Abstract
In this paper, we focus on human action detection for untrim-med long videos. We propose an effective action detection system aiming at solving two difficulties in existing works. Firstly, we propose to take into account the temporal context information in model learning to tackle with the problem of high-quality proposal generation. Secondly, we propose to utilize the posterior probability of proposal length to adjust the selection criterion of action proposals. This can effectively encourage the proposals with reasonable lengths and suppress the high-classification-score proposals with unreasonable lengths. We test our method on the THUMOS14 Dataset and the experiment results show that our action detection system improve the performance by about 4% compared with the state-of-art methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Oneata, D., Verbeek, J., Schmid, C.: Action and event recognition with fisher vectors on a compact feature set. In: IEEE International Conference on Computer Vision, pp. 1817–1824 (2013)
Du, T., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision, pp. 4489–4497 (2016)
Van Gemert, J.C., Jain, M., Gati, E., Snoek, C.G.M.: APT: action localization proposals from dense trajectories. In: BMVC (2015)
Gkioxari, G., Malik, J.: Finding action tubes, pp. 759–768 (2014)
Heilbron, F.C., Niebles, J.C., Ghanem, B.: Fast temporal activity proposals for efficient detection of human actions in untrimmed videos. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1914–1923 (2016)
Jiang, Y.G., Liu, J., Roshan Zamir, A., Toderici, G., Laptev, I., Shah, M., Sukthankar, R.: Thumos challenge: action recognition with a large number of classes (2014). http://crcv.ucf.edu/THUMOS14/
Karaman, S., Seidenari, L., Bimbo, A.D.: Fast saliency based pooling of fisher encoded dense trajectories. In: European Conference on Computer Vision (2014)
Klaser, A., Schmid, C.: Action recognition by dense trajectories. In: Computer Vision and Pattern Recognition, pp. 3169–3176 (2011)
Laptev, I., Lindeberg, T.: On space-time interest points. Int. J. Comput. Vis. 64(2–3), 107–123 (2005)
Mettes, P., Van Gemert, J.C., Cappallo, S., Mensink, T., Snoek, C.G.M.: Bag-of-fragments: selecting and encoding video fragments for event detection and recounting. In: ACM on International Conference on Multimedia Retrieval, pp. 427–434 (2015)
Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs, pp. 1049–1058 (2016)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 1(4), 568–576 (2014)
Singh, G., Cuzzolin, F.: Untrimmed video classification for activity detection: submission to activitynet challenge (2016)
Wang, L., Qiao, Y., Tang, X.: Action recognition and detection by combining motion and appearance features (2014). http://crcv.ucf.edu/THUMOS14/papers/CUHK&SIAT.pdf
Yeung, S., Russakovsky, O., Mori, G., Li, F.F.: End-to-end learning of action detection from frame glimpses in videos. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2678–2687 (2016)
Yu, G., Yuan, J.: Fast action proposals for human action detection and search. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1302–1311 (2015)
Yuan, J., Ni, B., Yang, X., Kassim, A.A.: Temporal action localization with pyramid of score distribution features. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3093–3102 (2016)
Yuan, J., Liu, Z., Wu, Y.: Discriminative subvolume search for efficient action detection. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 2442–2449 (2009)
Acknowledgments
This work was supported in part by the 973 Program under Grant 2014CB347600; in part by the National Nature Science Foundation of China under Grants 61672285.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Liu, X., Song, Y., Tang, J. (2018). Effective Action Detection Using Temporal Context and Posterior Probability of Length. In: Schoeffmann, K., et al. MultiMedia Modeling. MMM 2018. Lecture Notes in Computer Science(), vol 10705. Springer, Cham. https://doi.org/10.1007/978-3-319-73600-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-73600-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-73599-3
Online ISBN: 978-3-319-73600-6
eBook Packages: Computer ScienceComputer Science (R0)