{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:05:05Z","timestamp":1782990305293,"version":"3.54.5"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,7,28]],"date-time":"2020-07-28T00:00:00Z","timestamp":1595894400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,28]],"date-time":"2020-07-28T00:00:00Z","timestamp":1595894400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s12652-020-02347-7","type":"journal-article","created":{"date-parts":[[2020,7,28]],"date-time":"2020-07-28T21:34:13Z","timestamp":1595972053000},"page":"2339-2353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Uniting holistic and part-based attitudes for accurate and robust deep human pose estimation"],"prefix":"10.1007","volume":"12","author":[{"given":"Faranak","family":"Shamsafar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4071-2750","authenticated-orcid":false,"given":"Hossein","family":"Ebrahimnezhad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,7,28]]},"reference":[{"issue":"1","key":"2347_CR1","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/TPAMI.2006.21","volume":"28","author":"A Agarwal","year":"2006","unstructured":"Agarwal A, Triggs B (2006) Recovering 3D human pose from monocular images. IEEE Trans Pattern Anal Mach Intell 28(1):44\u201358. https:\/\/doi.org\/10.1109\/TPAMI.2006.21","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2347_CR2","doi-asserted-by":"publisher","unstructured":"Andriluka M, Pishchulin L, Gehler P, Schiele B (2014) 2D human pose estimation: new benchmark and state of the art analysis. In: IEEE conference on computer vision and pattern, pp 3686\u20133693. https:\/\/doi.org\/10.1109\/CVPR.2014.471","DOI":"10.1109\/CVPR.2014.471"},{"key":"2347_CR3","doi-asserted-by":"publisher","unstructured":"Belagiannis V, Rupprecht C, Carneiro G, Navab N (2015) Robust optimization for deep regression. In: International conference on computer vision, pp 2830\u20132838. https:\/\/doi.org\/10.1109\/ICCV.2015.324","DOI":"10.1109\/ICCV.2015.324"},{"key":"2347_CR4","doi-asserted-by":"publisher","unstructured":"Belagiannis V, Zisserman A (2017) Recurrent human pose estimation. In: IEEE international conference on automatic face and gesture recognition, pp 468\u2013475. https:\/\/doi.org\/10.1109\/FG.2017.64","DOI":"10.1109\/FG.2017.64"},{"key":"2347_CR5","doi-asserted-by":"publisher","unstructured":"Carreira J, Agrawal P, Fragkiadaki K, Malik J (2016) Human pose estimation with iterative error feedback. In: IEEE conference on computer vision and pattern, pp 4733\u20134742. https:\/\/doi.org\/10.1109\/CVPR.2016.512","DOI":"10.1109\/CVPR.2016.512"},{"key":"2347_CR6","unstructured":"Chen X, Yuille A (2014) Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Advances in neural information processing systems, pp 1736\u20131744"},{"key":"2347_CR7","doi-asserted-by":"publisher","unstructured":"Chu X, Ouyang W, Li H, Wang X (2016) Structured feature learning for pose estimation. In: IEEE conference on computer vision and pattern, vol 2016-Dec, pp 4715\u20134723. https:\/\/doi.org\/10.1109\/CVPR.2016.510. arXiv:1603.09065","DOI":"10.1109\/CVPR.2016.510"},{"key":"2347_CR8","first-page":"886","volume":"1","author":"N Dalal","year":"2005","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. IEEE Conf Comput Vis Pattern 1:886\u2013893","journal-title":"IEEE Conf Comput Vis Pattern"},{"issue":"8","key":"2347_CR9","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1109\/TPAMI.2014.2377715","volume":"37","author":"P Doll\u00e1ar","year":"2015","unstructured":"Doll\u00e1ar P, Zitnick CL (2015) Fast edge detection using structured forests. IEEE Trans Pattern Anal Mach Intell 37(8):1558\u20131570. https:\/\/doi.org\/10.1109\/TPAMI.2014.2377715","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2347_CR10","doi-asserted-by":"crossref","unstructured":"Eichner M, Ferrari V (2009) better appearance models for pictorial structures. In: British machine vision conference, pp 3.1\u20133.11. DOIurlhttps:\/\/doi.org\/10.5244\/C.23.3.arXiv:1504.08083","DOI":"10.5244\/C.23.3"},{"key":"2347_CR11","doi-asserted-by":"crossref","unstructured":"Eichner M, Ferrari V (2012) Appearance sharing for collective human pose estimation. In: Asian conference on computer vision. Springer, Berlin, pp 138\u2013151","DOI":"10.1007\/978-3-642-37331-2_11"},{"key":"2347_CR12","doi-asserted-by":"publisher","unstructured":"Fan X, Zheng K, Lin Y, Song W (2015) Combining local appearance and holistic view: dual-source deep neural networks for human pose estimation. In: IEEE conference on computer vision and pattern, pp 1347\u20131355. https:\/\/doi.org\/10.1109\/CVPR.2015.7298740","DOI":"10.1109\/CVPR.2015.7298740"},{"key":"2347_CR13","doi-asserted-by":"publisher","unstructured":"Felzenszwalb PF, Girshick RB, McAllester D (2010a) Cascade object detection with deformable part models. In: IEEE conference on computer vision and pattern, pp 2241\u20132248. https:\/\/doi.org\/10.1109\/CVPR.2010.5539906","DOI":"10.1109\/CVPR.2010.5539906"},{"issue":"1","key":"2347_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 61(1):55\u201379","journal-title":"Int J Comput Vis"},{"issue":"9","key":"2347_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 (2010b) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627\u20131645","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2347_CR16","doi-asserted-by":"crossref","unstructured":"Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multi-scale, deformable part model. In: IEEE conference on computer vision and pattern, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587597"},{"issue":"8","key":"2347_CR17","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1109\/TPAMI.2007.1062","volume":"29","author":"DM Gavrila","year":"2007","unstructured":"Gavrila DM (2007) A Bayesian, exemplar-based approach to hierarchical shape matching. IEEE Trans Pattern Anal Mach Intell 29(8):1408\u20131421. https:\/\/doi.org\/10.1109\/TPAMI.2007.1062","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"2347_CR18","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/s11263-015-0869-y","volume":"118","author":"A Hern\u00e1ndez-Vela","year":"2016","unstructured":"Hern\u00e1ndez-Vela A, Sclaroff S, Escalera S (2016) Poselet-based contextual rescoring for human pose estimation via pictorial structures. Int J Comput Vis 118(1):49\u201364","journal-title":"Int J Comput Vis"},{"key":"2347_CR19","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern, pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2347_CR20","unstructured":"Jain A, Tompson J, Andriluka M, Taylor GW, Bregler C (2014) Learning human pose estimation features with convolutional networks. In: International conference on learning representations. arXiv:1312.7302"},{"key":"2347_CR21","doi-asserted-by":"publisher","unstructured":"Johnson S, Everingham M (2010) Clustered pose and nonlinear appearance models for human pose estimation. In: British machine vision conference, pp 12.1\u201312.11. https:\/\/doi.org\/10.5244\/C.24.12","DOI":"10.5244\/C.24.12"},{"key":"2347_CR22","doi-asserted-by":"publisher","unstructured":"Johnson S, Everingham M (2011) Learning effective human pose estimation from inaccurate annotation. In: IEEE conference on computer vision and pattern, pp 1465\u20131472. https:\/\/doi.org\/10.1109\/CVPR.2011.5995318","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"2347_CR23","doi-asserted-by":"crossref","unstructured":"Kiefel M, Gehler PV (2014) Human pose estimation with fields of parts. In: European conference on computer vision, pp 331\u2013346","DOI":"10.1007\/978-3-319-10602-1_22"},{"key":"2347_CR24","doi-asserted-by":"crossref","unstructured":"Kokkinos I (2012) bounding part scores for rapid detection with deformable part models. In: European conference on computer vision, vol 7585 LNCS, pp 41\u201350","DOI":"10.1007\/978-3-642-33885-4_5"},{"issue":"1","key":"2347_CR25","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11263-014-0767-8","volume":"113","author":"S Li","year":"2015","unstructured":"Li S, Liu ZQ, Chan AB (2015) Heterogeneous multi-task learning for human pose estimation with deep convolutional neural network. Int J Comput Vis 113(1):19\u201336. https:\/\/doi.org\/10.1007\/s11263-014-0767-8. arXiv:1406.3474","journal-title":"Int J Comput Vis"},{"key":"2347_CR26","doi-asserted-by":"crossref","unstructured":"Lifshitz I, Fetaya E, Ullman S (2016) Human pose estimation using deep consensus voting. In: European conference on computer vision, pp 246\u2013260","DOI":"10.1007\/978-3-319-46475-6_16"},{"issue":"6","key":"2347_CR27","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1007\/s12652-014-0243-x","volume":"5","author":"T Liu","year":"2014","unstructured":"Liu T, Liu J, Xm Luo (2014) Radio tomographic imaging based body pose sensing for fall detection. J Ambient Intell Humaniz Comput 5(6):897\u2013907","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"2347_CR28","doi-asserted-by":"publisher","unstructured":"Mori G, Malik J (2002) Estimating human body configurations using shape context matching. In: European conference on computer vision, pp 666\u2013680. https:\/\/doi.org\/10.1007\/3-540-47977-5","DOI":"10.1007\/3-540-47977-5"},{"key":"2347_CR29","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1109\/ICPR.1994.576366","volume":"1","author":"T Ojala","year":"1994","unstructured":"Ojala T, Pietikainen M, Harwood D (1994) Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. Int Conf Pattern Recogn 1:582\u2013585. https:\/\/doi.org\/10.1109\/ICPR.1994.576366","journal-title":"Int Conf Pattern Recogn"},{"key":"2347_CR30","doi-asserted-by":"crossref","unstructured":"Ouyang W, Chu X, Wang X (2014) Multi-source deep learning for human pose estimation. In: IEEE conference on computer vision and pattern, pp 2329\u20132336","DOI":"10.1109\/CVPR.2014.299"},{"key":"2347_CR31","doi-asserted-by":"publisher","unstructured":"Pishchulin L, Andriluka M, Gehler P, Schiele B (2013a) Poselet conditioned pictorial structures. In: IEEE conference on computer vision and pattern, pp 588\u2013595. https:\/\/doi.org\/10.1109\/CVPR.2013.82","DOI":"10.1109\/CVPR.2013.82"},{"key":"2347_CR32","doi-asserted-by":"crossref","unstructured":"Pishchulin L, Andriluka M, Gehler P, Schiele B (2013b) Strong appearance and expressive spatial models for human pose estimation. In: International conference on computer vision, pp 3487\u20133494","DOI":"10.1109\/ICCV.2013.433"},{"key":"2347_CR33","doi-asserted-by":"publisher","unstructured":"Pishchulin L, Insafutdinov E, Tang S, Andres B, Andriluka M, Gehler P, Schiele B (2016) DeepCut: joint subset partition and labeling for multi person pose estimation. In: IEEE conference on computer vision and pattern, pp 4929\u20134937. https:\/\/doi.org\/10.1109\/CVPR.2016.533","DOI":"10.1109\/CVPR.2016.533"},{"key":"2347_CR34","doi-asserted-by":"crossref","unstructured":"Pishchulin L, Jain A, Andriluka M, Thorm\u00e4hlen T, Schiele B (2012) Articulated people detection and pose estimation: reshaping the future. In: IEEE Conference on computer vision and pattern, pp 3178\u20133185","DOI":"10.1109\/CVPR.2012.6248052"},{"key":"2347_CR35","doi-asserted-by":"publisher","unstructured":"Rafi U, Leibe B, Gall J, Kostrikov I (2016) An efficient convolutional network for human pose estimation. In: British machine vision conference, pp 109.1\u2013109.11. https:\/\/doi.org\/10.5244\/C.30.109","DOI":"10.5244\/C.30.109"},{"key":"2347_CR36","doi-asserted-by":"crossref","unstructured":"Ramakrishna V, Munoz D, Hebert M, Andrew Bagnell J, Sheikh Y (2014) Pose machines: articulated pose estimation via inference machines. In: European conference on computer vision, vol 8690 LNCS, pp 33\u201347","DOI":"10.1007\/978-3-319-10605-2_3"},{"key":"2347_CR37","doi-asserted-by":"publisher","unstructured":"Rogez G, Rihan J, Ramalingam S, Orrite C, Torr PH (2008) Randomized trees for human pose detection. In: IEEE conference on computer vision and pattern, pp 1\u20138. https:\/\/doi.org\/10.1109\/CVPR.2008.4587617","DOI":"10.1109\/CVPR.2008.4587617"},{"issue":"3","key":"2347_CR38","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"2347_CR39","doi-asserted-by":"publisher","unstructured":"Shakhnarovich G, Viola P, Darrell T (2003) Fast pose estimation with parameter-sensitive hashing. In: International conference on computer vision, pp 750\u2013757 vol. 2. https:\/\/doi.org\/10.1109\/ICCV.2003.1238424","DOI":"10.1109\/ICCV.2003.1238424"},{"issue":"18","key":"2347_CR40","doi-asserted-by":"publisher","first-page":"23193","DOI":"10.1007\/s11042-018-5617-1","volume":"77","author":"F Shamsafar","year":"2018","unstructured":"Shamsafar F, Ebrahimnezhad H (2018) Understanding holistic human pose using class-specific convolutional neural network. Multimed Tools Appl 77(18):23193\u201323225. https:\/\/doi.org\/10.1007\/s11042-018-5617-1","journal-title":"Multimed Tools Appl"},{"key":"2347_CR41","doi-asserted-by":"publisher","unstructured":"Sun X, Shang J, Liang S, Wei Y (2017) Compositional human pose regression. In: International conference on computer vision, pp 2621\u20132630. https:\/\/doi.org\/10.1109\/ICCV.2017.284. arXiv:1704.00159","DOI":"10.1109\/ICCV.2017.284"},{"key":"2347_CR42","unstructured":"Tompson J, 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":"2347_CR43","doi-asserted-by":"publisher","unstructured":"Toshev A, Szegedy C (2014) DeepPose: human pose estimation via deep neural networks. In: IEEE conference on computer vision and pattern, pp 1653\u20131660. https:\/\/doi.org\/10.1109\/CVPR.2014.214","DOI":"10.1109\/CVPR.2014.214"},{"key":"2347_CR44","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.cviu.2018.02.003","volume":"170","author":"N Ukita","year":"2018","unstructured":"Ukita N, Uematsu Y (2018) Semi-and weakly-supervised human pose estimation. Comput Vis Image Underst 170:67\u201378","journal-title":"Comput Vis Image Underst"},{"key":"2347_CR45","doi-asserted-by":"publisher","unstructured":"Vedaldi A, Lenc K (2015) MatConvNet: convolutional neural networks for MATLAB. In: ACM international conference on multimedia, pp 689\u2013692. https:\/\/doi.org\/10.1145\/2733373.2807412. http:\/\/www.vlfeat.org\/matconvnet\/","DOI":"10.1145\/2733373.2807412"},{"key":"2347_CR46","doi-asserted-by":"crossref","unstructured":"Wang F, Li Y (2013) beyond physical connections: tree models in human pose estimation. In: IEEE conference on computer vision and pattern, pp 596\u2013603","DOI":"10.1109\/CVPR.2013.83"},{"key":"2347_CR47","doi-asserted-by":"publisher","unstructured":"Wei SE, Ramakrishna V, Kanade T, Sheikh Y (2016) Convolutional pose machines. In: IEEE conference on computer vision and pattern, pp 4724\u20134732. https:\/\/doi.org\/10.1109\/CVPR.2016.511","DOI":"10.1109\/CVPR.2016.511"},{"key":"2347_CR48","first-page":"20","volume":"20","author":"C Yan","year":"2020","unstructured":"Yan C, Gong B, Wei Y, Gao Y (2020a) Deep multi-view enhancement hashing for image retrieval. IEEE Trans Pattern Anal Mach Intell 20:20","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2347_CR49","first-page":"20","volume":"20","author":"C Yan","year":"2020","unstructured":"Yan C, Shao B, Zhao H, Ning R, Zhang Y, Xu F (2020b) 3d room layout estimation from a single RGB image. IEEE Trans Multimed 20:20","journal-title":"IEEE Trans Multimed"},{"issue":"12","key":"2347_CR50","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"32","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 32(12):2878\u20132890","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2347_CR51","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: IEEE conference on computer vision and pattern, pp 3073\u20133082","DOI":"10.1109\/CVPR.2016.335"},{"key":"2347_CR52","doi-asserted-by":"crossref","unstructured":"Yu X, Zhou F, Chandraker M (2016) Deep deformation network for object landmark localization. In: European conference on computer vision, vol 9909 LNCS, pp 52\u201370. arXiv:1605.01014","DOI":"10.1007\/978-3-319-46454-1_4"},{"key":"2347_CR53","first-page":"1","volume":"20","author":"LA Zavala-Mondragon","year":"2019","unstructured":"Zavala-Mondragon LA, Lamichhane B, Zhang L, de Haan G (2019) CNN-skelpose: a CNN-based skeleton estimation algorithm for clinical applications. J Ambient Intell Human Comput 20:1\u201312","journal-title":"J Ambient Intell Human Comput"},{"key":"2347_CR54","doi-asserted-by":"crossref","unstructured":"Zhou X, Sun X, Zhang W, Liang S, Wei Y (2016) Deep kinematic pose regression. In: European conference on computer vision workshop, vol 9915 LNCS, pp 186\u2013201. arXiv:1609.05317","DOI":"10.1007\/978-3-319-49409-8_17"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-020-02347-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-020-02347-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-020-02347-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T23:25:05Z","timestamp":1627428305000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-020-02347-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,28]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["2347"],"URL":"https:\/\/doi.org\/10.1007\/s12652-020-02347-7","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,28]]},"assertion":[{"value":"16 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Faranak Shamsafar declares that she has no conflict of interest. Hossein Ebrahimnezhad declares that he has no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This research received no specific grant from any funding agency in the public, commercial, or non-profit sectors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Funding"}}]}}