{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:35:03Z","timestamp":1779294903136,"version":"3.51.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,9,26]],"date-time":"2014-09-26T00:00:00Z","timestamp":1411689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1007\/s11263-014-0767-8","type":"journal-article","created":{"date-parts":[[2014,9,25]],"date-time":"2014-09-25T06:31:21Z","timestamp":1411626681000},"page":"19-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network"],"prefix":"10.1007","volume":"113","author":[{"given":"Sijin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi-Qiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,9,26]]},"reference":[{"issue":"1\u20132","key":"767_CR1","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/s11263-008-0204-y","volume":"87","author":"L Bo","year":"2010","unstructured":"Bo, L., & Sminchisescu, C. (2010). Twin gaussian processes for structured prediction. International Journal of Computer Vision, 87(1\u20132), 28\u201352.","journal-title":"International Journal of Computer Vision"},{"key":"767_CR2","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005) Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2005.177"},{"key":"767_CR3","doi-asserted-by":"crossref","unstructured":"Dantone, M., Gall, J., Leistner, C., & van Gool L. (2013) Human pose estimation from still images using body parts dependent joint regressors. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2013.391"},{"key":"767_CR4","doi-asserted-by":"crossref","unstructured":"Eichner, M., & Ferrari, V. (2009a) Better appearance models for pictorial structures. In: British Machine Vision Conference, pp 1\u201311.","DOI":"10.5244\/C.23.3"},{"key":"767_CR5","unstructured":"Eichner, M., & Ferrari, V. (2009b) Upper body detector. http:\/\/groups.inf.ed.ac.uk\/calvin\/calvin_upperbody_detector\/"},{"key":"767_CR6","doi-asserted-by":"crossref","unstructured":"Eichner, M., & Ferrari, V. (2010) We are family: Joint pose estimation of multiple persons. In: European Conference.on Computer Vision.","DOI":"10.1007\/978-3-642-15549-9_17"},{"key":"767_CR7","doi-asserted-by":"crossref","unstructured":"Eichner, M., & Ferrari, V. (2012). Human pose co-estimation and applications. IEEE Trans Pattern Anal Mach Intell.","DOI":"10.1109\/TPAMI.2012.85"},{"issue":"2","key":"767_CR8","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1007\/s11263-012-0524-9","volume":"99","author":"M Eichner","year":"2012","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, 99(2), 190\u2013214.","journal-title":"International Journal of Computer Vision"},{"key":"767_CR9","first-page":"615","volume":"6","author":"T Evgeniou","year":"2005","unstructured":"Evgeniou, T., Micchelli, C. A., & Pontil, M. (2005). Learning multiple tasks with kernel methods. Journal of Machine Learning Research, 6, 615\u2013637.","journal-title":"Journal of Machine Learning Research"},{"key":"767_CR10","doi-asserted-by":"crossref","unstructured":"Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2013). Learning hierarchical features for scene labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1915\u20131929.","DOI":"10.1109\/TPAMI.2012.231"},{"issue":"1","key":"767_CR11","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"PF Felzenszwalb","year":"2005","unstructured":"Felzenszwalb, P. F., & Huttenlocher, D. P. (2005). Pictorial structures for object recognition. International Journal of Computer Vision, 61(1), 55\u201379.","journal-title":"International Journal of Computer Vision"},{"key":"767_CR12","unstructured":"G\u00fcl\u00e7ehrem, C., & Bengio, Y. (2013) Knowledge matters: Importance of prior information for optimization. In: International Conference on Learning Representations."},{"key":"767_CR13","doi-asserted-by":"crossref","unstructured":"Hara, K., & Chellappa, R. (2013) Computationally efficient regression on a dependency graph for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2013.435"},{"key":"767_CR14","unstructured":"Jain, A., Tompson, J., Andriluka, M., Taylor, G. W., & Bregler, C. (2014) Learning human pose estimation features with convolutional networks. In: International Conference on Learning Representations."},{"key":"767_CR15","doi-asserted-by":"crossref","unstructured":"Johnson, S., & Everingham, M. (2011) Learning effective human pose estimation from inaccurate annotation. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"767_CR16","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012) Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems."},{"key":"767_CR17","doi-asserted-by":"crossref","unstructured":"Le, Q., Ranzato, M., Monga, R., Devin, M., Chen, K., Corrado, G., Dean, J., & Ng, A. (2012) Building high-level features using large scale unsupervised learning. In: International Conference on Machine Learning.","DOI":"10.1109\/ICASSP.2013.6639343"},{"key":"767_CR18","first-page":"2579","volume":"9","author":"L Maaten van der","year":"2008","unstructured":"van der Maaten, L., & Hinton, G. (2008). Visualizing Data using t-SNE. Journal of Machine Learning Research, 9, 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"767_CR19","unstructured":"Nair, V., & Hinton, G. E. (2010) Rectified linear units improve restricted boltzmann machines. In: International Conference on Machine Learning."},{"key":"767_CR20","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Jain, A., Andriluka, M., Thormaehlen, T., & Schiele, B. (2012) Articulated people detection and pose estimation: Reshaping the future. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2012.6248052"},{"key":"767_CR21","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Andriluka, M., Gehler, P., & Schiele, B. (2013) Poselet conditioned pictorial structures. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 588\u2013595.","DOI":"10.1109\/CVPR.2013.82"},{"key":"767_CR22","unstructured":"Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1988). Learning representations by back-propagating errors. In J. A. Anderson & E. Rosenfeld (Eds.), Neurocomputing: Foundations of research (pp. 696\u2013699). Cambridge, MA: MIT Press."},{"key":"767_CR23","doi-asserted-by":"crossref","unstructured":"Sapp, B., & Taskar, B. (2013) Modec: Multimodal decomposable models for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2013.471"},{"key":"767_CR24","doi-asserted-by":"crossref","unstructured":"Sapp, B., Toshev, A., & Taskar, B. (2010) Cascaded models for articulated pose estimation. In: European Conference on Computer Vision.","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"767_CR25","doi-asserted-by":"crossref","unstructured":"Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., & Blake, A. (2011) Real-time human pose recognition in parts from single depth images. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"767_CR26","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning, 15, 1929\u20131958."},{"key":"767_CR27","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., & Tang, X. (2013) Deep convolutional network cascade for facial point detection. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2013.446"},{"key":"767_CR28","doi-asserted-by":"crossref","unstructured":"Toshev, A., & Szegedy, C. (2014) Deeppose: Human pose estimation via deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2014.214"},{"key":"767_CR29","doi-asserted-by":"crossref","unstructured":"Weston, J., Ratle, F., & Collobert, R. (2008) Deep learning via semi-supervised embedding. In: International Conference on Machine Learning.","DOI":"10.1145\/1390156.1390303"},{"key":"767_CR30","unstructured":"Yang, X., Kim, S., & Xing, E. P. (2009) Heterogeneous multitask learning with joint sparsity constraints. In: Neural Information Processing Systems."},{"key":"767_CR31","doi-asserted-by":"crossref","unstructured":"Yang, Y., & Ramanan, D. (2011) Articulated pose estimation with flexible mixtures-of-parts. In: IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2011.5995741"},{"issue":"12","key":"767_CR32","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang, Y., & Ramanan, D. (2013). Articulated human detection with flexible mixtures of parts. IEEE Trans Pattern Analysis and Machine Intelligence, 35(12), 2878\u20132890.","journal-title":"IEEE Trans Pattern Analysis and Machine Intelligence"},{"key":"767_CR33","doi-asserted-by":"crossref","unstructured":"Yu, K., Tresp, V., & Schwaighofer, A. (2005) Learning gaussian processes from multiple tasks. In: International Conference on Machine Learning, pp 1012\u20131019.","DOI":"10.1145\/1102351.1102479"},{"key":"767_CR34","doi-asserted-by":"crossref","unstructured":"Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Computer Vision \u2013 ECCV 2014. Lecture Notes in Computer Science (Vol. 8689, pp. 818\u2013833). Springer.","DOI":"10.1007\/978-3-319-10590-1_53"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0767-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-014-0767-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0767-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,15]],"date-time":"2019-08-15T10:55:45Z","timestamp":1565866545000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-014-0767-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,9,26]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,5]]}},"alternative-id":["767"],"URL":"https:\/\/doi.org\/10.1007\/s11263-014-0767-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,9,26]]}}}