Abstract
Complex events consist of various human interactions with different objects in diverse environments. The evidences needed to recognize events may occur in short time periods with variable lengths and can happen anywhere in a video. This fact prevents conventional machine learning algorithms from effectively recognizing the events. In this paper, we propose a novel method that can automatically identify the key evidences in videos for detecting complex events. Both static instances (objects) and dynamic instances (actions) are considered by sampling frames and temporal segments respectively. To compare the characteristic power of heterogeneous instances, we embed static and dynamic instances into a multiple instance learning framework via instance similarity measures, and cast the problem as an Evidence Selective Ranking (ESR) process. We impose ℓ1 norm to select key evidences while using the Infinite Push Loss Function to enforce positive videos to have higher detection scores than negative videos. The Alternating Direction Method of Multipliers (ADMM) algorithm is used to solve the optimization problem. Experiments on large-scale video datasets show that our method can improve the detection accuracy while providing the unique capability in discovering key evidences of each complex event.
Chapter PDF
Similar content being viewed by others
References
Agarwal, S.: The infinite push: A new support vector ranking algorithm that directly optimizes accuracy at the absolute top of the list. In: SDM, pp. 839–850. Society for Industrial and Applied Mathematics (2011)
Bhattacharya, S., Yu, F.X., Chang, S.F.: Minimally needed evidence for complex event recognition in unconstrained videos. In: ICMR (2014)
Cao, L., Mu, Y., Natsev, A., Chang, S.-F., Hua, G., Smith, J.R.: Scene aligned pooling for complex video recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 688–701. Springer, Heidelberg (2012)
Chen, Y., Bi, J., Wang, J.Z.: Miles: Multiple-instance learning via embedded instance selection. PAMI 28(12), 1931–1947 (2006)
Dietterich, T.G., Lathrop, R.H., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artificial Intelligence 89(1), 31–71 (1997)
Ikizler-Cinbis, N., Sclaroff, S.: Object, scene and actions: Combining multiple features for human action recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 494–507. Springer, Heidelberg (2010)
INRIA: Yael library: Optimized implementations of computationally demanding functions (2009), https://gforge.inria.fr/projects/yael/
Jiang, Y.G., Bhattacharya, S., Chang, S.F., Shah, M.: High-level event recognition in unconstrained videos. IJMIR, 1–29 (2012)
Joachims, T.: Optimizing search engines using clickthrough data. In: SIGKDD, pp. 133–142. ACM (2002)
Li, W., Yu, Q., Divakaran, A., Vasconcelos, N.: Dynamic pooling for complex event recognition. In: ICCV (2013)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)
Natarajan, P., Wu, S., Vitaladevuni, S., Zhuang, X., Tsakalidis, S., Park, U., Prasad, R.: Multimodal feature fusion for robust event detection in web videos. In: CVPR (2012)
Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 392–405. Springer, Heidelberg (2010)
Oneata, D., Verbeek, J., Schmid, C.: Action and event recognition with fisher vectors on a compact feature set. In: ICCV, pp. 1817–1824 (2013)
Over, P., Awad, G., Michel, M., Fiscus, J., Sanders, G., Kraaij, W., Smeaton, A.F., Quenot, G.: Trecvid 2013 – an overview of the goals, tasks, data, evaluation mechanisms and metrics. In: Proceedings of TRECVID 2013. NIST (2013)
Quattoni, A., Carreras, X., Collins, M., Darrell, T.: An efficient projection for l 1, ∞ , infinity regularization. In: ICML (2009)
Rakotomamonjy, A.: Sparse support vector infinite push. In: ICML (2012)
Rudin, C.: The p-norm push: A simple convex ranking algorithm that concentrates at the top of the list. JMLR 10, 2233–2271 (2009)
Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. CRCV-TR-12-01 (2012)
Tamrakar, A., Ali, S., Yu, Q., Liu, J., Javed, O., Divakaran, A., Cheng, H., Sawhney, H.: Evaluation of low-level features and their combinations for complex event detection in open source videos. In: CVPR (2012)
Tang, K., Fei-Fei, L., Koller, D.: Learning latent temporal structure for complex event detection. In: CVPR (2012)
Vahdat, A., Cannons, K., Mori, G., Oh, S., Kim, I.: Compositional models for video event detection: A multiple kernel learning latent variable approach. In: ICCV, pp. 1185–1192 (2013)
Vedaldi, A., Fulkerson, B.: Vlfeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/
Wang, H., Klaser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: CVPR (2011)
Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. IJCV, 1–20 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Lai, KT., Liu, D., Chen, MS., Chang, SF. (2014). Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8691. Springer, Cham. https://doi.org/10.1007/978-3-319-10578-9_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-10578-9_44
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10577-2
Online ISBN: 978-3-319-10578-9
eBook Packages: Computer ScienceComputer Science (R0)