Abstract
Despite the numerous methods to recognize human actions in a video, few are designed for videos containing more than one action over a certain time period. Moreover, existing multiple action recognition methods adopt windowed sequence search strategy. Windowed sequence searching requires an exhaustive trial of window length yielding intensive computation. This work presents a frame-based strategy, capable of searching for maximum score subsequences that correspond to actions. Therefore, start and ending times of all actions are located, and action categories are identified as well. Moreover, contrast mutual information is proposed as a new score function to increase recognition accuracy. Experimental results indicate that the proposed method locates and recognizes multiple actions in a video accurately, even for the conventional single action classification problem.
Similar content being viewed by others
References
Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: a review. ACM Comput. Surv. 43(3):16:1–16:43 (2011)
Roppe, R.: A survey on vision-based human action recognition. Image Comput. 28(3), 976–990 (2010)
Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2–3), 107–123 (2005)
Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: Proceedings 2rd International Workshop Visual Surveillance Performance Evaluation Tracking Surveillance, Beijing, China, Oct. 15–16, pp. 65–72 (2005)
Wang, H., Ullah, M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: Presented at British Machine Vision Conference, London, England, Sept. 7–10, (2009)
Kläser, A., Marszałek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: Presented at British Machine Vision Conference. Leeds, UK, Sept. 1–4, (2008)
Wang, Y., Mori, G.: Learning a discriminative hidden part model for human action recognition. In: Proceedings 22nd Annual Conference on Neural Information Processing Systems, Vancouver, Canada, Dec. 8–11, pp. 1721–1728 (2008)
Jhuang, H., Serre, T., Wolf, L., Poggio, T.: A biologically inspired system for action recognition. In: Proceedings International Conference Computer Vision, Rio de Janeiro, Brazil, Oct. 14–21, pp. 1–8 (2007)
Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings 15th ACM International Conference Multimedia, Bavaria, Germany, Sept. 24–29, pp. 357–360 (2007)
Laptev, I., Lindeberg, T.: Local descriptors for spatio-temporal recognition. In: Proceedings International Workshop on Spatial Coherence for Visual Motion Analysis, Prague, Czech republic, May 15–15, pp. 91–103 (2004)
Laptev, I., Marszałek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings 26th IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, United states, Jun. 23–28, pp. 1–8 (2008)
Willems, G., Tuytelaars, T., Van Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Proceedings 10th European Conference on Computer Vision, Marseille, France, Oct. 12–18, pp. 650–663 (2008)
Yuan, J., Liu, S., Wu, Y.: Discriminative video pattern search for efficient action detection. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1728–1743 (2011)
Niebles, J.C., Wang, H., Li, F.-F.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79(3), 299–318 (2008)
Bently, J.: Programming pearls: algorithm design techniques. Commun. ACM 27(9), 865–873 (1984)
Zhang, T., Liu, J., Liu, S., Xu, C., Lu, H.: Boosted exemplar learning for action recognition and annotation. IEEE Trans. Circuits Syst. Video Technol. 21(7), 853–866 (2011)
Seo, H.J., Milanfar, P.: Action recognition from one example. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 867–882 (2011)
Chakraborty, B., Holte, M., Moeslund, T.B., Gonzalez, J.: Selective spatio-temporal interest points. Comput. Vis. Image Underst. 116(3), 396–410 (2012)
Acknowledgments
The authors would like to thank the anonymous reviewers for the valuable and insightful comments on the earlier version of this manuscript. This work was partially supported by National Nature Science Foundation of China (No. 61202143), the Nature Science Foundation of Fujian Province (No. 2011J01367), Xiamen University 985 Project and National Science Council of Taiwan (NSC-101-2221-E-155-060).
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Zhang, HB., Li, SZ., Chen, SY. et al. Locating and recognizing multiple human actions by searching for maximum score subsequences. SIViP 9, 705–714 (2015). https://doi.org/10.1007/s11760-013-0501-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-013-0501-y