{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T11:55:59Z","timestamp":1771329359621,"version":"3.50.1"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,11,22]],"date-time":"2013-11-22T00:00:00Z","timestamp":1385078400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1007\/s11263-013-0672-6","type":"journal-article","created":{"date-parts":[[2013,11,20]],"date-time":"2013-11-20T22:54:39Z","timestamp":1384988079000},"page":"70-90","source":"Crossref","is-referenced-by-count":52,"title":["Automatic and Efficient Human Pose Estimation for Sign Language Videos"],"prefix":"10.1007","volume":"110","author":[{"given":"James","family":"Charles","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomas","family":"Pfister","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Everingham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,11,22]]},"reference":[{"issue":"7","key":"672_CR1","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1162\/neco.1997.9.7.1545","volume":"9","author":"Y Amit","year":"1997","unstructured":"Amit, Y., & Geman, D. (1997). Shape quantization and recognition with randomized trees. Neural Computation, 9(7), 1545\u20131588.","journal-title":"Neural Computation"},{"issue":"3","key":"672_CR2","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/s11263-011-0498-z","volume":"99","author":"M Andriluka","year":"2012","unstructured":"Andriluka, M., Roth, S., & Schiele, B. (2012). Discriminative appearance models for pictorial structures. International Journal of Computer Vision, 99(3), 259\u2013280.","journal-title":"International Journal of Computer Vision"},{"key":"672_CR3","doi-asserted-by":"crossref","unstructured":"Apostoloff, N. E., & Zisserman, A. (2007). Who are you?\u2014real-time person identification. In Proceedings of the British machine vision conference.","DOI":"10.5244\/C.21.48"},{"key":"672_CR4","doi-asserted-by":"crossref","unstructured":"Benfold, B., & Reid, I. (2008). Colour invariant head pose classification in low resolution video. In Proceedings of the British machine vision conference.","DOI":"10.5244\/C.22.49"},{"key":"672_CR5","doi-asserted-by":"crossref","unstructured":"Bosch, A., Zisserman, A., & Munoz, X. (2007). Image classification using random forests and ferns. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2007.4409066"},{"key":"672_CR6","unstructured":"Bowden, R., Windridge, D., Kadir, T., Zisserman, A., & Brady, J. M. (2004). A linguistic feature vector for the visual interpretation of sign language. In Proceedings of the European conference on computer vision. Berlin: Springer."},{"issue":"1","key":"672_CR7","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5\u201332.","journal-title":"Machine Learning"},{"issue":"2","key":"672_CR8","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1007\/s11263-011-0480-9","volume":"95","author":"P Buehler","year":"2011","unstructured":"Buehler, P., Everingham, M., Huttenlocher, D. P., & Zisserman, A. (2011). Upper body detection and tracking in extended signing sequences. International Journal of Computer Vision, 95(2), 180\u2013197.","journal-title":"International Journal of Computer Vision"},{"key":"672_CR9","doi-asserted-by":"crossref","unstructured":"Buehler, P., Everingham, M., & Zisserman, A. (2009). Learning sign language by watching TV (using weakly aligned subtitles). In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2009.5206523"},{"key":"672_CR10","unstructured":"Buehler, P., Everingham, M., & Zisserman, A. (2010). Employing signed TV broadcasts for automated learning of British sign language. In Workshop on representation and processing of sign languages."},{"key":"672_CR11","unstructured":"Chai, Y., Lempitsky, V., & Zisserman, A. (2011). BiCoS: A bi-level co-segmentation method for image classification. In Proceedings of the international conference on computer vision."},{"key":"672_CR12","doi-asserted-by":"crossref","unstructured":"Chai, Y., Rahtu, E., Lempitsky, V., Van Gool, L., & Zisserman, A. (2012). Tricos: A tri-level class-discriminative co-segmentation method for image classification. In European conference on computer vision.","DOI":"10.1007\/978-3-642-33718-5_57"},{"key":"672_CR13","doi-asserted-by":"crossref","unstructured":"Charles, J., Pfister, T., Magee, D., Hogg, D., & Zisserman, A. (2013). Domain adaptation for upper body pose tracking in signed TV broadcasts. In Proceedings of the British machine vision conference.","DOI":"10.5244\/C.27.47"},{"key":"672_CR14","doi-asserted-by":"crossref","unstructured":"Chunli, W., Wen, G., & Jiyong, M. (2002). A real-time large vocabulary recognition system for Chinese Sign Language. Gesture and sign language in HCI.","DOI":"10.1007\/3-540-47873-6_9"},{"key":"672_CR15","doi-asserted-by":"crossref","unstructured":"Cooper, H., & Bowden, R. (2007). Large lexicon detection of sign language. Workshop on human computer interaction.","DOI":"10.1007\/978-3-540-75773-3_10"},{"key":"672_CR16","doi-asserted-by":"crossref","unstructured":"Cooper, H., & Bowden, R. (2009). Learning signs from subtitles: A weakly supervised approach to sign language recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2009.5206647"},{"key":"672_CR17","doi-asserted-by":"crossref","unstructured":"Cootes, T., Ionita, M., Lindner, C., & Sauer, P. (2012). Robust and accurate shape model fitting using random forest regression voting. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-33786-4_21"},{"key":"672_CR18","unstructured":"Criminisi, A., Shotton, J., & Konukoglu, E. (2012). Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and Trends in Computer Graphics and Vision, 7(2), 81\u2013227."},{"key":"672_CR19","doi-asserted-by":"crossref","unstructured":"Criminisi, A., Shotton, J., & Robertson, & D., Konukoglu, E., (2011). Regression forests for efficient anatomy detection and localization in CT studies. In International conference on medical image computing and computer assisted intervention workshop on probabilistic models for medical image analysis.","DOI":"10.1007\/978-3-642-18421-5_11"},{"key":"672_CR20","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histogram of Oriented Gradients for Human Detection. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2005.177"},{"key":"672_CR21","doi-asserted-by":"crossref","unstructured":"Dantone, M., Gall, J., Fanelli, G., & Van Gool, L. (2012). Real-time facial feature detection using conditional regression forests. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2012.6247976"},{"key":"672_CR22","doi-asserted-by":"crossref","unstructured":"Dreuw, P., Deselaers, T., Rybach, D., Keysers, D., & Ney, H. (2006). Tracking using dynamic programming for appearance-based sign language recognition. In Proceedings of the IEEE conference on automatic face and gesture recognition.","DOI":"10.1109\/FGR.2006.107"},{"key":"672_CR23","unstructured":"Dreuw, P., Forster, J., & Ney, H. (2012). Tracking benchmark databases for video-based sign language recognition. In Trends and topics in computer vision (pp. 286\u2013297). Berlin: Springer."},{"key":"672_CR24","doi-asserted-by":"crossref","unstructured":"Eichner, M., & Ferrari, V. (2009). Better appearance models for pictorial structures. In Proceedings of the British machine vision conference.","DOI":"10.5244\/C.23.3"},{"key":"672_CR25","doi-asserted-by":"crossref","unstructured":"Eichner, M., Marin-Jimenez, M., Zisserman, A., & Ferrari, V. (2012). 2D articulated human pose estimation and retrieval in (almost) unconstrained still images. International Journal of Computer Vision, 1\u201325.","DOI":"10.1007\/s11263-012-0524-9"},{"issue":"3","key":"672_CR26","first-page":"1","volume":"101","author":"G Fanelli","year":"2012","unstructured":"Fanelli, G., Dantone, M., Gall, J., Fossati, A., & Van Gool, L. (2012). Random forests for real time 3D face analysis. International Journal of Computer Vision, 101(3), 1\u201322.","journal-title":"International Journal of Computer Vision"},{"key":"672_CR27","doi-asserted-by":"crossref","unstructured":"Fanelli, G., Gall, J., & Van Gool, L. (2011). Real time head pose estimation with random regression forests. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2011.5995458"},{"key":"672_CR28","doi-asserted-by":"crossref","unstructured":"Farhadi, A., & Forsyth, D. (2006). Aligning asl for statistical translation using a discriminative word model. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2006.51"},{"key":"672_CR29","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Forsyth, D., & White, R. (2007). Transfer learning in sign language. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2007.383346"},{"key":"672_CR30","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., Girshick, R., & McAllester, D. (2010). Cascade object detection with deformable part models. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2010.5539906"},{"issue":"1","key":"672_CR31","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"P Felzenszwalb","year":"2005","unstructured":"Felzenszwalb, P., & Huttenlocher, D. (2005). Pictorial structures for object recognition. International Journal of Computer Vision, 61(1), 55\u201379.","journal-title":"International Journal of Computer Vision"},{"key":"672_CR32","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., & Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"672_CR33","doi-asserted-by":"crossref","unstructured":"Ferrari, V., Marin-Jimenez, M., & Zisserman, A. (2008). Progressive search space reduction for human pose estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2008.4587468"},{"key":"672_CR34","doi-asserted-by":"crossref","unstructured":"Gall, J., & Lempitsky, V. (2009). Class-specific hough forests for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2009.5206740"},{"issue":"2","key":"672_CR35","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1016\/j.neuroimage.2011.03.080","volume":"57","author":"E Geremia","year":"2011","unstructured":"Geremia, E., Clatz, O., Menze, B., Konukoglu, E., Criminisi, A., & Ayache, N. (2011). Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images. NeuroImage, 57(2), 378\u2013390.","journal-title":"NeuroImage"},{"key":"672_CR36","doi-asserted-by":"crossref","unstructured":"Girshick, R., Shotton, J., Kohli, P., Criminisi, A., & Fitzgibbon, A. (2011). Efficient regression of general-activity human poses from depth images. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2011.6126270"},{"key":"672_CR37","doi-asserted-by":"crossref","unstructured":"Hochbaum, D., & Singh, V. (2009). An efficient algorithm for co-segmentation. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2009.5459261"},{"key":"672_CR38","doi-asserted-by":"crossref","unstructured":"Jammalamadaka, N., Zisserman, A., Eichner, M., Ferrari, V., & Jawahar, C. V. (2012). Has my algorithm succeeded? An evaluator for human pose estimators. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-33712-3_9"},{"key":"672_CR39","doi-asserted-by":"crossref","unstructured":"Johnson, S., & Everingham, M. (2009). Combining discriminative appearance and segmentation cues for articulated human pose estimation. In IEEE international workshop on machine learning for vision-based motion analysis.","DOI":"10.1109\/ICCVW.2009.5457673"},{"key":"672_CR40","doi-asserted-by":"crossref","unstructured":"Jojic, N., & Frey, B. (2001). Learning flexible sprites in video layers. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2001.990476"},{"key":"672_CR41","doi-asserted-by":"crossref","unstructured":"Joulin, A., Bach, F., & Ponce, J. (2010). Discriminative clustering for image co-segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2010.5539868"},{"key":"672_CR42","doi-asserted-by":"crossref","unstructured":"Kadir, T., Bowden, R., Ong, E., & Zisserman, A. (2004). Minimal training, large lexicon, unconstrained sign language recognition. In Proceedings of the British machine vision conference.","DOI":"10.5244\/C.18.96"},{"key":"672_CR43","doi-asserted-by":"crossref","unstructured":"Kadir, T., Zisserman, A., & Brady, J. M. (2004). An affine invariant salient region detector. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-540-24670-1_18"},{"key":"672_CR44","unstructured":"Kontschieder, P., Bul\u00f2, S., Criminisi, A., Kohli, P., Pelillo, M., & Bischof, H. (2012). Context-sensitive decision forests for object detection. In Advances in neural information processing systems."},{"key":"672_CR45","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/s11263-007-0064-x","volume":"76","author":"MP Kumar","year":"2008","unstructured":"Kumar, M. P., Torr, P. H. S., & Zisserman, A. (2008). Learning layered motion segmentations of video. International Journal of Computer Vision, 76, 301\u2013319.","journal-title":"International Journal of Computer Vision"},{"issue":"9","key":"672_CR46","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1109\/TPAMI.2006.188","volume":"28","author":"V Lepetit","year":"2006","unstructured":"Lepetit, V., & Fua, P. (2006). Keypoint recognition using randomized trees. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(9), 1465\u20131479.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"672_CR47","doi-asserted-by":"crossref","unstructured":"Liu, C., Gong, S., Loy, C., & Lin, X. (2012). Person re-identification: What features are important?. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-33863-2_39"},{"key":"672_CR48","doi-asserted-by":"crossref","unstructured":"Mar\u00e9e, R., Geurts, P., Piater, J., & Wehenkel, L. (2005). Random subwindows for robust image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2005.287"},{"key":"672_CR49","doi-asserted-by":"crossref","unstructured":"Moeslund, T. (2011). Visual analysis of humans: Looking at people. Berlin: Springer.","DOI":"10.1007\/978-0-85729-997-0"},{"key":"672_CR50","doi-asserted-by":"crossref","unstructured":"Nowozin, S., Rother, C., Bagon, S., Sharp, T., Yao, B., & Kohli, P. (2011). Decision tree fields. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.2011.6126429"},{"key":"672_CR51","unstructured":"Ong, E., & Bowden, R. (2004). A boosted classifier tree for hand shape detection. In Proceedings of the international conference on automatic face and gesture recognition."},{"issue":"3","key":"672_CR52","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1109\/TPAMI.2009.23","volume":"32","author":"M Ozuysal","year":"2010","unstructured":"Ozuysal, M., Calonder, M., Lepetit, V., & Fua, P. (2010). Fast keypoint recognition using random ferns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(3), 448\u2013461.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"672_CR53","doi-asserted-by":"crossref","unstructured":"Pfister, T., Charles, J., Everingham, M., & Zisserman, A. (2012). Automatic and efficient long term arm and hand tracking for continuous sign language TV broadcasts. In Proceedings of the British machine vision conference.","DOI":"10.5244\/C.26.4"},{"key":"672_CR54","unstructured":"Pfister, T., Charles, J., & Zisserman, A. (2013). Large-scale learning of sign language by watching TV (using co-occurrences). In Proceedings of the British machine vision conference."},{"key":"672_CR55","unstructured":"Ramanan, D. (2006). Learning to parse images of articulated bodies. In Advances in neural information processing systems."},{"issue":"1","key":"672_CR56","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/TPAMI.2007.250600","volume":"29","author":"D Ramanan","year":"2007","unstructured":"Ramanan, D., Forsyth, D. A., & Zisserman, A. (2007). Tracking people by learning their appearance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(1), 65\u201381.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"672_CR57","doi-asserted-by":"crossref","unstructured":"Rother, C., Kolmogorov, V., & Blake, A. (2004). Grabcut: interactive foreground extraction using iterated graph cuts. In Proceedings of the ACM SIGGRAPH conference on computer graphics.","DOI":"10.1145\/1015706.1015720"},{"key":"672_CR58","doi-asserted-by":"crossref","unstructured":"Rother, C., Minka, T., Blake, A., & Kolmogorov, V. (2006). Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2006.91"},{"key":"672_CR59","doi-asserted-by":"crossref","unstructured":"Santner, J., Leistner, C., Saffari, A., Pock, T., & Bischof, H. (2010). Prost: Parallel robust online simple tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2010.5540145"},{"key":"672_CR60","doi-asserted-by":"crossref","unstructured":"Sapp, B., Jordan, C., & Taskar, B. (2010). Adaptive pose priors for pictorial structures. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2010.5540182"},{"key":"672_CR61","doi-asserted-by":"crossref","unstructured":"Sapp, B., Weiss, D., & Taskar, B. (2011). Parsing human motion with stretchable models. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2011.5995607"},{"key":"672_CR62","doi-asserted-by":"crossref","unstructured":"Sharp, T. (2008). Implementing decision trees and forests on a GPU. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-540-88693-8_44"},{"key":"672_CR63","doi-asserted-by":"crossref","unstructured":"Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., et al. (2011). Real-time human pose recognition in parts from single depth images. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"672_CR64","doi-asserted-by":"crossref","unstructured":"Shotton, J., Johnson, M., & Cipolla, R. (2008). Semantic texton forests for image categorization and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2008.4587503"},{"key":"672_CR65","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zitnick, C. L., & Szeliski, R. (2006). Finding people in repeated shots of the same scene. In Proceedings of the British machine vision conference, Edinburgh.","DOI":"10.5244\/C.20.93"},{"issue":"12","key":"672_CR66","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1109\/34.735811","volume":"20","author":"T Starner","year":"1998","unstructured":"Starner, T., Weaver, J., & Pentland, A. (1998a). Real-time american sign language recognition using desk- and wearable computer-based video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(12), 1371\u20131375.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"12","key":"672_CR67","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1109\/34.735811","volume":"20","author":"T Starner","year":"1998","unstructured":"Starner, T., Weaver, J., & Pentland, A. (1998b). Real-time American Sign Language recognition using desk and wearable computer based video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(12), 1371\u20131375.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"672_CR68","unstructured":"Sun, M., Kohli, P., & Shotton, J. (2012). Conditional regression forests for human pose estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition."},{"key":"672_CR69","doi-asserted-by":"crossref","unstructured":"Szeliski, R., Avidan, S., & Anandan, P. (2000). Layer extraction from multiple images containing reflections and transparency. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2000.855826"},{"key":"672_CR70","doi-asserted-by":"crossref","unstructured":"Taylor, J., Shotton, J., Sharp, T., & Fitzgibbon, A. (2012). The vitruvian manifold: Inferring dense correspondences for one-shot human pose estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2012.6247664"},{"key":"672_CR71","doi-asserted-by":"crossref","unstructured":"Tran, D., & Forsyth, D. (2010). Improved human parsing with a full relational model. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-15561-1_17"},{"key":"672_CR72","doi-asserted-by":"crossref","unstructured":"Vogler, C., & Metaxas, D. (1998). ASL recognition based on a coupling between HMMs and 3D motion analysis. In Proceedings of the international conference on computer vision.","DOI":"10.1109\/ICCV.1998.710744"},{"key":"672_CR73","doi-asserted-by":"crossref","unstructured":"Yang, Y., & Ramanan, D. (2011). Articulated pose estimation with flexible mixtures-of-parts. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"672_CR74","doi-asserted-by":"crossref","unstructured":"Yin, P., Criminisi, A., Winn, J., & Essa, I. (2007). Tree-based classifiers for bilayer video Segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2007.383008"},{"key":"672_CR75","unstructured":"Zhu, X., & Ramanan, D. (2012). Face detection, pose estimation, and landmark localization in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition."},{"key":"672_CR76","doi-asserted-by":"crossref","unstructured":"Zisserman, A., Winn, J., Fitzgibbon, A., van Gool, L., Sivic, J., Williams, C., & Hogg, D. (2012). In memoriam: Mark Everingham. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2081\u20132082.","DOI":"10.1109\/TPAMI.2012.204"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-013-0672-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-013-0672-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-013-0672-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,3]],"date-time":"2019-08-03T17:31:10Z","timestamp":1564853470000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-013-0672-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11,22]]},"references-count":76,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,10]]}},"alternative-id":["672"],"URL":"https:\/\/doi.org\/10.1007\/s11263-013-0672-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,11,22]]}}}