Classification of human actions using pose-based features and stacked auto encoder

Pattern Recognition Letters

Volumn 83, Issue , 2016, Pages 268-277

  Ijjina, Earnest Paul ^a   Krishna Mohan, C ^a  

^a INDIAN INSTITUTE OF TECHNOLOGY HYDERABAD   (India)

Author keywords

Fuzzy membership functions; Human action recognition; Pose based features; Stacked auto encoder

Indexed keywords

GESTURE RECOGNITION; IMAGE RECOGNITION; LEARNING SYSTEMS; MOTION ESTIMATION;

AUTO ENCODERS; FUZZY MEMBERSHIP FUNCTION; HUMAN ACTIONS; HUMAN-ACTION RECOGNITION; INPUT DATAS; POSE-BASED FEATURES; STATISTICAL INFORMATION;

MEMBERSHIP FUNCTIONS;

EID: 84963532632     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patrec.2016.03.021     Document Type: Article

References (25)

1. [1] Cmu human motion capture database, ( http://mocap.cs.cmu.edu/). (accessed: 02.09.16).
2. [2] Brun, L., Foggia, P., Saggese, A., Vento, M., Recognition of human actions using edit distance on aclet strings. VISAPP 2015 - Proceedings of the 10th International Conference on Computer Vision Theory and Applications, Volume 2, Berlin, Germany, 11–14 March, 2015, 2015, 97–103.
3. [3] Cheema, M.S., Eweiwi, A., Bauckhage, C., Human activity recognition by separating style and content. Pattern Recogn. Lett. 50 (2014), 130–138. Depth Image Analysis.
4. [4] Du, Y., Wang, W., Wang, L., Hierarchical recurrent neural network for skeleton based action recognition. CVPR, IEEE, 2015, 1110–1118.
5. [5] Evangelidis, G., Singh, G., Horaud, R., Skeletal quads: Human action recognition using joint quadruples. Proceedings of the International Conference on Pattern Recognition (ICPR), 2014, 4513–4518.
6. [6] Han, J., Shao, L., Xu, D., Shotton, J., Enhanced computer vision with microsoft kinect sensor: a review. IEEE Trans. Cybern. 43 (2013), 1318–1334.
7. [7] Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J., Towards understanding action recognition. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, 2013, 3192–3199.
8. [8] Ji, S., Xu, W., Yang, M., Yu, K., 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35 (2013), 221–231.
9. [9] Jiang, Z., Lin, Z., Davis, L.S., Label consistent k-svd: learning a discriminative dictionary for recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35 (2013), 2651–2664.
10. [10] Lin, W., Chu, H., Wu, J., Sheng, B., Chen, Z., A heat-map-based algorithm for recognizing group activities in videos. IEEE Trans. Circ. Syst. Video Technol. 23 (2013), 1980–1992.
11. [11] Mocanu, D.C., Ammar, H.B., Lowet, D., Driessens, K., Liotta, A., Weiss, G., Tuyls, K., Factored four way conditional restricted boltzmann machines for activity recognition. Pattern Recogn. Lett. 66 (2015), 100–108. Pattern Recognition in Human Computer Interaction.
12. [12] Møller, M.F., Original contribution: A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw. 6 (1993), 525–533.
13. [13] Ofli, F., Chaudhry, R., Kurillo, G., Vidal, R., Bajcsy, R., Berkeley mhad: a comprehensive multimodal human action database. Proceedings of the 2013 IEEE Workshop on Applications of Computer Vision (WACV), 2013, 53–60.
14. [14] Ofli, F., Chaudhry, R., Kurillo, G., Vidal, R., Bajcsy, R., Sequence of the most informative joints (smij). J. Vis. Commun. Image Represent. 25 (2014), 24–38.
15. [15] Oreifej, O., Liu, Z., Hon4d: Histogram of oriented 4d normals for activity recognition from depth sequences. CVPR,IEEE, 2013, 716–723.
16. [16] Foggia, P., Percannella, G., V., A.S.M., Recognizing human actions by a bag of visual words. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, IEEE SMC 2013, 2013.
17. [17] Foggia, P., Saggese, A., V., N.S.M., Exploiting the deep learning paradigm for recognizing human actions. IEEE, (eds.) Proceedings of the IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS 2014), 2014.
18. [18] Prest, A., Ferrari, V., Schmid, C., Explicit modeling of human-object interactions in realistic videos. IEEE Trans. Pattern Anal. Mach. Intell. 35 (2013), 835–848.
19. [19] Shen, W., Lei, R., Zeng, D., Zhang, Z., Regularity guaranteed human pose correction. Asian Conference on Computer Vision, Springer, 2014, 242–256.
20. [20] Wei Shen, K.D., Bai, X., Leyvand, T., Guo, B., Tu, Z., Exemplar-based human action pose correction and tagging. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012, 1784–1791, 10.1109/CVPR.2012.6247875.
21. [21] Wei Shen, K.D., Bai, X., Leyvand, T., Guo, B., Tu, Z., Exemplar-based human action pose correction. IEEE Trans. Cybern. 44 (2014), 1053–1066.
22. [22] Xia, L., Chen, C.C., Aggarwal, J.K., View invariant human action recognition using histograms of 3d joints. Workshop on Human Activity Understanding from 3D Data in conjunction with CVPR (HAU3D), Rhode Island, USA, 2012, 20–27.
23. [23] Yun, K., Honorio, J., Chattopadhyay, D., Berg, T.L., Samaras, D., Two-person interaction detection using body-pose features and multiple instance learning. IEEE, 2012.
24. [24] Zhang, H., Reardon, C., Zhang, C., Parker, L.E., Adaptive human-centered representation for activity recognition of multiple individuals from 3d point cloud sequences. IEEE, 2015, 1991–1998.
25. [25] Zhu, Z., Wang, X., Bai, S., Yao, C., Bai, X., Deep learning representation using autoencoder for 3d shape retrieval. Proceedings of the International Conference on Security, Pattern Analysis, and Cybernetics (SPAC), IEEE, 2014, 279–284.