science Research Program (NRF-2017R1E1A1A010 77999, NRF-2018R1C1B6001223) and Next-Generation Information Computing Development Program (NRF-2017M3C4A7069369) through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT.

Supplementary material

504471_1_En_21_MOESM1_ESM.pdf (13.3 mb)
Supplementary material 1 (pdf 13642 KB)

References

  1. 1.
    Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vision (IJCV) 92(1), 1–31 (2011)CrossRefGoogle Scholar
  2. 2.
    Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  3. 3.
    Chen, Y., Kalantidis, Y., Li, J., Yan, S., Feng, J.: Multi-fiber networks for video recognition. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)Google Scholar
  4. 4.
    Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  5. 5.
    Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)Google Scholar
  6. 6.
    Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2015)Google Scholar
  7. 7.
    Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  8. 8.
    Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: Proceedings of Neural Information Processing Systems (NeurIPS) (2016)Google Scholar
  9. 9.
    Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)Google Scholar
  10. 10.
    Goyal, R., et al.: The "something something" video database for learning and evaluating visual common sense. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  11. 11.
    Han, K., et al.: Scnet: learning semantic correspondence. In: Proceeding of IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  12. 12.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)Google Scholar
  13. 13.
    Honari, S., Molchanov, P., Tyree, S., Vincent, P., Pal, C., Kautz, J.: Improving landmark localization with semi-supervised learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  14. 14.
    Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint arXiv:1704.04861
  15. 15.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv preprint arXiv:1502.03167
  16. 16.
    Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: Stm: spatiotemporal and motion encoding for action recognition. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)Google Scholar
  17. 17.
    Kay, W., et al.: The kinetics human action video dataset (2017). arXiv preprint arXiv:1705.06950
  18. 18.
    Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2011)Google Scholar
  19. 19.
    Lee, J., Kim, D., Ponce, J., Ham, B.: SFNET: learning object-aware semantic correspondence. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  20. 20.
    Lee, M., Lee, S., Son, S., Park, G., Kwak, N.: Motion feature network: fixed motion filter for action recognition. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)Google Scholar
  21. 21.
    Lin, J., Gan, C., Han, S.: Tsm: temporal shift module for efficient video understanding. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)Google Scholar
  22. 22.
    Liu, X., Lee, J.Y., Jin, H.: Learning video representations from correspondence proposals. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  23. 23.
    Martinez, B., Modolo, D., Xiong, Y., Tighe, J.: Action recognition with spatial-temporal discriminative filter banks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)Google Scholar
  24. 24.
    Min, J., Lee, J., Ponce, J., Cho, M.: Hyperpixel flow: semantic correspondence with multi-layer neural features. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)Google Scholar
  25. 25.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of International Conference on Machine Learning (ICML) (2010)Google Scholar
  26. 26.
    Ng, J.Y.H., Choi, J., Neumann, J., Davis, L.S.: Actionflownet: learning motion representation for action recognition. In: Proceedings of Winter Conference on Applications of Computer Vision (WACV) (2018)Google Scholar
  27. 27.
    Piergiovanni, A., Ryoo, M.S.: Representation flow for action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  28. 28.
    Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  29. 29.
    Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  30. 30.
    Sevilla-Lara, L., Liao, Y., Güney, F., Jampani, V., Geiger, A., Black, M.J.: On the integration of optical flow and action recognition. In: Proceedings of German Conference on Pattern Recognition (GCPR) (2018)Google Scholar
  31. 31.
    Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of Neural Information Processing Systems (NeurIPS) (2014)Google Scholar
  32. 32.
    Stroud, J., Ross, D., Sun, C., Deng, J., Sukthankar, R.: D3D: distilled 3D networks for video action recognition. In: Proceedings of Winter Conference on Applications of Computer Vision (WACV) (2020)Google Scholar
  33. 33.
    Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: CNNs for optical flow using pyramid, warping, and cost volume. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  34. 34.
    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: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  35. 35.
    Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2015)Google Scholar
  36. 36.
    Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)Google Scholar
  37. 37.
    Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  38. 38.
    Wang, H., Kläser, A., Schmid, C., Cheng-Lin, L.: Action recognition by dense trajectories. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011)Google Scholar
  39. 39.
    Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)Google Scholar
  40. 40.
    Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Proceedings of European Conference on Computer Vision (ECCV) (2016)Google Scholar
  41. 41.
    Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  42. 42.
    Wang, X., Gupta, A.: Videos as space-time region graphs. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 399–417 (2018)Google Scholar
  43. 43.
    Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)Google Scholar
  44. 44.
    Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime tv-l 1 optical flow. In: Hamprecht, Fred A., Schnörr, Christoph, Jähne, Bernd (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-74936-3_22CrossRefGoogle Scholar
  45. 45.
    Zhao, Y., Xiong, Y., Lin, D.: Recognize actions by disentangling components of dynamics. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  46. 46.
    Zhao, Y., Xiong, Y., Lin, D.: Trajectory convolution for action recognition. In: Proceedings of Neural Information Processing Systems (NeurIPS) (2018)Google Scholar
  47. 47.
    Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)Google Scholar
  48. 48.
    Zolfaghari, M., Singh, K., Brox, T.: Eco: efficient convolutional network for online video understanding. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.POSTECHPohang University of Science and TechnologyPohangKorea
  2. 2.NPRCThe Neural Processing Research CenterSeoulKorea

Personalised recommendations