Abstract
Max-margin-based early event detection is first solved by max-margin early event detector (MMED) proposed by Hoai and Torre [10]. In this study, the stochastic gradient descent mechanism is used to replace the quadratic programming solver in [10] to achieve early event detection. Three datasets are tested, including synthetic data, the extended Cohn-Kanade dataset (CK+), and Australian sign language data (ASL). The experimental results show that the proposed approach is feasible, and that the performance is comparable to that obtained in MMED.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Shahroudy, A., Ng, T., Gong, Y., Wang, G.: Deep multimodal feature analysis for action recognition in RGB+D videos. IEEE Trans. Pattern Anal. Mach. Intell. 40(5), 1045–1058 (2018)
Tran, D., Yuan, J., Forsyth, D.: Video event detection: from sub-volume localization to spatio-temporal path search. IEEE Trans. Pattern Anal. Mach. Intell. 36(2), 404–416 (2014)
Alpaydin, E.: Introduction to Machine Learning, 4th edn. MIT Press, London (2020)
Huang, D., Yao, S., Wang, Y., De La Torre, F.: Sequential max-margin event detectors. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 410–424. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_27
Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6(2), 1453–1484 (2005)
Azorin-López, J., Saval-Calvo, M., Fuster-Guilló, A., Oliver-Albert, A.: A predictive model for recognizing human behaviour based on trajectory representation. In: Proceedings of International Joint Conference on Neural Networks (IJCNN) (2014)
Wang, J., Wu, Y.: Learning maximum margin temporal warping for action recognition. In: Proceedings of ICCV 2013, pp. 2688-2695 (2013)
Su, L., Sato, Y.: Early facial expression recognition using early RankBoost. In: Proceedings of FG 2013, pp. 1–7 (2013)
Xie, L., Zhao, J., Wei, H., Zhang, K., Pang, G.: Online kernel-based structured output SVM for early expression detection. IEEE Signal Process. Lett. 26(9), 1305–1309 (2019)
Hoai, M., De la Torre, F.: Max-margin early event detectors. Int. J. Comput. Vision 107(2), 191–202 (2013). https://doi.org/10.1007/s11263-013-0683-3
Lu, S., Jin, Z.: Improved stochastic gradient descent algorithm for SVM. Int. J. Recent Eng. Sci. (IJRES) 4(4), 28–31 (2017)
Shalev-Shwartz, S., Singer, Y., Srebro, N., Cotter, A.: Pegasos: primal estimated sub-GrAdient SOlver for SVM. Math. Program 127, 3–30 (2011)
Guha, T., Ward, R.K.: Learning sparse representations for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1576–1588 (2012)
Cao, Y., et al.: Recognize human activities from partially observed videos. In: Proceedings of CVPR 2013, pp. 2658–2665 (2013)
Yang, Z.F., Hung, C.T.: Feedback max-margin early event detector. In: Proceedings of 8th International Conference on Applied System Innovation (ICASI), pp. 115–118 (2022)
Yang, Z.F., Lin, Y.C.: Reduction in number of constraints in max-margin early event detectors. Pattern Recogn. 91, 111–122 (2019)
Xu, Z., Yang, Y., Hauptmann, A.G.: A discriminative CNN video representation for event detection. In: Proceedings of CVPR 2015 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, HW., Chiu, DY., Chan, WC., Yang, ZF. (2022). Stochastic-Gradient-Descent-Based Max-Margin Early Event Detector. In: Hsieh, SY., Hung, LJ., Klasing, R., Lee, CW., Peng, SL. (eds) New Trends in Computer Technologies and Applications. ICS 2022. Communications in Computer and Information Science, vol 1723. Springer, Singapore. https://doi.org/10.1007/978-981-19-9582-8_48
Download citation
DOI: https://doi.org/10.1007/978-981-19-9582-8_48
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-9581-1
Online ISBN: 978-981-19-9582-8
eBook Packages: Computer ScienceComputer Science (R0)