Abstract
The weakly-supervised temporal action localization task aims to train a model that can accurately locate each action instance in the video using only video-level class labels. The existing methods take into account the information of different modalities (primarily RGB and Flow), and present numerous multi-modal complementary methods. RGB features are obtained by calculating appearance information, which are easy to be disrupted by the background. On the contrary, Flow features are obtained by calculating motion information, which are usually less disrupted by the background. Based on this phenomenon, we propose a Regional Similarity Consistency (RSC) constraint between these two modalities to suppress the disturbance of background in RGB features. Specifically, we calculate the regional similarity matrices of RGB and Flow features, and impose the consistency constraint through \(L_2\) loss. To verify the effectiveness of our method, we integrate the proposed RSC constraint into three recent methods. The comprehensive experimental results show that the proposed RSC constraint can boost the performance of these methods, and achieve the state-of-the-art results on the widely-used THUMOS14 and ActivityNet1.2 datasets.
H. Ren, H. Ren—Contributed equally to this work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 961–970 (2015)
Cao, M., Zhang, C., Chen, L., Shou, M.Z., Zou, Y.: Deep motion prior for weakly-supervised temporal action localization. IEEE Trans. Image Process. 31, 5203–5213 (2022)
Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 6299–6308 (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: IEEE Computer Vision and Pattern Recognition Conference, pp. 1130–1139 (2018)
Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: European Conference on Computer Vision, pp. 214–229 (2020)
He, B., Yang, X., Kang, L., Cheng, Z., Zhou, X., Shrivastava, A.: ASM-LOC: action-aware segment modeling for weakly-supervised temporal action localization. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 13925–13935 (2022)
Hong, F.T., Feng, J.C., Xu, D., Shan, Y., Zheng, W.S.: Cross-modal consensus network for weakly supervised temporal action localization. In: ACM International Conference on Multimedia, pp. 1591–1599 (2021)
Huang, L., Wang, L., Li, H.: Weakly supervised temporal action localization via representative snippet knowledge propagation. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 3272–3281 (2022)
Idrees, H., et al.: The thumos challenge on action recognition for videos in the wild. Comput. Vis. Image Underst. 155, 1–23 (2017)
Islam, A., Long, C., Radke, R.: A hybrid attention mechanism for weakly-supervised temporal action localization. In: AAAI Conference on Artificial Intelligence, vol. 35, pp. 1637–1645 (2021)
Ji, Y., Jia, X., Lu, H., Ruan, X.: Weakly-supervised temporal action localization via cross-stream collaborative learning. In: ACM International Conference on Multimedia, pp. 853–861 (2021)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)
Lee, J.T., Jain, M., Park, H., Yun, S.: Cross-attentional audio-visual fusion for weakly-supervised action localization. In: International Conference on Learning Representations (2020)
Lee, P., Uh, Y., Byun, H.: Background suppression network for weakly-supervised temporal action localization. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 11320–11327 (2020)
Lerman, P.: Fitting segmented regression models by grid search. J. Royal Stat. Soc. 29(1), 77–84 (1980)
Liu, D., Jiang, T., Wang, Y.: Completeness modeling and context separation for weakly supervised temporal action localization. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 1298–1307 (2019)
Liu, Z., Wang, L., Zhang, Q., Tang, W., Yuan, J., Zheng, N., Hua, G.: ACSNet: action-context separation network for weakly supervised temporal action localization. In: AAAI Conference on Artificial Intelligence. vol. 35, pp. 2233–2241 (2021)
Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian temporal awareness networks for action localization. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 344–353 (2019)
Luo, Z., et al.: Weakly-supervised action localization with expectation-maximization multi-instance learning. In: European Conference on Computer Vision, pp. 729–745 (2020)
Ma, F., et al.: SF-net: single-frame supervision for temporal action localization. In: European Conference on Computer Vision, pp. 420–437 (2020)
Narayan, S., Cholakkal, H., Khan, F.S., Shao, L.: 3C-Net: category count and center loss for weakly-supervised action localization. In: International Conference on Computer Vision, pp. 8679–8687 (2019)
Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 6752–6761 (2018)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Annual Conference on Neural Information Processing Systems, pp. 8026–8037 (2019)
Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: European Conference on Computer Vision, pp. 563–579 (2018)
Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 1049–1058 (2016)
Snidaro, L., Micheloni, C., Chiavedale, C.: Video security for ambient intelligence. IEEE Trans. Syst. Man Cybern. 35(1), 133–144 (2004)
Wang, L., Xiong, Y., Lin, D., Van Gool, L.: UntrimmedNets for weakly supervised action recognition and detection. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 4325–4334 (2017)
Xu, Y., et al.: Segregated temporal assembly recurrent networks for weakly supervised multiple action detection. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 9070–9078 (2019)
Yang, W., Zhang, T., Yu, X., Qi, T., Zhang, Y., Wu, F.: Uncertainty guided collaborative training for weakly supervised temporal action detection. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 53–63 (2021)
Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime tv-l 1 optical flow. In: Joint Pattern Recognition Symposium, pp. 214–223 (2007)
Zhai, Y., Wang, L., Tang, W., Zhang, Q., Yuan, J., Hua, G.: Two-stream consensus network for weakly-supervised temporal action localization. In: European Conference on Computer Vision, pp. 37–54 (2020)
Zhang, C., Cao, M., Yang, D., Chen, J., Zou, Y.: CoLA: weakly-supervised temporal action localization with snippet contrastive learning. In: IEEE Computer Vision and Pattern Recognition Conference, pp. 16010–16019 (2021)
Zhang, C., et al.: Adversarial seeded sequence growing for weakly-supervised temporal action localization. In: ACM International Conference on Multimedia, pp. 738–746 (2019)
Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: International Conference on Computer Vision, pp. 2914–2923 (2017)
Acknowledgments
This work was supported by Shanghai Municipal Science and Technology Commission with Grant No. 22dz1204900.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ren, H., Ren, H., Lu, H., Jin, C. (2023). Weakly-Supervised Temporal Action Localization with Regional Similarity Consistency. In: Dang-Nguyen, DT., et al. MultiMedia Modeling. MMM 2023. Lecture Notes in Computer Science, vol 13833. Springer, Cham. https://doi.org/10.1007/978-3-031-27077-2_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-27077-2_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27076-5
Online ISBN: 978-3-031-27077-2
eBook Packages: Computer ScienceComputer Science (R0)