Abstract
Modelling temporal dependencies is important for accurate action detection. In this work, we develop a temporal attention unit to mine the global dependencies among features from different temporal locations. Additionally, based on the developed temporal attention unit, we propose an attention-guided boundary refinement module for revising action prediction results. Besides, we integrate the proposed module into a contemporary anchor-free detector for performing temporal action detection. To evaluate the proposed method, experiments are carried out on two large-scale temporal action detection datasets, namely THUMOS14 and ActivityNet1.3 datasets. Experimental results show that the action detection performance is significantly boosted by the proposed temporal attention module which outperforms several state-of-the-art methods.
This work was supported by the Academy of Finland for Academy Professor project EmotionAI (grants 336116, 345122), project MiGA (grant 316765), the University of Oulu & The Academy of Finland Profi 7 (grant 352788), and Ministry of Education and Culture of Finland for AI forum project. As well, the authors wish to acknowledge CSC - IT Center for Science, Finland, for computational resources.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bai, Y., Wang, Y., Tong, Y., Yang, Y., Liu, Q., Liu, J.: Boundary content graph neural network for temporal action proposal generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 121ā137. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58604-1_8
Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS-improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5561ā5569 (2017)
Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961ā970 (2015)
Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299ā6308 (2017)
Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1130ā1139 (2018)
Gao, J., Yang, Z., Chen, K., Sun, C., Nevatia, R.: Turn tap: temporal unit regression network for temporal action proposals. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3628ā3636 (2017)
Jiang, Y.G., et al.: Thumos challenge: action recognition with a large number of classes (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3320ā3329 (2021)
Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3889ā3898 (2019)
Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 988ā996 (2017)
Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 3ā21. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_1
Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 344ā353 (2019)
Qiu, H., Ma, Y., Li, Z., Liu, S., Sun, J.: BorderDet: border feature for dense object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 549ā564. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_32
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. arXiv preprint arXiv:1406.2199 (2014)
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. 4489ā4497 (2015)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998ā6008 (2017)
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794ā7803 (2018)
Xu, H., Das, A., Saenko, K.: R-c3d: Region Convolutional 3D Network for Temporal Activity detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5783ā5792 (2017)
Yang, L., Peng, H., Zhang, D., Fu, J., Han, J.: Revisiting anchor mechanisms for temporal action localization. IEEE Trans. Image Process. 29, 8535ā8548 (2020)
Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914ā2923 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shi, H., Chen, H., Zhao, G. (2023). Attention-guided Boundary Refinement onĀ Anchor-free Temporal Action Detection. In: Gade, R., Felsberg, M., KƤmƤrƤinen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13885. Springer, Cham. https://doi.org/10.1007/978-3-031-31435-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-31435-3_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31434-6
Online ISBN: 978-3-031-31435-3
eBook Packages: Computer ScienceComputer Science (R0)