Abstract
Temporal action localization is an important task of computer vision. Though many methods have been proposed, it still remains an open question how to predict the temporal location of action segments precisely. Most state-of-the-art works train action classifiers on video segments pre-determined by action proposal. However, recent work found that a desirable model should move beyond segment-level and make dense predictions at a fine granularity in time to determine precise temporal boundaries. In this paper, we propose a Frame Segmentation Network (FSN) that places a temporal CNN on top of the 2D spatial CNNs. Spatial CNNs are responsible for abstracting semantics in spatial dimension while temporal CNN is responsible for introducing temporal context information and performing dense predictions. The proposed FSN can make dense predictions at frame-level for a video clip using both spatial and temporal context information. FSN is trained in an end-to-end manner, so the model can be optimized in spatial and temporal domain jointly. Experiment results on public dataset show that FSN achieves superior performance in both frame-level action localization and temporal action localization.
This work was supported by the National Basic Research Program of China (973) under Grant No.2014CB340303 and the National Natural Science Foundation of China under Grants U1435219, 61402507 and 61572515.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Caba Heilbron, F., Carlos Niebles, J., Ghanem, B.: Fast temporal activity proposals for efficient detection of human actions in untrimmed videos. In: CVPR (2016)
Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR (2017)
Chollet, F., et al.: Keras (2015). https://github.com/fchollet/keras
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)
Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)
Escorcia, V., Caba Heilbron, F., Niebles, J.C., Ghanem, B.: DAPs: deep action proposals for action understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768–784. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_47
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580–587 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Idrees, H., et al.: The THUMOS challenge on action recognition for videos “in the wild”. In: CVIU (2017)
Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: ACM Multimedia (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)
Oneata, D., Verbeek, J., Schmid, C.: The LEAR submission at THUMOS (2014)
Richard, A., Gall, J.: Temporal action detection using a statistical language model. In: CVPR (2016)
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: CVPR (2017)
Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: CVPR (2016)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)
Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)
Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)
Wang, L., Qiao, Y., Tang, X.: Action recognition and detection by combining motion and appearance features. In: THUMOS14 Action Recognition Challenge (2014)
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
Yang, K., Qiao, P., Li, D., Lv, S., Dou, Y.: Exploring temporal preservation networks for precise temporal action localization. In: AAAI (2018)
Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., Fei-Fei, L.: Every moment counts: dense detailed labeling of actions in complex videos. arXiv preprint arXiv:1507.05738 (2015)
Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: CVPR (2016)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
Yuan, J., Ni, B., Yang, X., Kassim, A.A.: Temporal action localization with pyramid of score distribution features. In: CVPR (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, K. et al. (2018). Frame Segmentation Networks for Temporal Action Localization. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11165. Springer, Cham. https://doi.org/10.1007/978-3-030-00767-6_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-00767-6_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00766-9
Online ISBN: 978-3-030-00767-6
eBook Packages: Computer ScienceComputer Science (R0)