{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T02:18:37Z","timestamp":1771294717809,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012274","type":"print"},{"value":"9783030012281","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01228-1_31","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T05:03:51Z","timestamp":1538802231000},"page":"519-534","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":108,"title":["Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2433-5983","authenticated-orcid":false,"given":"Xuecheng","family":"Nie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"issue":"12","key":"31_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR2","unstructured":"Bertinetto, L., Henriques, J.F., Valmadre, J., Torr, P., Vedaldi, A.: Learning feed-forward one-shot learners. In: NIPS (2016)"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"31_CR4","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. In: ICLR (2015)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.396"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Yuille, A.: Parsing occluded people by flexible compositions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299020"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Chou, C.J., Chien, J.T., Chen, H.T.: Self adversarial training for human pose estimation. In: CVPR Workshops (2017)","DOI":"10.23919\/APSIPA.2018.8659538"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Dong, J., Chen, Q., Shen, X., Yang, J., Yan, S.: Towards unified human parsing and pose estimation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.113"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Gan, C., Lin, M., Yang, Y., de Melo, G., Hauptmann, A.G.: Concepts not alone: exploring pairwise relationships for zero-shot video activity recognition. In: AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10466"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Shen, X., Lin, L.: Look into person: self-supervised structure-sensitive learning and a new benchmark for human parsing. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.715"},{"key":"31_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-46466-4_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Insafutdinov","year":"2016","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Ladicky, L., Torr, P.H., Zisserman, A.: Human pose estimation using a joint pixel-wise and part-wise formulation. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.459"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"31_CR14","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.neucom.2012.08.071","volume":"126","author":"Y Lu","year":"2014","unstructured":"Lu, Y., Boukharouba, K., Boon\u00e6rt, J., Fleury, A., Lecoeuche, S.: Application of an incremental SVM algorithm for on-line human recognition from video surveillance using texture and color features. Neurocomputing 126, 132\u2013140 (2014)","journal-title":"Neurocomputing"},{"key":"31_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Xing, J., Yan, S.: Generative partition networks for multi-person pose estimation. arXiv preprint arXiv:1705.07422 (2017)","DOI":"10.1007\/978-3-030-01228-1_42"},{"key":"31_CR17","unstructured":"Paszke, A., Gross, S., Chintala, S.: PyTorch (2017)"},{"key":"31_CR18","unstructured":"Ren, S., Kaiming, H., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"31_CR19","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Su, C., Li, J., Zhang, S., Xing, J., Gao, W., Tian, Q.: Pose-driven deep convolutional model for person re-identification. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.427"},{"key":"31_CR21","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning (2012)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Wang, C., Wang, Y., Yuille, A.L.: An approach to pose-based action recognition. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.123"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Xia, F., Wang, P., Chen, X., Yuille, A.: Joint multi-person pose estimation and semantic part segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.644"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Xia, F., Zhu, J., Wang, P., Yuille, A.L.: Pose-guided human parsing by an and\/or graph using pose-context features. In: AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10460"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Yamaguchi, K., Kiapour, M.H., Ortiz, L.E., Berg, T.L.: Parsing clothing in fashion photographs. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248101"},{"issue":"12","key":"31_CR27","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang, Y., Ramanan, D.: Articulated human detection with flexible mixtures of parts. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2878\u20132890 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, J., et al.: Self-supervised neural aggregation networks for human parsing. In: CVPR Workshops (2017)","DOI":"10.1109\/CVPRW.2017.204"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, R., Ouyang, W., Wang, X.: Unsupervised salience learning for person re-identification. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.460"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhu, M., Leonardos, S., Derpanis, K.G., Daniilidis, K.: Sparseness meets deepness: 3D human pose estimation from monocular video. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.537"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01228-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:31:26Z","timestamp":1665016286000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}