{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T04:46:54Z","timestamp":1794545214294,"version":"4.9.1"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319570204","type":"print"},{"value":"9783319570211","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-57021-1_9","type":"book-chapter","created":{"date-parts":[[2017,7,19]],"date-time":"2017-07-19T00:43:44Z","timestamp":1500425024000},"page":"273-301","source":"Crossref","is-referenced-by-count":8,"title":["Discriminative Hierarchical Part-Based Models for Human Parsing and Action Recognition"],"prefix":"10.1007","author":[{"given":"Yang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duan","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zicheng","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Forsyth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,7,20]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"M. Andriluka, S. Roth, B. Schiele, Pictorial structures revisited: people detection and articulated pose estimation, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009","DOI":"10.1109\/CVPR.2009.5206754"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"L. Bourdev, J. Malik, Poselets: body part detectors training using 3d human pose annotations, in IEEE International Conference on Computer Vision, 2009","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"L. Bourdev, S. Maji, T. Brox, J. Malik, Detecting people using mutually consistent poselet activations, in European Conference on Computer Vision, 2010","DOI":"10.1007\/978-3-642-15567-3_13"},{"issue":"3","key":"9_CR4","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1109\/TIT.1968.1054142","volume":"14","author":"CK Chow","year":"1968","unstructured":"C.K. Chow, C.N. Liu, Approximating discrete probability distributions with dependence trees. IEEE Trans. Inf. Theory 14(3), 462\u2013467 (1968)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"N. Dalal, B. Triggs, Histogram of oriented gradients for human detection, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005","DOI":"10.1109\/CVPR.2005.177"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"V. Delaitre, I. Laptev, J. Sivic, Recognizing human actions in still images: a study of bag-of-features and part-based representations, in British Machine Vision Conference, 2010","DOI":"10.5244\/C.24.97"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"C. Desai, D. Ramanan, C. Fowlkes, Discriminative models for static human-object interactions, in Workshop on Structured Models in Computer Vision, 2010","DOI":"10.1109\/CVPRW.2010.5543176"},{"key":"9_CR8","unstructured":"P. Doll\u00e1r, V. Rabaud, G. Cottrell, S. Belongie, Behavior recognition via sparse spatio-temporal features, in ICCV\u201905 Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"A.A. Efros, A.C. Berg, G. Mori, J. Malik, Recognizing action at a distance, in IEEE International Conference on Computer Vision, 2003, pp. 726\u2013733","DOI":"10.1109\/ICCV.2003.1238420"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"M. Eichner, V. Ferrari, Better appearance models for pictorial structures, in British Machine Vision Conference, 2009","DOI":"10.5244\/C.23.3"},{"issue":"1","key":"9_CR11","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"PF Felzenszwalb","year":"2005","unstructured":"P.F. Felzenszwalb, D.P. Huttenlocher, Pictorial structures for object recognition. Int. J. Comput. Vis. 61(1), 55\u201379 (2005)","journal-title":"Int. J. Comput. Vis."},{"issue":"9","key":"9_CR12","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"P.F. Felzenszwalb, R.B. Girshick, D. McAllester, D. Ramanan, Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"V. Ferrari, M. Mar\u00edn-Jim\u00e9nez, A. Zisserman, Progressive search space reduction for human pose estimation, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008","DOI":"10.1109\/CVPR.2008.4587468"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"V. Ferrari, M. Mar\u00edn-Jim\u00e9nez, A. Zisserman, Pose search: retrieving people using their pose, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009","DOI":"10.1109\/CVPR.2009.5206495"},{"issue":"2\/3","key":"9_CR15","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1561\/0600000005","volume":"1","author":"DA Forsyth","year":"2006","unstructured":"D.A. Forsyth, O. Arikan, L. Ikemoto, J. O\u2019Brien, D. Ramanan, Computational studies of human motion: part 1, tracking and motion synthesis. Found. Trends Comput. Gr. Vis. 1(2\/3), 77\u2013254 (2006)","journal-title":"Found. Trends Comput. Gr. Vis."},{"issue":"10","key":"9_CR16","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"A. Gupta, A. Kembhavi, L.S. Davis, Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(10), 1775\u20131789 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"N. Ikizler, R. Gokberk Cinbis, S. Pehlivan, P. Duygulu, Recognizing actions from still images, in International Conference on Pattern Recognition, 2008","DOI":"10.1109\/ICPR.2008.4761663"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"N. Ikizler-Cinbis, R. Gokberk Cinbis, S. Sclaroff, Learning actions from the web, in IEEE International Conference on Computer Vision, 2009","DOI":"10.1109\/ICCV.2009.5459368"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"H. Jiang, D.R. Martin, Globel pose estimation using non-tree models, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008","DOI":"10.1109\/CVPR.2008.4587457"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"T. Joachims, T. Finley, C.-N. Yu, Cutting-plane training of structural SVMs, in Machine Learning, 2008","DOI":"10.1007\/s10994-009-5108-8"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"S. Johnson, M. Everingham, Combining discriminative appearance and segmentation cues for articulated human pose estimation, in International Workshop on Machine Learning for Vision-based Motion Analysis, 2009","DOI":"10.1109\/ICCVW.2009.5457673"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"S. Johnson, M. Everingham, Clustered pose and nonlinear appearance models for human pose estimation, in British Machine Vision Conference, 2010","DOI":"10.5244\/C.24.12"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"S.X. Ju, M.J. Black, Y. Yaccob, Cardboard people: a parameterized model of articulated image motion, in International Conference on Automatic Face and Gesture Recognition, 1996, pp. 38\u201344","DOI":"10.1109\/AFGR.1996.557241"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Y. Ke, R. Sukthankar, M. Hebert, Event detection in crowded videos, in IEEE International Conference on Computer Vision, 2007","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"M.P. Kumar, A. Zisserman, P.H.S. Torr, Efficient discriminative learning of parts-based models, in IEEE International Conference on Computer Vision, 2009","DOI":"10.1109\/ICCV.2009.5459192"},{"key":"9_CR26","unstructured":"T. Lan, Y. Wang, W. Yang, G. Mori, Beyond actions: discriminative models for contextual group activities, in Advances in Neural Information Processing Systems (MIT Press, 2010)"},{"key":"9_CR27","first-page":"470","volume":"1","author":"X Lan","year":"2005","unstructured":"X. Lan, D.P. Huttenlocher, Beyond trees: common-factor models for 2d human pose recovery. IEEE Int. Conf. Comput. Vis. 1, 470\u2013477 (2005)","journal-title":"IEEE Int. Conf. Comput. Vis."},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"I. Laptev, M. Marszalek, C. Schmid, B. Rozenfeld, Learning realistic human actions from movies, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"S. Maji, L. Bourdev, J. Malik, Action recognition from a distributed representation of pose and appearance, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"9_CR30","volume-title":"A Computational Investigation into the Human Representation and Processing of Visual Information","author":"D Marr","year":"1982","unstructured":"D. Marr, A Computational Investigation into the Human Representation and Processing of Visual Information (W. H. Freeman, San Francisco, 1982)"},{"key":"9_CR31","first-page":"1417","volume":"2","author":"G Mori","year":"2005","unstructured":"G. Mori, Guiding model search using segmentation. IEEE Int. Conf. Comput. Vis. 2, 1417\u20131423 (2005)","journal-title":"IEEE Int. Conf. Comput. Vis."},{"key":"9_CR32","first-page":"666","volume":"3","author":"G Mori","year":"2002","unstructured":"G. Mori, J. Malik, Estimating human body configurations using shape context matching. Eur. Conf. Comput. Vis. 3, 666\u2013680 (2002)","journal-title":"Eur. Conf. Comput. Vis."},{"key":"9_CR33","first-page":"326","volume":"2","author":"G Mori","year":"2004","unstructured":"G. Mori, X. Ren, A. Efros, J. Malik, Recovering human body configuration: combining segmentation and recognition. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 2, 326\u2013333 (2004)","journal-title":"IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit."},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"J.C. Niebles, L. Fei-Fei, A hierarchical model of shape and appearance for human action classification, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007","DOI":"10.1109\/CVPR.2007.383132"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"J.C. Niebles, H. Wang, L. Fei-Fei, Unsupervised learning of human action categories using spatial-temporal words, in British Machine Vision Conference, vol. 3, 2006, pp. 1249\u20131258","DOI":"10.5244\/C.20.127"},{"key":"9_CR36","first-page":"1129","volume":"19","author":"D Ramanan","year":"2006","unstructured":"D. Ramanan, Learning to parse images of articulated bodies. Adv. Neural Inf. Process. Syst. 19, 1129\u20131136 (2006)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"9_CR37","first-page":"206","volume":"1","author":"D Ramanan","year":"2006","unstructured":"D. Ramanan, C. Sminchisescu, Training deformable models for localization. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 1, 206\u2013213 (2006)","journal-title":"IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit."},{"key":"9_CR38","first-page":"271","volume":"1","author":"D Ramanan","year":"2005","unstructured":"D. Ramanan, D.A. Forsyth, A. Zisserman, Strike a pose: tracking people by finding stylized poses. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 1, 271\u2013278 (2005)","journal-title":"IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit."},{"key":"9_CR39","first-page":"824","volume":"1","author":"X Ren","year":"2005","unstructured":"X. Ren, A. Berg, J. Malik, Recovering human body configurations using pairwise constraints between parts. IEEE Int. Conf. Comput. Vis. 1, 824\u2013831 (2005)","journal-title":"IEEE Int. Conf. Comput. Vis."},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"B. Sapp, C. Jordan, B. Taskar, Adaptive pose priors for pictorial structures, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010a","DOI":"10.1109\/CVPR.2010.5540182"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"B. Sapp, A. Toshev, B. Taskar, Cascaded models for articulated pose estimation, in European Conference on Computer Vision, 2010b","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"9_CR42","first-page":"750","volume":"2","author":"G Shakhnarovich","year":"2003","unstructured":"G. Shakhnarovich, P. Viola, T. Darrell, Fast pose estimation with parameter sensitive hashing. IEEE Int. Conf. Comput. Vis. 2, 750\u2013757 (2003)","journal-title":"IEEE Int. Conf. Comput. Vis."},{"key":"9_CR43","first-page":"2041","volume":"2","author":"L Sigal","year":"2006","unstructured":"L. Sigal, M.J. Black, Measure locally, reason globally: occlusion-sensitive articulated pose estimation. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 2, 2041\u20132048 (2006)","journal-title":"IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit."},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"V.K. Singh, R. Nevatia, C. Huang, Efficient inference with multiple heterogenous part detectors for human pose estimation, in European Conference on Computer Vision, 2010","DOI":"10.1007\/978-3-642-15558-1_23"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"P. Srinivasan, J. Shi, Bottom-up recognition and parsing of the human body, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007","DOI":"10.1109\/CVPR.2007.383301"},{"key":"9_CR46","doi-asserted-by":"crossref","unstructured":"J. Sullivan, S. Carlsson, Recognizing and tracking human action, in European Conference on Computer Vision LNCS 2352, vol.\u00a01, 2002, pp. 629\u2013644","DOI":"10.1007\/3-540-47969-4_42"},{"key":"9_CR47","doi-asserted-by":"crossref","unstructured":"M. Sun, S. Savarese, Articulated part-base model for joint object detection and pose estimation, in IEEE International Conference on Computer Vision, 2011","DOI":"10.1109\/ICCV.2011.6126309"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"T.-P. Tian, S. Sclaroff, Fast globally optimal 2d human detection with loopy graph models, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010","DOI":"10.1109\/CVPR.2010.5540227"},{"key":"9_CR49","first-page":"50","volume":"2","author":"K Toyama","year":"2001","unstructured":"K. Toyama, A. Blake, Probabilistic exemplar-based tracking in a metric space. IEEE Int. Conf. Comput. Vis. 2, 50\u201357 (2001)","journal-title":"IEEE Int. Conf. Comput. Vis."},{"key":"9_CR50","doi-asserted-by":"crossref","unstructured":"D. Tran, D. Forsyth, Improved human parsing with a full relational model, in European Conference on Computer Vision, 2010","DOI":"10.1007\/978-3-642-15561-1_17"},{"key":"9_CR51","first-page":"1453","volume":"6","author":"I Tsochantaridis","year":"2005","unstructured":"I. Tsochantaridis, T. Joachims, T. Hofmann, Y. Altun, Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6, 1453\u20131484 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR52","doi-asserted-by":"crossref","unstructured":"Y. Wang, G. Mori, Multiple tree models for occlusion and spatial constraints in human pose estimation, in European Conference on Computer Vision, 2008","DOI":"10.1007\/978-3-540-88690-7_53"},{"key":"9_CR53","doi-asserted-by":"crossref","unstructured":"Y. Wang, H. Jiang, M.S. Drew, Z.-N. Li, G. Mori, Unsupervised discovery of action classes, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006","DOI":"10.1109\/CVPR.2006.321"},{"key":"9_CR54","doi-asserted-by":"crossref","unstructured":"Y. Wang, D. Tran, Z. Liao, Learning hierarchical poselets for human parsing, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011","DOI":"10.1109\/CVPR.2011.5995519"},{"key":"9_CR55","doi-asserted-by":"crossref","unstructured":"W. Yang, Y. Wang, G. Mori, Recognizing human actions from still images with latent poses, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010","DOI":"10.1109\/CVPR.2010.5539879"},{"key":"9_CR56","doi-asserted-by":"crossref","unstructured":"Y. Yang, D. Ramanan, Articulated pose estimation with flexible mixtures-of-parts, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"9_CR57","doi-asserted-by":"crossref","unstructured":"B. Yao, L. Fei-Fei, Modeling mutual context of object and human pose in human\u2013object interaction activities, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"9_CR58","unstructured":"L. Zhu, Y. Chen, Y. Lu, C. Lin, A. Yuille, Max margin AND\/OR graph learning for parsing the human body, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008"}],"container-title":["The Springer Series on Challenges in Machine Learning","Gesture Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-57021-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,30]],"date-time":"2019-09-30T17:35:45Z","timestamp":1569864945000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-57021-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319570204","9783319570211"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-57021-1_9","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-319-57021-1","asserted-by":"object"}]},"ISSN":["2520-131X","2520-1328"],"issn-type":[{"value":"2520-131X","type":"print"},{"value":"2520-1328","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}