Advertisement

Temporal Action Localization Based on Temporal Evolution Model and Multiple Instance Learning

  • Minglei Yang
  • Yan Song
  • Xiangbo Shu
  • Jinhui Tang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11296)

Abstract

Temporal action localization in untrimmed long videos is an important yet challenging problem. The temporal ambiguity and the intra-class variations of temporal structure of actions make existing methods far from being satisfactory. In this paper, we propose a novel framework which firstly models each action clip based on its temporal evolution, and then adopts a deep multiple instance learning (MIL) network for jointly classifying action clips and refining their temporal boundaries. The proposed network utilizes a MIL scheme to make clip-level decisions based on temporal-instance-level decisions. Besides, a temporal smoothness constraint is introduced into the multi-task loss. We evaluate our framework on THUMOS Challenge 2014 benchmark and the experimental results show that it achieves considerable improvements as compared to the state-of-the-art methods. The performance gain is especially remarkable under precise localization with high tIoU thresholds, e.g. mAP@tIoU=0.5 is improved from 31.0% to 35.0%.

Keywords

Temporal action localization Temporal evolution model Multiple instance learning 

Notes

Acknowledgments

This work was supported in part by the National Nature Science Foundation of China under Grants 61672285; the work of Xiangbo Shu is supported by the National Natural Science Foundation of China (Grant No. 61702265), Natural Science Foundation of Jiangsu Province (Grant No. BK20170856), and CCF-Tencent Open Research Fund (PI: Xiangbo Shu).

References

  1. 1.
    Cinbis, R.G., Verbeek, J., Schmid, C.: Weakly supervised object localization with multi-fold multiple instance learning. IEEE transactions on pattern analysis and machine intelligence 39(1), 189–203 (2017)Google Scholar
  2. 2.
    Dai, X., Singh, B., Zhang, G., Davis, L.S., Chen, Y.Q.: Temporal context network for activity localization in videos. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5727–5736. IEEE (2017)Google Scholar
  3. 3.
    Dietterich, T.G., Lathrop, R.H., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 9(1–2), 31–71 (1997)CrossRefGoogle Scholar
  4. 4.
    Gao, J., Yang, Z., Nevatia, R.: Cascaded boundary regression for temporal action detection. arXiv preprint arXiv:1705.01180 (2017)
  5. 5.
    Gao, J., Yang, Z., Sun, C., Chen, K., Nevatia, R.: Turn tap: Temporal unit regression network for temporal action proposals. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3648–3656. IEEE (2017)Google Scholar
  6. 6.
    Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes. http://crcv.ucf.edu/THUMOS14/ (2014)
  7. 7.
    Jolliffe, I.: Principal Component Analysis. International Encyclopedia of Statistical Science, pp. 1094–1096. Springer, New York (2011).  https://doi.org/10.1007/978-3-642-04898-2_455CrossRefGoogle Scholar
  8. 8.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  9. 9.
    Kraus, O.Z., Ba, J.L., Frey, B.J.: Classifying and segmenting microscopy images with deep multiple instance learning. Bioinformatics 32(12), i52–i59 (2016)CrossRefGoogle Scholar
  10. 10.
    Mallya, A., Lazebnik, S.: Learning models for actions and person-object interactions with transfer to question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 414–428. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_25CrossRefGoogle Scholar
  11. 11.
    Montes, A., Salvador, A., Pascual, S., Giro-i Nieto, X.: Temporal activity detection in untrimmed videos with recurrent neural networks. arXiv preprint arXiv:1608.08128 (2016)
  12. 12.
    Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.F.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1417–1426. IEEE (2017)Google Scholar
  13. 13.
    Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1049–1058 (2016)Google Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568–576 (2014)Google Scholar
  15. 15.
    Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. Center for Research in Computer Vision (CRCV), University of Central Florida (UCF) (2018)Google Scholar
  16. 16.
    Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489–4497 (2015)Google Scholar
  17. 17.
    Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3169–3176. IEEE (2011)Google Scholar
  18. 18.
    Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551–3558 (2013)Google Scholar
  19. 19.
    Wu, J., Yu, Y., Huang, C., Yu, K.: Deep multiple instance learning for image classification and auto-annotation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3460–3469 (2015)Google Scholar
  20. 20.
    Xu, H., Das, A., Saenko, K.: R-c3d: region convolutional 3D network for temporal activity detection. In: IEEE International Conference on Computer Vision (ICCV), pp. 5794–5803 (2017)Google Scholar
  21. 21.
    Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., Fei-Fei, L.: Every moment counts: dense detailed labeling of actions in complex videos. Int. J. Comput. Vis. 126(2–4), 375–389 (2018)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Yun, K., Honorio, J., Chattopadhyay, D., Berg, T.L., Samaras, D.: Two-person interaction detection using body-pose features and multiple instance learning. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 28–35. IEEE (2012)Google Scholar
  23. 23.
    Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: ICCV, October 2 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Minglei Yang
    • 1
  • Yan Song
    • 1
  • Xiangbo Shu
    • 1
  • Jinhui Tang
    • 1
  1. 1.Nanjing University of Science and TechnologyNanjingChina

Personalised recommendations