Abstract
In this paper, we propose an algorithm that learns from uncertain data and exploits related videos for the problem of event detection; related videos are those that are closely associated, though not fully depicting the event of interest. In particular, two extensions of the linear SVM with Gaussian Sample Uncertainty are presented, which (a) lead to non-linear decision boundaries and (b) incorporate related class samples in the optimization problem. The resulting learning methods are especially useful in problems where only a limited number of positive and related training observations are provided, e.g., for the 10Ex subtask of TRECVID MED, where only ten positive and five related samples are provided for the training of a complex event detector. Experimental results on the TRECVID MED 2014 dataset verify the effectiveness of the proposed methods.
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
Notes
- 1.
\(\mathbb {S}_{++}^{n}\) denotes the convex cone of all symmetric positive definite \(n\times n\) matrices with entries in \(\mathbb {R}\). \(I_n\) denotes the identity matrix of order n.
- 2.
Convexity can be shown using Theorem 2 proved in [27].
- 3.
Their derivation is omitted, as it is technical but straightforward.
References
Bhattacharyya, C., Pannagadatta, K., Smola, A.J.: A second order cone programming formulation for classifying missing data. In: Neural Information Processing Systems (NIPS), pp. 153–160 (2005)
Bolles, R., Burns, B., Herson, J., et al.: The 2014 SESAME multimedia event detection and recounting system. In: Proceedings of the TRECVID Workshop (2014)
Broyden, C.G.: The convergence of a class of double-rank minimization algorithms 1. general considerations. IMA J. Appl. Math. 6(1), 76–90 (1970)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011). http://www.csie.ntu.edu.tw/cjlin/libsvm
Cheng, H., Liu, J., Chakraborty, I., Chen, G., Liu, Q., Elhoseiny, M., Gan, G., Divakaran, A., Sawhney, H., Allan, J., Foley, J., Shah, M., Dehghan, A., Witbrock, M., Curtis, J.: SRI-Sarnoff AURORA system at TRECVID 2014 multimedia event detection and recounting. In: Proceedings of the TRECVID Workshop (2014)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition CVPR 2009, pp. 248–255. IEEE (2009)
Douze, M., Oneata, D., Paulin, M., Leray, C., Chesneau, N., Potapov, D., Verbeek, J., Alahari, K., Harchaoui, Z., Lamel, L., Gauvain, J.L., Schmidt, C.A., Schmid, C.: The INRIA-LIM-VocR and AXES submissions to TRECVID 2014 multimedia event detection (2014)
Gkalelis, N., Markatopoulou, F., Moumtzidou, A., Galanopoulos, D., Avgerinakis, K., Pittaras, N., Vrochidis, S., Mezaris, V., Kompatsiaris, I., Patras, I.: ITI-CERTH participation to TRECVID 2014. In: Proceedings of the TRECVID Workshop (2014)
Gkalelis, N., Mezaris, V.: Video event detection using generalized subclass discriminant analysis and linear support vector machines. In: Proceedings of International Conference on Multimedia Retrieval, p. 25. ACM (2014)
Golub, G.H., Van Loan, C.F.: Matrix Comput., vol. 3. JHU Press, Baltimore (2012)
Guangnan, Y., Dong, L., Shih-Fu, C., Ruslan, S., Vlad, M., Larry, D., Abhinav, G., Ismail, H., Sadiye, G., Ashutosh, M.: BBN VISER TRECVID 2014 multimedia event detection and multimedia event recounting systems. In: Proceedings of the TRECVID Workshop (2014)
Habibian, A., van de Sande, K.E., Snoek, C.G.: Recommendations for video event recognition using concept vocabularies. In: Proceedings of the 3rd ACM Conference on International Conference on Multimedia Retrieval, pp. 89–96. ACM (2013)
Habibian, A., Mensink, T., Snoek, C.G.: Videostory: A new multimedia embedding for few-example recognition and translation of events. In: Proceedings of the ACM International Conference on Multimedia, pp. 17–26. ACM (2014)
Jiang, L., Meng, D., Mitamura, T., Hauptmann, A.G.: Easy samples first: self-paced reranking for zero-example multimedia search. In: Proceedings of the ACM International Conference on Multimedia, pp. 547–556. ACM (2014)
Jiang, L., Yu, S.I., Meng, D., Mitamura, T., Hauptmann, A.G.: Bridging the ultimate semantic gap: a semantic search engine for internet videos. In: ACM International Conference on Multimedia Retrieval (2015)
Jiang, Y.G., Bhattacharya, S., Chang, S.F., Shah, M.: High-level event recognition in unconstrained videos. Int. J. Multimedia Inf. Retrieval 2(2), 73–101 (2013)
Kimeldorf, G., Wahba, G.: Some results on Tchebycheffian spline functions. J. Math. Anal. Appl. 33(1), 82–95 (1971)
Lanckriet, G.R., Ghaoui, L.E., Bhattacharyya, C., Jordan, M.I.: A robust minimax approach to classification. J. Mach. Learn. Res. 3, 555–582 (2003)
Liang, Z., Inoue, N., Shinoda, K.: Event Detection by Velocity Pyramid. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O’Connor, N. (eds.) MMM 2014, Part I. LNCS, vol. 8325, pp. 353–364. Springer, Heidelberg (2014)
Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Mathematical prog. 45(1–3), 503–528 (1989)
Mazloom, M., Habibian, A., Liu, D., Snoek, C.G., Chang, S.F.: Encoding concept prototypes for video event detection and summarization (2015)
Over, P., Awad, G., Michel, M., Fiscus, J., Sanders, G., Kraaij, W., Smeaton, A.F., Quenot, G.: An overview of the goals, tasks, data, evaluation mechanisms and metrics. In: Proceedings of the TRECVID 2014. NIST, USA (2014)
Robertson, S.: A new interpretation of average precision. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 689–690. ACM (2008)
Schölkopf, B., Herbrich, R., Smola, A.J.: A generalized representer theorem. In: Helmbold, D.P., Williamson, B. (eds.) COLT 2001 and EuroCOLT 2001. LNCS (LNAI), vol. 2111, pp. 416–426. Springer, Heidelberg (2001)
Shivaswamy, P.K., Bhattacharyya, C., Smola, A.J.: Second order cone programming approaches for handling missing and uncertain data. J. Mach. Learn. Res. 7, 1283–1314 (2006)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint arXiv:1409.1556
Tzelepis, C., Mezaris, V., Patras, I.: Linear maximum margin classifier for learning from uncertain data (2015). arXiv preprint arXiv:1504.03892
Tzelepis, C., Gkalelis, N., Mezaris, V., Kompatsiaris, I.: Improving event detection using related videos and relevance degree support vector machines. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 673–676. ACM (2013)
Xu, H., Caramanis, C., Mannor, S.: Robustness and regularization of support vector machines. J. Mach. Learn. Res. 10, 1485–1510 (2009)
Xu, H., Mannor, S.: Robustness and generalization. Mach. Learn. 86(3), 391–423 (2012)
Yu, S.I., Jiang, L., Mao, Z., Chang, X., Du, X., Gan, C., Lan, Z., Xu, Z., Li, X., Cai, Y., et al.: Informedia at TRECVID 2014 MED and MER. In: NIST TRECVID Video Retrieval Evaluation Workshop (2014)
Acknowledgment
This work was supported by the European Commission under contract FP7-600826 ForgetIT.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Tzelepis, C., Mezaris, V., Patras, I. (2016). Video Event Detection Using Kernel Support Vector Machine with Isotropic Gaussian Sample Uncertainty (KSVM-iGSU). In: Tian, Q., Sebe, N., Qi, GJ., Huet, B., Hong, R., Liu, X. (eds) MultiMedia Modeling. MMM 2016. Lecture Notes in Computer Science(), vol 9516. Springer, Cham. https://doi.org/10.1007/978-3-319-27671-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-27671-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27670-0
Online ISBN: 978-3-319-27671-7
eBook Packages: Computer ScienceComputer Science (R0)