{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:49Z","timestamp":1740122869283,"version":"3.37.3"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2018,12,13]],"date-time":"2018-12-13T00:00:00Z","timestamp":1544659200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61503017","61702150"],"award-info":[{"award-number":["61503017","61702150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["2016ZC51022"],"award-info":[{"award-number":["2016ZC51022"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s11042-018-6964-7","type":"journal-article","created":{"date-parts":[[2018,12,13]],"date-time":"2018-12-13T01:17:02Z","timestamp":1544663822000},"page":"16077-16096","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multiple human upper bodies detection via candidate-region convolutional neural network"],"prefix":"10.1007","volume":"78","author":[{"given":"Aichun","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6972-5534","authenticated-orcid":false,"given":"Tian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,13]]},"reference":[{"key":"6964_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka M, Roth S, Schiele B (2010) Monocular 3d pose estimation and tracking by detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 623\u2013630","DOI":"10.1109\/CVPR.2010.5540156"},{"key":"6964_CR2","volume-title":"Pattern recognition and machine learning","author":"CM Bishop","year":"2006","unstructured":"Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin"},{"key":"6964_CR3","doi-asserted-by":"crossref","unstructured":"Chen B, Yang Z, Huang S, Du X, Cui Z, Bhimani J, Xie X, Mi N (2017) Cyber-physical system enabled nearby traffic flow modelling for autonomous vehicles. In: IEEE International PERFORMANCE computing and communications conference, pp 1\u20136","DOI":"10.1109\/PCCC.2017.8280498"},{"key":"6964_CR4","doi-asserted-by":"publisher","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol 1, pp 886\u2013893. \n                    https:\/\/doi.org\/10.1109\/CVPR.2005.177","DOI":"10.1109\/CVPR.2005.177"},{"key":"6964_CR5","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Li FF (2009) Imagenet: a large-scale hierarchical image database. In: IEEE Conference on computer vision and pattern recognition, 2009. CVPR 2009., pp 248\u2013255"},{"issue":"2","key":"6964_CR6","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1109\/TIP.2015.2507445","volume":"25","author":"M Ding","year":"2015","unstructured":"Ding M, Fan G (2015) Articulated and generalized gaussian kernel correlation for human pose estimation. IEEE Trans Image Process 25(2):776\u2013789","journal-title":"IEEE Trans Image Process"},{"issue":"11","key":"6964_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCYB.2014.2373393","volume":"45","author":"M Ding","year":"2015","unstructured":"Ding M, Fan G (2015) Multilayer joint gait-pose manifolds for human gait motion modeling. IEEE Trans Cybern 45(11):1\u20138","journal-title":"IEEE Trans Cybern"},{"key":"6964_CR8","unstructured":"Ding X, Xu H, Cui P, Sun L (2009) A cascade svm approach for head-shoulder detection using histograms of oriented gradients. In: IEEE International symposium on circuits and systems, pp 1791\u20131794"},{"key":"6964_CR9","doi-asserted-by":"crossref","unstructured":"Duan K, Batra D, Crandall DJ (2012) A multi-layer composite model for human pose estimation. In: BMVC, pp 1\u201311","DOI":"10.5244\/C.26.116"},{"issue":"2","key":"6964_CR10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"key":"6964_CR11","unstructured":"Fan X, Zheng K, Lin Y, Wang S (2015) Combining local appearance and holistic view: Dual-source deep neural networks for human pose estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"issue":"22","key":"6964_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-016-3316-3","volume":"75","author":"Z Fang","year":"2016","unstructured":"Fang Z, Fei F, Fang Y, Lee C, Xiong N, Shu L, Chen S (2016) Abnormal event detection in crowded scenes based on deep learning. Multimed Tools Appl 75(22):1\u201323","journal-title":"Multimed Tools Appl"},{"issue":"9","key":"6964_CR13","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb PF, Girshick R, McAllester D, Ramanan D (2010) 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"},{"issue":"1","key":"6964_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. \n                    https:\/\/doi.org\/10.1023\/B:VISI.0000042934.15159.49","journal-title":"Int J Comput Vis"},{"key":"6964_CR15","unstructured":"Fischler MA, Elschlager RA (1973) The representation and matching of pictorial structures. IEEE Transactions on computers 22(1):67\u201392"},{"key":"6964_CR16","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2014.81"},{"key":"6964_CR17","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: International conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2015.169"},{"key":"6964_CR18","unstructured":"Glauner PO (2015) Deep convolutional neural networks for smile recognition. arXiv:\n                    1508.06535"},{"key":"6964_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Computer vision\u2013ECCV 2014. Springer, pp 346\u2013361","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"6964_CR20","doi-asserted-by":"crossref","unstructured":"Hoai M, Zisserman A (2014) Talking heads: Detecting humans and recognizing their interactions. In: IEEE Computer vision and pattern recognition","DOI":"10.1109\/CVPR.2014.117"},{"key":"6964_CR21","doi-asserted-by":"crossref","unstructured":"Jarrett K, Kavukcuoglu K, Ranzato M, LeCun Y (2009) What is the best multi-stage architecture for object recognition?. In: Proceedings of International conference on computer vision (ICCV\u201909). IEEE","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"6964_CR22","doi-asserted-by":"publisher","unstructured":"Jiang H, Martin D (2008) Global pose estimation using non-tree models. In: 2008. CVPR 2008. IEEE conference on Computer vision and pattern recognition, pp 1\u20138. \n                    https:\/\/doi.org\/10.1109\/CVPR.2008.4587457","DOI":"10.1109\/CVPR.2008.4587457"},{"key":"6964_CR23","unstructured":"Karpagavalli P, Ramprasad AV (2016) An adaptive hybrid gmm for multiple human detection in crowd scenario. Multimedia Tools & Applications 76(12):1\u201321"},{"key":"6964_CR24","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"6964_CR25","doi-asserted-by":"publisher","unstructured":"Kumar M, Zisserman A, Torr P (2009) Efficient discriminative learning of parts-based models. In: Proceedings of International Conference on Computer Vision (ICCV), pp 552\u2013559. \n                    https:\/\/doi.org\/10.1109\/ICCV.2009.5459192","DOI":"10.1109\/ICCV.2009.5459192"},{"key":"6964_CR26","doi-asserted-by":"publisher","unstructured":"LeCun Y, Huang FJ, Bottou L (2004) Learning methods for generic object recognition with invariance to pose and lighting. In: 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol 2, pp II\u201397\u2013104. \n                    https:\/\/doi.org\/10.1109\/CVPR.2004.1315150","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"6964_CR27","doi-asserted-by":"publisher","unstructured":"Lee H, Grosse R, Ranganath R, Ng AY (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML \u201909. ACM, pp 609\u2013616. \n                    https:\/\/doi.org\/10.1145\/1553374.1553453","DOI":"10.1145\/1553374.1553453"},{"key":"6964_CR28","doi-asserted-by":"crossref","unstructured":"Li M, Zhang Z, Huang K, Tan T (2009) Rapid and robust human detection and tracking based on omega-shape features, pp 2545\u20132548","DOI":"10.1109\/ICIP.2009.5414008"},{"key":"6964_CR29","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6964_CR30","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2015) You only look once: Unified, real-time object detection, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"6964_CR31","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2016) Yolo9000: Better, faster, stronger, pp 6517\u20136525","DOI":"10.1109\/CVPR.2017.690"},{"issue":"99","key":"6964_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2017.2753830","volume":"PP","author":"Y Liu","year":"2017","unstructured":"Liu Y, Wu Q, Tang L, Shi H (2017) Gaze-assisted multi-stream deep neural network for action recognition. IEEE Access PP (99):1\u20131. \n                    https:\/\/doi.org\/10.1109\/ACCESS.2017.2753830","journal-title":"IEEE Access"},{"key":"6964_CR33","unstructured":"Long J, Shelhamer E, Darrell T (2014) Fully convolutional networks for semantic segmentation. arXiv:\n                    1411.4038"},{"key":"6964_CR34","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. In: 1999. The proceedings of the seventh IEEE international conference on Computer vision. IEEE, vol 2, pp 1150\u20131157"},{"issue":"99","key":"6964_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2017.2689058","volume":"PP","author":"C Meng","year":"2017","unstructured":"Meng C, Zhao X (2017) Webcam-based eye movement analysis using cnn. IEEE Access PP(99):1\u20131. \n                    https:\/\/doi.org\/10.1109\/ACCESS.2017.2754299","journal-title":"IEEE Access"},{"issue":"12","key":"6964_CR36","doi-asserted-by":"publisher","first-page":"2441","DOI":"10.1109\/TPAMI.2012.24","volume":"34","author":"A Patron-Perez","year":"2012","unstructured":"Patron-Perez A, Marszalek M, Reid I, Zisserman A (2012) Structured learning of human interactions in tv shows. IEEE Trans Pattern Anal Mach Intell 34(12):2441\u201353","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"6964_CR37","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, Girshick R, Girshick R, Sun J (2017) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6964_CR38","doi-asserted-by":"crossref","unstructured":"Roh MC, Lee JY (2017) Refining faster-rcnn for accurate object detection. In: Fifteenth iapr international conference on machine vision applications","DOI":"10.23919\/MVA.2017.7986913"},{"key":"6964_CR39","doi-asserted-by":"crossref","unstructured":"Sapp B, Toshev A, Taskar B (2010) Cascaded models for articulated pose estimation. In: Proceedings of European Conference on Computer Vision (ECCV), ECCV\u201910. Springer-Verlag, Berlin, pp 406\u2013420. \n                    http:\/\/dl.acm.org\/citation.cfm?id=1888028.1888060","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"6964_CR40","doi-asserted-by":"publisher","unstructured":"Sapp B, Taskar B (2013) Modec: Multimodal decomposable models for human pose estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3674\u20133681. \n                    https:\/\/doi.org\/10.1109\/CVPR.2013.471\n                    \n                  . \n                    http:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=6619315","DOI":"10.1109\/CVPR.2013.471"},{"key":"6964_CR41","unstructured":"Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2014) Overfeat: Integrated recognition, localization and detection using convolutional networks. In: International Conference on Learning Representations (ICLR 2014). CBLS. \n                    http:\/\/openreview.net\/document\/d332e77d-459a-4af8-b3ed-55ba"},{"key":"6964_CR42","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Computer Science"},{"key":"6964_CR43","doi-asserted-by":"publisher","unstructured":"Sun M, Savarese S (2011) Articulated part-based model for joint object detection and pose estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ICCV \u201911. IEEE Computer Society, Washington, pp 723\u2013730. \n                    https:\/\/doi.org\/10.1109\/ICCV.2011.6126309","DOI":"10.1109\/ICCV.2011.6126309"},{"key":"6964_CR44","unstructured":"Szegedy C, Toshev A, Erhan D (2013) Deep neural networks for object detection. In: Burges C, Bottou L, Welling M, Ghahramani Z, Weinberger K (eds) Advances in Neural Information Processing Systems, vol 26, pp 2553\u20132561"},{"key":"6964_CR45","doi-asserted-by":"publisher","unstructured":"Tian TP, Sclaroff S (2010) Fast globally optimal 2d human detection with loopy graph models. In: 2010 IEEE conference on Computer vision and pattern recognition (CVPR), pp 81\u201388. \n                    https:\/\/doi.org\/10.1109\/CVPR.2010.5540227","DOI":"10.1109\/CVPR.2010.5540227"},{"key":"6964_CR46","doi-asserted-by":"crossref","unstructured":"Tsochantaridis I, Hofmann T, Joachims T, Altun Y (2004) Support vector machine learning for interdependent and structured output spaces. In: Proceedings of the twenty-first international conference on Machine learning. ACM, pp 104","DOI":"10.1145\/1015330.1015341"},{"key":"6964_CR47","doi-asserted-by":"publisher","unstructured":"Uijlings J, van de Sande K, Gevers T, Smeulders A (2013) Selective search for object recognition. In: International Journal of Computer Vision. Springer, US, vol 104, pp 154\u2013171. \n                    https:\/\/doi.org\/10.1007\/s11263-013-0620-5","DOI":"10.1007\/s11263-013-0620-5"},{"key":"6964_CR48","doi-asserted-by":"publisher","unstructured":"Wang F, Li Y (2013) Beyond physical connections: Tree models in human pose estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 596\u2013603. \n                    https:\/\/doi.org\/10.1109\/CVPR.2013.83\n                    \n                  . \n                    http:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=6618927","DOI":"10.1109\/CVPR.2013.83"},{"key":"6964_CR49","doi-asserted-by":"publisher","unstructured":"Wang Y, Tran D, Liao Z (2011) Learning hierarchical poselets for human parsing. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR \u201911. IEEE Computer Society, Washington, pp 1705\u20131712. \n                    https:\/\/doi.org\/10.1109\/CVPR.2011.5995519","DOI":"10.1109\/CVPR.2011.5995519"},{"key":"6964_CR50","unstructured":"Xie X, Liu S, Yang C, Yang Z, Xu J, Zhai X (2017) The application of smart materials in tactile actuators for tactile information delivery . arXiv:\n                    1708.07077"},{"issue":"3","key":"6964_CR51","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1007\/s11042-014-2177-x","volume":"74","author":"R Xu","year":"2015","unstructured":"Xu R, Guan Y, Huang Y (2015) Multiple human detection and tracking based on head detection for real-time video surveillance. Multimed Tools Appl 74(3):729\u2013742","journal-title":"Multimed Tools Appl"},{"key":"6964_CR52","doi-asserted-by":"crossref","unstructured":"Yang Y, Ramanan D (2011) Articulated pose estimation with flexible mixtures-of-parts. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1385\u20131392","DOI":"10.1109\/CVPR.2011.5995741"},{"issue":"1","key":"6964_CR53","doi-asserted-by":"publisher","first-page":"35","DOI":"10.5573\/IEIESPC.2015.4.1.035","volume":"4","author":"HJ Yoo","year":"2015","unstructured":"Yoo HJ (2015) Deep convolution neural networks in computer vision. IEIE Trans Smart Process Comput 4(1):35\u201343","journal-title":"IEIE Trans Smart Process Comput"},{"key":"6964_CR54","doi-asserted-by":"crossref","unstructured":"Zhang N, Donahue J, Girshick R, Darrell T (2014) Part-based r-cnns for fine-grained category detection. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision ECCV 2014, Lecture Notes in Computer Science, vol 8689. Springer International Publishing, pp 834\u2013849","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"6964_CR55","doi-asserted-by":"crossref","unstructured":"Zhu A, Snoussi H, Cherouat A (2015) Articulated pose estimation via multiple mixture parts model. In: 2015 12th IEEE international conference on Advanced video and signal based surveillance (AVSS). IEEE, pp 1\u20135","DOI":"10.1109\/AVSS.2015.7301801"},{"issue":"4","key":"6964_CR56","doi-asserted-by":"publisher","first-page":"043,021","DOI":"10.1117\/1.JEI.24.4.043021","volume":"24","author":"A Zhu","year":"2015","unstructured":"Zhu A, Snoussi H, Wang T, Cherouat A (2015) Human pose estimation with multiple mixture parts model based on upper body categories. J Electron Imaging 24(4):043,021. \n                    https:\/\/doi.org\/10.1117\/1.JEI.24.4.043021","journal-title":"J Electron Imaging"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6964-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6964-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6964-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T19:19:35Z","timestamp":1576178375000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6964-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,13]]},"references-count":56,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["6964"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6964-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2018,12,13]]},"assertion":[{"value":"3 December 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}