{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:41:12Z","timestamp":1776688872488,"version":"3.51.2"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:00:00Z","timestamp":1578009600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:00:00Z","timestamp":1578009600000},"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":["Front. Comput. Sci."],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1007\/s11704-019-8266-2","type":"journal-article","created":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T05:28:33Z","timestamp":1578029313000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Multipath affinage stacked\u2014hourglass networks for human pose estimation"],"prefix":"10.1007","volume":"14","author":[{"given":"Guoguang","family":"Hua","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiguang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,3]]},"reference":[{"issue":"2","key":"8266_CR1","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11704-016-6066-5","volume":"11","author":"K Chen","year":"2017","unstructured":"Chen K, Ding G, Han J. Attribute-based supervised deep learning model for action recognition. Frontiers of Computer Science, 2017, 11(2): 219\u2013229","journal-title":"Frontiers of Computer Science"},{"key":"8266_CR2","doi-asserted-by":"crossref","unstructured":"Varior R R, Shuai B, Lu J. A siamese long short-term memory architecture for human re-identification. In: Proceedings of European Conference on Computer Vision. 2016, 135\u2013153","DOI":"10.1007\/978-3-319-46478-7_9"},{"key":"8266_CR3","doi-asserted-by":"crossref","unstructured":"Sapp B, Taskar B. MODEC: multimodal decomposable models for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2013, 3674\u20133681","DOI":"10.1109\/CVPR.2013.471"},{"key":"8266_CR4","doi-asserted-by":"crossref","unstructured":"Felzenszwalb P, Mcallester D, Ramanan D. A discriminatively trained, multiscale, deformable part model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2008","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"8266_CR5","doi-asserted-by":"crossref","unstructured":"Pishchulin L, Andriluka M, Gehler P. Strong appearance and expressive spatial models for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. 2014, 3487\u20133494","DOI":"10.1109\/ICCV.2013.433"},{"key":"8266_CR6","doi-asserted-by":"crossref","unstructured":"Johnson S, Everingham M. Learning effective human pose estimation from inaccurate annotation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2011, 1465\u20131472","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"8266_CR7","doi-asserted-by":"crossref","unstructured":"Ouyang W, Chu X, Wang X. Multi-source deep learning for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014, 2329\u20132336","DOI":"10.1109\/CVPR.2014.299"},{"key":"8266_CR8","doi-asserted-by":"crossref","unstructured":"Ladicky L, Torr P H S, Zisserman A. Human pose estimation using a joint pixel-wise and part-wise formulation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2013, 3578\u20133585","DOI":"10.1109\/CVPR.2013.459"},{"key":"8266_CR9","doi-asserted-by":"crossref","unstructured":"Liu S G, Li Y, Hua G. Human pose estimation in video via structured space learning and halfway temporal evaluation. IEEE Transactions on Circuits and Systems for Video Technology. 2018, 1","DOI":"10.1109\/TCSVT.2018.2858828"},{"key":"8266_CR10","unstructured":"Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems. 2012, 1097\u20131105"},{"key":"8266_CR11","unstructured":"Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of International Conference on Machine Learning. 2015, 448\u2013456"},{"key":"8266_CR12","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"8266_CR13","unstructured":"Li Y, Liu S G. Temporal-coherency-aware human pose estimation in video via pre-trained res-net and flow-CNN. In: Proceedings of International Conference on Computer Animation and Social Agents. 2017, 150\u2013159"},{"key":"8266_CR14","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. 2010, 1\u201311","DOI":"10.5244\/C.24.12"},{"key":"8266_CR15","doi-asserted-by":"crossref","unstructured":"Andriluka M, Pishchulin L, Gehler P. 2D Human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014, 3686\u20133693","DOI":"10.1109\/CVPR.2014.471"},{"key":"8266_CR16","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J. Stacked hourglass networks forhuman pose estimation. In: Proceedings of European Conference on Computer Vision. 2016, 483\u2013499","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"8266_CR17","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. 2015, 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"8266_CR18","doi-asserted-by":"crossref","unstructured":"Andriluka M, Roth S, Schiele B. Pictorial structures revisited: people detection and articulated pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2009, 1014\u20131021","DOI":"10.1109\/CVPR.2009.5206754"},{"key":"8266_CR19","doi-asserted-by":"crossref","unstructured":"Andriluka M, Roth S, Schiele B. Monocular 3D pose estimation and tracking by detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2010, 623\u2013630","DOI":"10.1109\/CVPR.2010.5540156"},{"issue":"6","key":"8266_CR20","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1049\/iet-cvi.2016.0249","volume":"11","author":"Q Lopez","year":"2017","unstructured":"Lopez Q, Manuel I. Mixing body-parts model for 2D human pose estimation in stereo videos. IET Computer Vision, 2017, 11(6): 426\u2013433","journal-title":"IET Computer Vision"},{"key":"8266_CR21","unstructured":"Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2005, 886\u2013893"},{"issue":"4","key":"8266_CR22","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1049\/iet-cvi.2017.0146","volume":"12","author":"E Dogan","year":"2018","unstructured":"Dogan E, Eren G, Wolf C. Multi-view pose estimation with mixtures-of-parts and adaptive viewpoint selection. IET Computer Vision, 2018, 12(4): 403\u2013411","journal-title":"IET Computer Vision"},{"key":"8266_CR23","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. 2014, 1653\u20131660","DOI":"10.1109\/CVPR.2014.214"},{"key":"8266_CR24","doi-asserted-by":"crossref","unstructured":"Tompson J, Goroshin R, Jain A. Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 648\u2013656","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"8266_CR25","unstructured":"Tompson J, Jain A, LeCun Y. Joint training of a convolutional network and a graphical model for human pose estimation. In: Proceedings of the 28th Annual Conference on Neural Information Processing Systems. 2014, 1799\u20131807"},{"key":"8266_CR26","doi-asserted-by":"crossref","unstructured":"Carreira J, Agrawal P, Fragkiadaki K. Human pose estimation with iterative error feedback. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 4733\u20134742","DOI":"10.1109\/CVPR.2016.512"},{"key":"8266_CR27","doi-asserted-by":"crossref","unstructured":"Wei S E, Ramakrishna V, Kanade T. Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 4724\u20134732","DOI":"10.1109\/CVPR.2016.511"},{"key":"8266_CR28","doi-asserted-by":"crossref","unstructured":"Cao Z, Simon T, ShihEn W. Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 1302\u20131310","DOI":"10.1109\/CVPR.2017.143"},{"key":"8266_CR29","doi-asserted-by":"crossref","unstructured":"Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 1520\u20131528","DOI":"10.1109\/ICCV.2015.178"},{"key":"8266_CR30","doi-asserted-by":"crossref","unstructured":"Rematas K, Ritschel T, Fritz M. Deep reflectance maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 4508\u2013s4516","DOI":"10.1109\/CVPR.2016.488"},{"key":"8266_CR31","doi-asserted-by":"crossref","unstructured":"He K M, Zhang X, Ren S. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8266_CR32","unstructured":"Jaderberg M, Simonyan K, Zisserman A. Spatial transformer networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems. 2015, 2017\u20132025"},{"key":"8266_CR33","doi-asserted-by":"crossref","unstructured":"Ferrari V, Marin M, Zisserman A. Progressive search space reduction for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2008, 1\u20138","DOI":"10.1109\/CVPR.2008.4587468"},{"key":"8266_CR34","doi-asserted-by":"crossref","unstructured":"Yang W, Li S, Ouyang W. Learning feature pyramids for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 1281\u20131290","DOI":"10.1109\/ICCV.2017.144"},{"issue":"12","key":"8266_CR35","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. Articulated human detection with flexible mixtures of parts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12): 2878\u20132890","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"8266_CR36","doi-asserted-by":"crossref","unstructured":"Yu X, Zhou F, Chandraker M. Deep deformation network for object landmark localization. In: Proceedings of European Conference on Computer Vision. 2016, 52\u201370","DOI":"10.1007\/978-3-319-46454-1_4"},{"key":"8266_CR37","doi-asserted-by":"crossref","unstructured":"Belagiannis V, Zisserman A. Recurrent human pose estimation. In: Proceedings of the International Conference on Automatic Face and Gesture Recognition. 2017, 468\u2013475","DOI":"10.1109\/FG.2017.64"},{"key":"8266_CR38","doi-asserted-by":"crossref","unstructured":"Lifshitz I, Fetaya E, Ullman S. Human pose estimation using deep consensus voting. In: Proceedings of European Conference on Computer Vision. 2016, 246\u2013260","DOI":"10.1007\/978-3-319-46475-6_16"},{"key":"8266_CR39","doi-asserted-by":"crossref","unstructured":"Pishchulin L, Insafutdinov E, Tang S. Deepcut: joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 4929\u20134937","DOI":"10.1109\/CVPR.2016.533"},{"key":"8266_CR40","doi-asserted-by":"crossref","unstructured":"Insafutdinov E, Pishchulin L, Andres B. Deepercut: a deeper, stronger, and faster multi-person pose estimation model. In: Proceedings of the 14th European Conference on Computer Vision. 2016, 34\u201350","DOI":"10.1007\/978-3-319-46466-4_3"},{"key":"8266_CR41","doi-asserted-by":"crossref","unstructured":"Hu P, Ramanan D. Bottom-up and top-down reasoning with hierarchical rectified gaussians. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 5600\u20135609","DOI":"10.1109\/CVPR.2016.604"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-019-8266-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-019-8266-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-019-8266-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T20:12:18Z","timestamp":1665346338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-019-8266-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,3]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["8266"],"URL":"https:\/\/doi.org\/10.1007\/s11704-019-8266-2","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,3]]},"assertion":[{"value":"1 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"144701"}}