Abstract
Achieving joint segmentation and recognition of continuous actions in a long-term video is a challenging task due to the varying durations of actions and the complex transitions of multiple actions. In this paper, a novel discriminative structural model is proposed for splitting a long-term video into segments and annotating the action label of each segment. A set of state variables is introduced into the model to explore discriminative semantic concepts shared among different actions. To exploit the statistical dependences among segments, temporal context is captured at both the action level and the semantic concept level. The state variables are treated as latent information in the discriminative structural model and inferred during both training and testing. Experiments on multi-view IXMAS and realistic Hollywood datasets demonstrate the effectiveness of the proposed method.
Similar content being viewed by others
References
Baccouche M, Mamalet F, Wolf C, Garcia C, Baskurt A (2011) Sequential deep learning for human action recognition. In: International conference on human behavior unterstanding, pp 29–39
Chen Q, Cai Y, Brown L, Datta A, Fan Q, Feris R, Yan S, Hauptmann A, Pankanti S (2013) Spatio-temporal fisher vector coding for surveillance event detection. In: Proceedings of the 21st ACM international conference on Multimedia, ACM, pp 589–592
Cheng Y, Fan Q, Pankanti S, Choudhary A (2014) Temporal sequence modeling for video event detection. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 2235–2242
Chun SY, Lee CS (2016) Human action recognition using histogram of motion intensity and direction from multiple views. IET Comput Vis 10(4):250–256
Dalal N, Triggs B, Schmid C (2006) Human detection using oriented histograms of flow and appearance. In: Eurpoean conference on computer vision, Springer, pp 428–441
Do TMT, Artières T (2009) Large margin training for hidden markov models with partially observed states. In: Annual international conference on machine learning, ACM, pp 265–272
Fernando B, Gavves E, Oramas J, Ghodrati A, Tuytelaars T (2015) Modeling video evolution for action recognition. In: IEEE Conference on computer vision and pattern recognition, vol 2. p 8
Fu Y, Zhang T, Wang W (2017) Sparse coding-based space-time video representation for action recognition. Multimedia Tools and Applications 76:1–14
Gaidon A, Harchaoui Z, Schmid C (2011) Actom sequence models for efficient action detection. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 3201–3208
Harchaoui Z, Moulines E, Bach FR (2009) Kernel change-point analysis. In: Advances in neural information processing systems, pp 609–616
Herath S, Harandi M, Porikli F (2017) Going deeper into action recognition: a survey. Image Vis Comput 60:4–21
Hoai M, Lan ZZ, De la Torre F (2011) Joint segmentation and classification of human actions in video. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 3265–3272
Hsu YP, Liu C, Chen TY, Fu LC (2016) Online view-invariant human action recognition using rgb-d spatio-temporal matrix. Pattern Recogn 60:215–226
Ji S, Xu W, Yang M, Yu K (2013) 3d convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221–231
Junejo IN, Dexter E, Laptev I, Perez P (2011) View-independent action recognition from temporal self-similarities. IEEE Trans Pattern Anal Mach Intell 33 (1):172–185
Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: IEEE Conference on computer vision and pattern recognition, pp 1725–1732
Kulkarni K, Evangelidis G, Cech J, Horaud R (2015) Continuous action recognition based on sequence alignment. Int J Comput Vis 112(1):90–114
Laptev I (2005) On space-time interest points. Int J Comput Vis 64(2-3):107–123
Laptev I, Marszalek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 1–8
Lei J, Zhang J, Li G, Guo Q, Tu D (2016) Continuous action segmentation and recognition using hybrid convolutional neural network-hidden markov model model. IET Comput Vis 10(6):537–544
Li S, Li K, Fu Y (2015) Temporal subspace clustering for human motion segmentation. In: IEEE International conference on computer vision, pp 4453–4461
Lin W, Chen Y, Wu J, Wang H, Sheng B, Li H (2015) A new network-based algorithm for human activity recognition in videos. IEEE Trans Circuits Syst Video Technol 24(5):826–841
Liu C, Wu X, Jia Y (2016) A hierarchical video description for complex activity understanding. Int J Comput Vis 118(2):240–255
Liu C, Xu W, Wu Q, Yang G (2016) Learning motion and content-dependent features with convolutions for action recognition. Multimedia Tools and Applications 75(21):13,023–13,039
Liu J, Gu Y, Kamijo S (2017) Customer behavior classification using surveillance camera for marketing. Multimedia Tools and Applications 76(5):6595–6622
Liu J, Kuipers B, Savarese S (2011) Recognizing human actions by attributes. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 3337–3344
Lu G, Kudo M, Toyama J (2013) Temporal segmentation and assignment of successive actions in a long-term video. Pattern Recogn Lett 34(15):1936–1944
Lv F, Nevatia R (2007) Single view human action recognition using key pose matching and viterbi path searching. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 1–8
Ni B, Moulin P, Yang X, Yan S (2015) Motion part regularization: Improving action recognition via trajectory selection. In: IEEE Conference on computer vision and pattern recognition, pp 3698–3706
Ogale A, Karapurkar A, Guerra-Filho G, Aloimonos Y (2004) View-invariant identification of pose sequences for action recognition. In: Video analysis and content extraction workshop, Citeseer
Ramezani M, Yaghmaee F (2016) A review on human action analysis in videos for retrieval applications. Artif Intell Rev 46(4):485–514
Ryan MS, Nudd GR (1973) The viterbi algorithm. Proc IEEE 61(5):268–278
Sadanand S, Corso JJ (2012) Action bank: a high-level representation of activity in video. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 1234–1241
Santos L, Khoshhal K, Dias J (2015) Trajectory-based human action segmentation. Pattern Recogn 48(2):568–579
Shao L, Ji L, Liu Y, Zhang J (2012) Human action segmentation and recognition via motion and shape analysis. Pattern Recogn Lett 33(4):438–445
Shao L, Zhen X, Tao D, Li X (2014) Spatio-temporal laplacian pyramid coding for action recognition. IEEE Transactions on Cybernetics 44(6):2168–2267
Shi Q, Wang L, Cheng L, Smola A (2008) Discriminative human action segmentation and recognition using semi-markov model. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 1–8
Shi Q, Cheng L, Wang L, Smola A (2011) Human action segmentation and recognition using discriminative semi-markov models. Int J Comput Vis 93(1):22–32
Simon T, Nguyen MH, De La Torre F, Cohn JF (2010) Action unit detection with segment-based svms. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 2737–2744
Tejerodepablos A, Nakashima Y, Sato T, Yokoya N (2016) Human action recognition-based video summarization for rgb-d personal sports video. In: IEEE International conference on multimedia and expo, pp 1–6
Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In: IEEE International conference on computer vision, pp 4489–4497
Vitaladevuni SN, Kellokumpu V, Davis LS (2008) Action recognition using ballistic dynamics. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 1–8
Wang H, Kläser A., Schmid C, Liu CL (2013) Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis 103(1):60–79
Wang J, Nie X, Xia Y, Wu Y, Zhu SC (2014) Cross-view action modeling, learning, and recognition. In: IEEE Conference on computer vision and pattern recognition, IEEE, pp 2649–2656
Wang H, Dan O, Verbeek J, Schmid C (2016) A robust and efficient video representation for action recognition. Int J Comput Vis 119(3):219–238
Wang W, Yan Y, Zhang L, Hong R, Sebe N (2016) Collaborative sparse coding for multiview action recognition. IEEE MultiMedia 23(4):80–87
Weinland D, Ronfard R, Boyer E (2006) Free viewpoint action recognition using motion history volumes. Comput Vis Image Underst 104(2):249–257
Weinland D, Boyer E, Ronfard R (2007) Action recognition from arbitrary views using 3d exemplars. In: IEEE International conference on computer vision, IEEE, pp 1–7
Weinland D, Özuysal M, Fua P (2010) Making action recognition robust to occlusions and viewpoint changes. In: European conference on computer vision, Springer, pp 635–648
Wu D, Shao L (2013) Silhouette analysis-based action recognition via exploiting human poses. IEEE Trans Circuits Syst Video Technol 23(2):236–243
Wu X, Xu D, Duan L, Luo J, Jia Y (2013) Action recognition using multilevel features and latent structural svm. IEEE Trans Circuits Syst Video Technol 23(8):1422–1431
Wu D, Sharma N, Blumenstein M (2017) Recent advances in video-based human action recognition using deep learning: a review. In: International joint conference on neural networks, IEEE, pp 2865–2872
Xuan X, Murphy K (2007) Modeling changing dependency structure in multivariate time series. In: International conference on machine learning, ACM, pp 1055–1062
Yang Y, Mao G (2013) A self-adaptive sliding window technique for mining data streams. In: Intelligence computation and evolutionary computation, pp 689–697
Yi Y, Wang H, Zhang B (2017) Learning correlations for human action recognition in videos. Multimedia Tools and Applications 76(18):18891–18913
Yu CNJ, Joachims T (2009) Learning structural svms with latent variables. In: Annual international conference on machine learning, ACM, pp 1169–1176
Zhao S, Liu Y, Han Y, Hong R, Hu Q, Tian Q (2017) Pooling the convolutional layers in deep convnets for video action recognition. IEEE Transactions on Circuits and Systems for Video Technology
Zhen X, Shao L (2013) Spatio-temporal steerable pyramid for human action recognition. In: IEEE International conference and workshops on automatic face and gesture recognition, IEEE
Zhou Q, Wang G, Jia K, Zhao Q (2013) Learning to share latent tasks for action recognition. In: IEEE International conference on computer vision, IEEE, pp 2264–2271
Zhu G, Huang Q, Xu C, Xing L, Gao W, Yao H (2007) Human behavior analysis for highlight ranking in broadcast racket sports video. IEEE Trans Multimedia 9(6):1167–1182
Acknowledgements
This work was supported in part by the Natural Science Foundation of China(NSFC) under Grants No. 61602320 and No. 61673062, and Liaoning Doctoral Startup Project under Grant No. 201601172, and project of Liaoning provincial education department under Grant No. L201607.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, C., Hou, J., Wu, X. et al. A discriminative structural model for joint segmentation and recognition of human actions. Multimed Tools Appl 77, 31627–31645 (2018). https://doi.org/10.1007/s11042-018-6189-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6189-9