{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T21:10:07Z","timestamp":1750972207978,"version":"3.41.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2017,11,1]],"date-time":"2017-11-01T00:00:00Z","timestamp":1509494400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1007\/s00530-017-0570-9","type":"journal-article","created":{"date-parts":[[2017,11,1]],"date-time":"2017-11-01T04:29:41Z","timestamp":1509510581000},"page":"439-457","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Customer pose estimation using orientational spatio-temporal network from surveillance camera"],"prefix":"10.1007","volume":"24","author":[{"given":"Jingwen","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanlei","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunsuke","family":"Kamijo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,11,1]]},"reference":[{"key":"570_CR1","unstructured":"Sminchisescu, C., Telea, A.: Human pose estimation from silhouettes. A consistent approach using distance level sets. In: Proceedings of the International Conference on Computer Graphics, Visualization and Computer Vision (WSCG) (2002)"},{"key":"570_CR2","unstructured":"Wagg, D.K., Nixon, M.S.: Model-based gait enrolment in real-world imagery. In: Proceedings of the Workshop on Multimodal User Authentication, pp. 189\u2013195 (2003)"},{"issue":"8","key":"570_CR3","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1016\/j.engappai.2010.07.004","volume":"23","author":"F Tafazzoli","year":"2010","unstructured":"Tafazzoli, F., Safabakhsh, R.: Model-based human gait recognition using leg and arm movements. Eng. Appl. Artif. Intell. 23(8), 1237\u20131246 (2010)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"570_CR4","unstructured":"Zhao, L.: Dressed human modeling, detection, and parts localization, Ph.D. thesis, Carnegie Mellon University Pittsburgh, PA, (2001)"},{"key":"570_CR5","doi-asserted-by":"crossref","unstructured":"Mittal, A., Zhao, L., Davis, L.S.: Human body pose estimation using silhouette shape analysis. In: Proceedings of IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 263\u2013270 (2003)","DOI":"10.1109\/AVSS.2003.1217930"},{"key":"570_CR6","doi-asserted-by":"crossref","unstructured":"Kushwaha, A.K.S., Srivastava, S., Srivastava, R.: Multi-view human activity recognition based on silhouette and uniform rotation invariant local binary patterns. Multimed. Syst. pp. 1\u201317 (2016)","DOI":"10.1007\/s00530-016-0505-x"},{"issue":"1","key":"570_CR7","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/TPAMI.2007.250600","volume":"29","author":"D Ramanan","year":"2007","unstructured":"Ramanan, D., Forsyth, D.A., Zisserman, A.: Tracking people by learning their appearance. IEEE Trans. Pattern Anal. Mach. Intell. 29(1), 65\u201381 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"570_CR8","first-page":"623","volume":"2010","author":"M Andriluka","year":"2010","unstructured":"Andriluka, M., Roth, S., Schiele, B.: Monocular 3D pose estimation and tracking by detection. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) 2010, 623\u2013630 (2010)","journal-title":"IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)"},{"key":"570_CR9","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: people detection and articulated pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1014\u20131021 (2009)","DOI":"10.1109\/CVPR.2009.5206754"},{"key":"570_CR10","doi-asserted-by":"crossref","unstructured":"Moutzouris, A., Martinez-del-Rincon, J., Lewandowski, M., Nebel, J., Makris, D.: Human pose tracking in low dimensional space enhanced by limb correction. In: 2011 18th IEEE International Conference on Image Processing (ICIP), pp. 2301\u20132304 (2011)","DOI":"10.1109\/ICIP.2011.6116100"},{"key":"570_CR11","unstructured":"Weiss, D., Sapp, B., Taskar, B.: Sidestepping intractable inference with structured ensemble cascades. In: Advances in Neural Information Processing Systems, pp. 2415\u20132423 (2010)"},{"key":"570_CR12","first-page":"1281","volume":"2011","author":"B Sapp","year":"2011","unstructured":"Sapp, B., Weiss, D., Taskar, B.: Parsing human motion with stretchable models. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) 2011, 1281\u20131288 (2011)","journal-title":"IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)"},{"issue":"2","key":"570_CR13","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1007\/s11263-012-0524-9","volume":"99","author":"M Eichner","year":"2012","unstructured":"Eichner, M., Marin-Jimenez, M., Zisserman, A., Ferrari, V.: 2d articulated human pose estimation and retrieval in (almost) unconstrained still images. Int. J. Comput. Vis. 99(2), 190\u2013214 (2012)","journal-title":"Int. J. Comput. Vis."},{"key":"570_CR14","doi-asserted-by":"crossref","unstructured":"Cherian, A., Mairal, J., Alahari, K., Schmid, C.: Mixing body-part sequences for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2353\u20132360 (2014)","DOI":"10.1109\/CVPR.2014.302"},{"issue":"1","key":"570_CR15","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"PF Felzenszwalb","year":"2005","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. Int. J. Comput. Vis. IJCV 61(1), 55\u201379 (2005)","journal-title":"Int. J. Comput. Vis. IJCV"},{"key":"570_CR16","doi-asserted-by":"crossref","unstructured":"Sun, M., Savarese, S.: Articulated part-based model for joint object detection and pose estimation. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 723\u2013730 (2011)","DOI":"10.1109\/ICCV.2011.6126309"},{"key":"570_CR17","doi-asserted-by":"crossref","unstructured":"Dantone, M., Gall, J., Leistner, C., Van Gool, L.: Human pose estimation using body parts dependent joint regressors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3041\u20133048 (2013)","DOI":"10.1109\/CVPR.2013.391"},{"issue":"12","key":"570_CR18","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang, Y., Ramanan, D.: Articulated human detection with flexible mixtures of parts. IEEE Trans. Pattern Anal. Mach. Intell. PAMI 35(12), 2878\u20132890 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. PAMI"},{"key":"570_CR19","doi-asserted-by":"crossref","unstructured":"Eichner, M., Ferrari, V.: Appearance sharing for collective human pose estimation. In: Proceedings of the Asian Conference on Computer Vision (ACCV), pp. 138\u2013151 (2012)","DOI":"10.1007\/978-3-642-37331-2_11"},{"issue":"1","key":"570_CR20","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s00530-014-0422-9","volume":"22","author":"S Li","year":"2016","unstructured":"Li, S., Zhang, M., Su, S., Shuai, B., Ji, R.: Decomposed human localization from social photo album. Multimed. Syst. 22(1), 137\u2013148 (2016)","journal-title":"Multimed. Syst."},{"key":"570_CR21","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Poselet conditioned pictorial structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 588\u2013595 (2013)","DOI":"10.1109\/CVPR.2013.82"},{"key":"570_CR22","unstructured":"Le Cun, B.B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Neural Information Processing Systems (NIPS) (1989)"},{"key":"570_CR23","unstructured":"LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time-series. Handb. Brain Theory Neural Netw. 3361(10), (1995)"},{"key":"570_CR24","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097\u20131105 (2012)"},{"key":"570_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ArXiv Prepr. ArXiv14091556, (2014)"},{"key":"570_CR26","doi-asserted-by":"crossref","unstructured":"C. Szegedy et al., \u201cGoing deeper with convolutions,\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"570_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. ArXiv Prepr. ArXiv151203385, (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"570_CR28","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"570_CR29","doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimation with iterative error feedback. ArXiv Prepr. ArXiv150706550, (2015)","DOI":"10.1109\/CVPR.2016.512"},{"key":"570_CR30","doi-asserted-by":"crossref","unstructured":"Haque, A., Peng, B., Luo, Z., Alahi, A., Yeung, S., Fei-Fei, L.: Towards viewpoint invariant 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 160\u2013177 (2016)","DOI":"10.1007\/978-3-319-46448-0_10"},{"key":"570_CR31","unstructured":"Chen, X., Yuille, A.L.: Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Advances in Neural Information Processing Systems, pp. 1736\u20131744 (2014)"},{"key":"570_CR32","doi-asserted-by":"crossref","unstructured":"Chen, X., Yuille, A.L.: Parsing occluded people by flexible compositions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3945\u20133954 (2015)","DOI":"10.1109\/CVPR.2015.7299020"},{"key":"570_CR33","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in neural information processing systems, pp. 1799\u20131807 (2014)"},{"key":"570_CR34","doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 648\u2013656 (2015)","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"570_CR35","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Li, H., Wang, X.: End-to-end learning of deformable mixture of parts and deep convolutional neural networks for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4715\u20134723 (2016)","DOI":"10.1109\/CVPR.2016.335"},{"key":"570_CR36","doi-asserted-by":"crossref","unstructured":"Chu, X., Ouyang, W., Li, H., Wang, X.: Structured feature learning for pose estimation. ArXiv Prepr. ArXiv160309065, 2016","DOI":"10.1109\/CVPR.2016.510"},{"key":"570_CR37","doi-asserted-by":"crossref","unstructured":"Jain, A., Tompson, J., LeCun, Y., Bregler, C.: MoDeep: a deep learning framework using motion features for human pose estimation. In: Proceedings of the Asian Conference on Computer Vision (ACCV), pp. 302\u2013315 (2014)","DOI":"10.1007\/978-3-319-16808-1_21"},{"key":"570_CR38","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: large displacement optical flow with deep matching. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1385\u20131392 (2013)","DOI":"10.1109\/ICCV.2013.175"},{"key":"570_CR39","doi-asserted-by":"crossref","unstructured":"Pfister, T., Charles, J., Zisserman, A.: Flowing convnets for human pose estimation in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1913\u20131921 (2015)","DOI":"10.1109\/ICCV.2015.222"},{"key":"570_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Video action detection with relational dynamic-poselets. In: European Conference on Computer Vision, pp. 565\u2013580 (2014)","DOI":"10.1007\/978-3-319-10602-1_37"},{"key":"570_CR41","doi-asserted-by":"crossref","unstructured":"Yao, J., Odobez, J.: Multi-layer background subtraction based on color and texture. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR\u201907, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383497"},{"key":"570_CR42","doi-asserted-by":"crossref","unstructured":"Liu, J., Gu, Y., Kamijo, S.: Customer behavior classification using surveillance camera for marketing. Multimed. Tools Appl., pp. 1\u201328 (2016)","DOI":"10.1007\/s11042-016-3342-1"},{"key":"570_CR43","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"570_CR44","doi-asserted-by":"crossref","unstructured":"Haque, A., Peng, B., Luo, Z., Alahi, A., Yeung, S., Fei-Fei, L.: Viewpoint invariant 3D human pose estimation with recurrent error feedback. ArXiv160307076 Cs, (2016)","DOI":"10.1007\/978-3-319-46448-0_10"},{"key":"570_CR45","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"570_CR46","unstructured":"Arthur, D., Vassilvitskii, S.: k-means++: The advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms, pp. 1027\u20131035 (2007)"},{"issue":"7553","key":"570_CR47","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"570_CR48","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: Proceedings of the British Machine Vision Conference (BMVC), 2010","DOI":"10.5244\/C.24.12"},{"key":"570_CR49","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3192\u20133199 (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"570_CR50","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1465\u20131472 (2011)","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"570_CR51","doi-asserted-by":"crossref","unstructured":"Rafi, U., Leibe, B., Gall, J., Kostrikov, I.: An efficient convolutional network for human pose estimation. In: BMVC, vol. 1, p. 2 (2016)","DOI":"10.5244\/C.30.109"},{"key":"570_CR52","doi-asserted-by":"crossref","unstructured":"Yu, X., Zhou, F., Chandraker, M.: Deep deformation network for object landmark localization. ArXiv Prepr. ArXiv160501014, 2016","DOI":"10.1007\/978-3-319-46454-1_4"},{"key":"570_CR53","doi-asserted-by":"crossref","unstructured":"Xiaohan Nie, B., Xiong, C., Zhu, S.-C.: Joint action recognition and pose estimation from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1293\u20131301 (2015)","DOI":"10.1109\/CVPR.2015.7298734"},{"key":"570_CR54","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Garbade, M., Gall, J.: Pose for action-action for pose. In: 2017 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017), pp. 438\u2013445 (2017)","DOI":"10.1109\/FG.2017.61"},{"key":"570_CR55","doi-asserted-by":"crossref","unstructured":"Song, J., Wang, L., Van Gool, L., Hilliges, O.: Thin-slicing network: a deep structured model for pose estimation in videos. ArXiv170310898 Cs, 2017","DOI":"10.1109\/CVPR.2017.590"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-017-0570-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-017-0570-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-017-0570-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T20:34:11Z","timestamp":1750970051000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-017-0570-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,1]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,7]]}},"alternative-id":["570"],"URL":"https:\/\/doi.org\/10.1007\/s00530-017-0570-9","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2017,11,1]]}}}