{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T08:00:24Z","timestamp":1774944024019,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2020,6,1]]},"DOI":"10.1587\/transinf.2019mvp0007","type":"journal-article","created":{"date-parts":[[2020,5,31]],"date-time":"2020-05-31T22:09:59Z","timestamp":1590962999000},"page":"1257-1264","source":"Crossref","is-referenced-by-count":4,"title":["Human Pose Annotation Using a Motion Capture System for Loose-Fitting Clothes"],"prefix":"10.1587","volume":"E103.D","author":[{"given":"Takuya","family":"MATSUMOTO","sequence":"first","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kodai","family":"SHIMOSATO","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"MAEDA","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"MURAKAMI","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koji","family":"MURAKOSO","sequence":"additional","affiliation":[{"name":"Zukun Lab, Toei Digital Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiko","family":"MINO","sequence":"additional","affiliation":[{"name":"Zukun Lab, Toei Digital Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norimichi","family":"UKITA","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] S.E. Wei, V. Ramakrishna, T. Kanade, and Y. Sheikh, \u201cConvolutional pose machines,\u201d CVPR, 2016. 10.1109\/CVPR.2016.511","DOI":"10.1109\/CVPR.2016.511"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] Z. Cao, T. Simon, S.E. Wei, and Y. Sheikh, \u201cRealtime multi-person 2d pose estimation using part affinity fields,\u201d CVPR, 2017. 10.1109\/CVPR.2017.143","DOI":"10.1109\/CVPR.2017.143"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] Y. Kawana, N. Ukita, J. Huang, and M. Yang, \u201cEnsemble convolutional neural networks for pose estimation,\u201d CVIU, vol.169, pp.62-74, April 2018. 10.1016\/j.cviu.2017.12.005","DOI":"10.1016\/j.cviu.2017.12.005"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] K. Sun, B. Xiao, D. Liu, and J. Wang, \u201cDeep high-resolution representation learning for human pose estimation,\u201d CVPR, 2019. 10.1109\/CVPR.2019.00584","DOI":"10.1109\/CVPR.2019.00584"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] E. Insafutdinov, M. Andriluka, L. Pishchulin, S. Tang, E. Levinkov, B. Andres, and B. Schiele, \u201cArttrack: Articulated multi-person tracking in the wild,\u201d CVPR, 2017. 10.1109\/CVPR.2017.142","DOI":"10.1109\/CVPR.2017.142"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] S. Johnson and M. Everingham, \u201cClustered pose and nonlinear appearance models for human pose estimation,\u201d BMVC, 2010. 10.5244\/C.24.12","DOI":"10.5244\/C.24.12"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] M. Andriluka, L. Pishchulin, P.V. Gehler, and B. Schiele, \u201c2d human pose estimation: New benchmark and state of the art analysis,\u201d CVPR, 2014. 10.1109\/CVPR.2014.471","DOI":"10.1109\/CVPR.2014.471"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] J. Charles, T. Pfister, M. Everingham, and A. Zisserman, \u201cAutomatic and efficient human pose estimation for sign language videos,\u201d IJCV, vol.110, no.1, pp.70-90, 2014. 10.1007\/s11263-013-0672-6","DOI":"10.1007\/s11263-013-0672-6"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] L. Sigal, A.O. Balan, and M.J. Black, \u201cHumaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion,\u201d IJCV, vol.87, no.1-2, pp.4-27, 2010. 10.1007\/s11263-009-0273-6","DOI":"10.1007\/s11263-009-0273-6"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] C. Ionescu, D. Papava, V. Olaru, and C. Sminchisescu, \u201cHuman3.6m: Large scale datasets and predictive methods for 3d human sensing in natural environments,\u201d PAMI, vol.36, no.7, pp.1325-1339, July 2014. 10.1109\/TPAMI.2013.248","DOI":"10.1109\/TPAMI.2013.248"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] T. Matsumoto, K. Shimosato, T. Maeda, T. Murakami, K. Murakoso, K. Mino, and N. Ukita, \u201cAutomatic human pose annotation for loose-fitting clothes,\u201d MVA, 2019.  10.23919\/MVA.2019.8757927","DOI":"10.23919\/MVA.2019.8757927"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] P.F. Felzenszwalb and D.P. Huttenlocher, \u201cPictorial structures for object recognition,\u201d IJCV, vol.61, no.1, pp.55-79, 2005. 10.1023\/B:VISI.0000042934.15159.49","DOI":"10.1023\/B:VISI.0000042934.15159.49"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] P.F. Felzenszwalb, R.B. Girshick, D.A. McAllester, and D. Ramanan, \u201cObject detection with discriminatively trained part-based models,\u201d PAMI, vol.32, no.9, pp.1627-1645, Sept. 2010. 10.1109\/TPAMI.2009.167","DOI":"10.1109\/TPAMI.2009.167"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] B. Sapp, A. Toshev, and B. Taskar, \u201cCascaded models for articulated pose estimation,\u201d ECCV, 2010. 10.1007\/978-3-642-15552-9_30","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] N. Ukita, \u201cArticulated pose estimation with parts connectivity using discriminative local oriented contours,\u201d CVPR, 2012. 10.1109\/CVPR.2012.6248049","DOI":"10.1109\/CVPR.2012.6248049"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake, \u201cReal-time human pose recognition in parts from single depth images,\u201d CVPR, 2011. 10.1109\/CVPR.2011.5995316","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, and C.L. Zitnick, \u201cMicrosoft COCO: common objects in context,\u201d ECCV, 2014. 10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] S. Johnson and M. Everingham, \u201cLearning effective human pose estimation from inaccurate annotation,\u201d CVPR, 2011. 10.1109\/CVPR.2011.5995318","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] D. Mehta, H. Rhodin, D. Casas, P. Fua, O. Sotnychenko, W. Xu, and C. Theobalt, \u201cMonocular 3d human pose estimation in the wild using improved CNN supervision,\u201d 3DV, 2017. 10.1109\/3DV.2017.00064","DOI":"10.1109\/3DV.2017.00064"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] R.A. G\u00fcler, N. Neverova, and I. Kokkinos, \u201cDensepose: Dense human pose estimation in the wild,\u201d CVPR, 2018. 10.1109\/CVPR.2018.00762","DOI":"10.1109\/CVPR.2018.00762"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] N. Ukita, R. Tsuji, and M. Kidode, \u201cReal-time shape analysis of a human body in clothing using time-series part-labeled volumes,\u201d ECCV, 2008. 10.1007\/978-3-540-88690-7_51","DOI":"10.1007\/978-3-540-88690-7_51"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] N. Ukita, M. Hirai, and M. Kidode, \u201cComplex volume and pose tracking with probabilistic dynamical models and visual hull constraints,\u201d ICCV, 2009. 10.1109\/ICCV.2009.5459298","DOI":"10.1109\/ICCV.2009.5459298"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[24] B. Xiao, H. Wu, and Y. Wei, \u201cSimple baselines for human pose estimation and tracking,\u201d ECCV, 2018. 10.1007\/978-3-030-01231-1_29","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[25] J.M. Wang, D.J. Fleet, and A. Hertzmann, \u201cGaussian process dynamical models for human motion,\u201d PAMI, vol.30, no.2, pp.283-298, Feb. 2008. 10.1109\/TPAMI.2007.1167","DOI":"10.1109\/TPAMI.2007.1167"},{"key":"25","doi-asserted-by":"publisher","unstructured":"[26] N. Ukita and T. Kanade, \u201cGaussian process motion graph models for smooth transitions among multiple actions,\u201d CVIU, vol.116, no.4, pp.500-509, 2012. 10.1016\/j.cviu.2011.11.005","DOI":"10.1016\/j.cviu.2011.11.005"},{"key":"26","doi-asserted-by":"publisher","unstructured":"[27] N. Ukita, \u201cSimultaneous particle tracking in multi-action motion models with synthesized paths,\u201d Image Vision Comput., vol.31, no.6-7, pp.448-459, 2013. 10.1016\/j.imavis.2012.09.010","DOI":"10.1016\/j.imavis.2012.09.010"},{"key":"27","unstructured":"[28] K. Morimoto, Y. Matsuyama, and N. Ukita, \u201cContinuous action recognition by action-specific motion models,\u201d MVA, pp.323-326, 2013."},{"key":"28","doi-asserted-by":"crossref","unstructured":"[29] D. Zhang, G. Guo, D. Huang, and J. Han, \u201cPoseflow: A deep motion representation for understanding human behaviors in videos,\u201d CVPR, 2018. 10.1109\/CVPR.2018.00707","DOI":"10.1109\/CVPR.2018.00707"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[30] H. Coskun, D.J. Tan, S. Conjeti, N. Navab, and F. Tombari, \u201cHuman motion analysis with deep metric learning,\u201d ECCV, 2018. 10.1007\/978-3-030-01264-9_41","DOI":"10.1007\/978-3-030-01264-9_41"},{"key":"30","doi-asserted-by":"publisher","unstructured":"[31] N. Ukita and Y. Uematsu, \u201cSemi- and weakly-supervised human pose estimation,\u201d CVIU, vol.170, pp.67-78, May 2018. 10.1016\/j.cviu.2018.02.003","DOI":"10.1016\/j.cviu.2018.02.003"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[32] M.R.I. Hossain and J.J. Little, \u201cExploiting temporal information for 3d human pose estimation,\u201d ECCV, 2018. 10.1007\/978-3-030-01249-6_5","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[33] R. Dabral, A. Mundhada, U. Kusupati, S. Afaque, A. Sharma, and A. Jain, \u201cLearning 3d human pose from structure and motion,\u201d ECCV, 2018. 10.1007\/978-3-030-01240-3_41","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[34] C. Li and G.H. Lee, \u201cGenerating multiple hypotheses for 3d human pose estimation with mixture density network,\u201d CVPR, 2019. 10.1109\/CVPR.2019.01012","DOI":"10.1109\/CVPR.2019.01012"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/6\/E103.D_2019MVP0007\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,6]],"date-time":"2020-06-06T03:27:50Z","timestamp":1591414070000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/6\/E103.D_2019MVP0007\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,1]]},"references-count":33,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2019mvp0007","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,1]]}}}