{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T12:14:47Z","timestamp":1762604087996},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2018,3,5]],"date-time":"2018-03-05T00:00:00Z","timestamp":1520208000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1007\/s11042-018-5839-2","type":"journal-article","created":{"date-parts":[[2018,3,5]],"date-time":"2018-03-05T16:35:38Z","timestamp":1520267738000},"page":"26107-26134","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Integral customer pose estimation using body orientation and visibility mask"],"prefix":"10.1007","volume":"77","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":[[2018,3,5]]},"reference":[{"key":"5839_CR1","doi-asserted-by":"crossref","unstructured":"Achilles F, Ichim A-E, Coskun H, Tombari F, Noachtar S, Navab N (2016) Patient MoCap: human pose estimation under blanket occlusion for hospital monitoring applications. In: Proceedings of the international conference on medical image computing and computer-assisted intervention, pp 491\u2013499","DOI":"10.1007\/978-3-319-46720-7_57"},{"key":"5839_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka M, Pishchulin L, Gehler P, Schiele B (2014) 2D human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3686\u20133693","DOI":"10.1109\/CVPR.2014.471"},{"key":"5839_CR3","doi-asserted-by":"crossref","unstructured":"Azizpour H, Laptev I (2012) Object detection using strongly-supervised deformable part models. In: European Conference on Computer Vision (ECCV), pp 836\u2013849","DOI":"10.1007\/978-3-642-33718-5_60"},{"key":"5839_CR4","doi-asserted-by":"crossref","unstructured":"Carreira J, Agrawal P, Fragkiadaki K, Malik J (2016) Human pose estimation with iterative error feedback. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4733\u20134742","DOI":"10.1109\/CVPR.2016.512"},{"key":"5839_CR5","unstructured":"Chen X, Yuille AL (2014) Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Advances in Neural Information Processing Systems, pp 1736\u20131744"},{"key":"5839_CR6","doi-asserted-by":"crossref","unstructured":"Chen X, Yuille AL (2015) Parsing occluded people by flexible compositions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3945\u20133954","DOI":"10.1109\/CVPR.2015.7299020"},{"key":"5839_CR7","doi-asserted-by":"crossref","unstructured":"Chen J, Song X, Nie L, Wang X, Zhang H, Chua T-S (2016) Micro tells macro: predicting the popularity of micro-videos via a transductive model. In: Proceedings of the 2016 ACM on multimedia conference, New York, pp 898\u2013907","DOI":"10.1145\/2964284.2964314"},{"key":"5839_CR8","doi-asserted-by":"crossref","unstructured":"Chu X, Ouyang W, Li H, Wang X (2016) Structured feature learning for pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4715\u20134723","DOI":"10.1109\/CVPR.2016.510"},{"key":"5839_CR9","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"5839_CR10","doi-asserted-by":"crossref","unstructured":"Dantone M, Gall J, Leistner C, Van Gool L (2013) 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","DOI":"10.1109\/CVPR.2013.391"},{"key":"5839_CR11","doi-asserted-by":"crossref","unstructured":"Desai C, Ramanan D (2012) Detecting actions, poses, and objects with relational phraselets. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 158\u2013172","DOI":"10.1007\/978-3-642-33765-9_12"},{"key":"5839_CR12","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A, et al. (2015) Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 2758\u20132766","DOI":"10.1109\/ICCV.2015.316"},{"key":"5839_CR13","unstructured":"Eichner M, Ferrari V (2012) Appearance sharing for collective human pose estimation. In: Proceedings of the Asian Conference on Computer Vision (ACCV), pp 138\u2013151"},{"issue":"1","key":"5839_CR14","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"PF Felzenszwalb","year":"2005","unstructured":"Felzenszwalb PF, Huttenlocher DP (2005) Pictorial structures for object recognition. Int J Comput Vis (IJCV) 61(1):55\u201379","journal-title":"Int J Comput Vis (IJCV)"},{"issue":"9","key":"5839_CR15","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell (PAMI) 32(9):1627\u20131645","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"key":"5839_CR16","doi-asserted-by":"crossref","unstructured":"Fragkiadaki K, Levine S, Felsen P, Malik J (2015) Recurrent network models for human dynamics. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4346\u20134354","DOI":"10.1109\/ICCV.2015.494"},{"key":"5839_CR17","doi-asserted-by":"crossref","unstructured":"Haque A, Peng B, Luo Z, Alahi A, Yeung S, Fei-Fei L (2016) Towards viewpoint invariant 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 160\u2013177","DOI":"10.1007\/978-3-319-46448-0_10"},{"key":"5839_CR18","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"5839_CR19","doi-asserted-by":"crossref","unstructured":"Iqbal U, Garbade M, Gall J (2017) Pose for action-action for pose. In: Proceedings of the IEEE International Conference on Automatic Face & Gesture Recognition, pp 438\u2013445","DOI":"10.1109\/FG.2017.61"},{"key":"5839_CR20","unstructured":"Jain A, Tompson J, LeCun Y, Bregler C (2014) 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"},{"key":"5839_CR21","doi-asserted-by":"crossref","unstructured":"Jhuang H, Gall J, Zuffi S, Schmid C, Black MJ (2013) Towards understanding action recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 3192\u20133199","DOI":"10.1109\/ICCV.2013.396"},{"key":"5839_CR22","doi-asserted-by":"crossref","unstructured":"Johnson S, Everingham M (2010) Clustered pose and nonlinear appearance models for human pose estimation. In: Proceedings of the British Machine Vision Conference (BMVC)","DOI":"10.5244\/C.24.12"},{"key":"5839_CR23","doi-asserted-by":"crossref","unstructured":"Johnson S, Everingham M (2011) Learning effective human pose estimation from inaccurate annotation. In: 2011 I.E. Conference on Computer Vision and Pattern Recognition (CVPR), pp 1465\u20131472","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"5839_CR24","unstructured":"Le Cun BB, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Handwritten digit recognition with a back-propagation network. In: Neural Information Processing Systems (NIPS)"},{"key":"5839_CR25","unstructured":"LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time-series. In: The handbook of brain theory and neural networks, vol. 3361, no. 10"},{"key":"5839_CR26","doi-asserted-by":"publisher","first-page":"26675","DOI":"10.1007\/s11042-016-4193-5","volume":"76","author":"Z Liu","year":"2016","unstructured":"Liu Z, Wang Z (2016) Action recognition with low observational latency via part movement model. Multimed Tools Appl (MTAP) 76:26675\u201326693","journal-title":"Multimed Tools Appl (MTAP)"},{"key":"5839_CR27","doi-asserted-by":"publisher","first-page":"6595","DOI":"10.1007\/s11042-016-3342-1","volume":"76","author":"J Liu","year":"2016","unstructured":"Liu J, Gu Y, Kamijo S (2016) Customer behavior classification using surveillance camera for marketing. Multimed Tools Appl (MTAP) 76:6595\u20136622","journal-title":"Multimed Tools Appl (MTAP)"},{"key":"5839_CR28","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"5839_CR29","doi-asserted-by":"crossref","unstructured":"Park D, Ramanan D (2015) Articulated pose estimation with tiny synthetic videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp 58\u201366","DOI":"10.1109\/CVPRW.2015.7301337"},{"key":"5839_CR30","doi-asserted-by":"crossref","unstructured":"Pfister T, Charles J, Zisserman A (2015) Flowing convnets for human pose estimation in videos. In: Proceedings of the IEEE International Conference on Computer Vision (CVPR), pp 1913\u20131921","DOI":"10.1109\/ICCV.2015.222"},{"key":"5839_CR31","doi-asserted-by":"crossref","unstructured":"Pishchulin L, Andriluka M, Gehler P, Schiele B (2013) Poselet conditioned pictorial structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 588\u2013595","DOI":"10.1109\/CVPR.2013.82"},{"key":"5839_CR32","doi-asserted-by":"crossref","unstructured":"Rafi U, Gall J, Leibe B (2015) A semantic occlusion model for human pose estimation from a single depth image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp 67\u201374","DOI":"10.1109\/CVPRW.2015.7301338"},{"issue":"3","key":"5839_CR33","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis (IJCV) 115(3):211\u2013252","journal-title":"Int J Comput Vis (IJCV)"},{"issue":"11","key":"5839_CR34","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45(11):2673\u20132681","journal-title":"IEEE Trans Signal Process"},{"key":"5839_CR35","unstructured":"Sminchisescu C, Telea A (2002) 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)"},{"key":"5839_CR36","doi-asserted-by":"crossref","unstructured":"Song J, Wang L, Van Gool L, Hilliges O (2017) Thin-slicing network: a deep structured model for pose estimation in videos. arXiv preprint arXiv:1703.10898","DOI":"10.1109\/CVPR.2017.590"},{"key":"5839_CR37","doi-asserted-by":"crossref","unstructured":"Sun M, Savarese S (2011) Articulated part-based model for joint object detection and pose estimation. In: Proceedings of the International Conference on Computer Vision (ICCV), pp 723\u2013730","DOI":"10.1109\/ICCV.2011.6126309"},{"issue":"8","key":"5839_CR38","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1016\/j.engappai.2010.07.004","volume":"23","author":"F Tafazzoli","year":"2010","unstructured":"Tafazzoli F, Safabakhsh R (2010) Model-based human gait recognition using leg and arm movements. Eng Appl Artif Intell 23(8):1237\u20131246","journal-title":"Eng Appl Artif Intell"},{"key":"5839_CR39","unstructured":"Tompson JJ, Jain A, LeCun Y, Bregler C (2014) Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems, pp 1799\u20131807"},{"key":"5839_CR40","doi-asserted-by":"crossref","unstructured":"Tompson J, Goroshin R, Jain A, LeCun Y, Bregler C (2015) Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 648\u2013656","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"5839_CR41","doi-asserted-by":"crossref","unstructured":"Toshev A, Szegedy C (2014) Deeppose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1653\u20131660","DOI":"10.1109\/CVPR.2014.214"},{"key":"5839_CR42","unstructured":"Wagg DK, Nixon MS (2003) Model-based gait enrolment in real-world imagery. In: Proceedings of the workshop on multimodal user authentication, pp 189\u2013195"},{"key":"5839_CR43","doi-asserted-by":"crossref","unstructured":"Weinzaepfel P, Revaud J, Harchaoui Z, Schmid C (2013) DeepFlow: large displacement optical flow with deep matching. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 1385\u20131392","DOI":"10.1109\/ICCV.2013.175"},{"key":"5839_CR44","unstructured":"Xiaohan Nie B, Xiong C, Zhu S-C (2015) Joint action recognition and pose estimation from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1293\u20131301"},{"issue":"12","key":"5839_CR45","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang Y, Ramanan D (2013) Articulated human detection with flexible mixtures of parts. IEEE Trans Pattern Anal Mach Intell (PAMI) 35(12):2878\u20132890","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"key":"5839_CR46","doi-asserted-by":"crossref","unstructured":"Yang W, Ouyang W, Li H, Wang X (2016) 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","DOI":"10.1109\/CVPR.2016.335"},{"key":"5839_CR47","doi-asserted-by":"crossref","unstructured":"Yao J, Odobez J-M (2007) Multi-layer background subtraction based on color and texture. In: Proceedings of the IEEE International Conference on Computer Vision (CVPR), pp 1\u20138","DOI":"10.1109\/CVPR.2007.383497"},{"key":"5839_CR48","doi-asserted-by":"crossref","unstructured":"Zhang J, Nie L, Wang X, He X, Huang X, Chua TS (2016) Shorter-is-better: Venue category estimation from micro-video. In: Proceedings of the 2016 ACM on multimedia conference, pp 1415\u20131424","DOI":"10.1145\/2964284.2964307"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-5839-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5839-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5839-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,5]],"date-time":"2019-03-05T01:58:39Z","timestamp":1551751119000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-5839-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3,5]]},"references-count":48,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2018,10]]}},"alternative-id":["5839"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-5839-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3,5]]},"assertion":[{"value":"6 April 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}