{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:07:00Z","timestamp":1743102420746,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030660956"},{"type":"electronic","value":"9783030660963"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-66096-3_33","type":"book-chapter","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T07:03:14Z","timestamp":1609570994000},"page":"479-495","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Self-supervised Framework for Human Instance Segmentation"],"prefix":"10.1007","author":[{"given":"Yalong","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenrui","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongguang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"33_CR2","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":"33_CR3","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. arXiv preprint arXiv:1606.00915 (2016)"},{"key":"33_CR4","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":"33_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. arXiv Preprint arXiv:1610.02357 (2016)","DOI":"10.1109\/CVPR.2017.195"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Convolutional feature masking for joint object and stuff segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.343"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Lu, G., Fang, X., Xie, J., Tai, Y.W., Lu., C.: Weakly and semi supervised human body part parsing via pose-guided knowledge transfer. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00015"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., Lu, C.: RMPE: regional multi-person pose estimation. In: CVPR, pp. 2334\u20132343 (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R., Iandola, F., Darrell, T., Malik, J.: Deformable part models are convolutional neural networks. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298641"},{"key":"33_CR12","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Dollar, P., He, K.: Detectron (2018). https:\/\/github.com\/facebookresearch\/detectron\/"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Gong, K., Gao, Y., Liang, X., Shen, X., Wang, M., Lin, L.: Graphonomy: universal human parsing via graph transfer learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00763"},{"key":"33_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1007\/978-3-030-01225-0_47","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Gong","year":"2018","unstructured":"Gong, K., Liang, X., Li, Y., Chen, Y., Yang, M., Lin, L.: Instance-level human parsing via part grouping network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 805\u2013822. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_47"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Zhang, D., 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":"33_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. arXiv Preprint arXiv:1703.06870v3 (2018)","DOI":"10.1109\/ICCV.2017.322"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. arXiv preprint arXiv:1603.05027 (2016)","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017. http:\/\/lmb.informatik.uni-freiburg.de\/\/Publications\/2017\/IMKDB17","DOI":"10.1109\/CVPR.2017.179"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"33_CR20","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1109\/TPAMI.2015.2408360","volume":"37","author":"X Liang","year":"2015","unstructured":"Liang, X., et al.: Deep human parsing with active template regression. TPAMI 37, 2402\u20132414 (2015)","journal-title":"TPAMI"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Liang, X., Shen, X., Xiang, D., Feng, J., Lin, L., Yan, S.: Semantic object parsing with local-global long short term memory. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.347"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Liang, X., et al.: Human parsing with contextualized convolutional neural network. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.163"},{"key":"33_CR23","first-page":"256","volume":"34","author":"MZ Lifkooee","year":"2019","unstructured":"Lifkooee, M.Z., Liu, C., Liang, Y., Zhu, Y., Li, X.: Real-time avatar pose transfer and motion generation using locally encoded Laplacian offsets. JCST 34, 256\u2013271 (2019)","journal-title":"JCST"},{"key":"33_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Auto-DeepLab: hierarchical neural architecture search for semantic image segmentation. arXiv preprint arXiv 1901.02985 (2018)","DOI":"10.1109\/CVPR.2019.00017"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Liu, S., Jia, J., Fidler, S., Urtasun., R.: SGN: sequential grouping networks for instance segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.378"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Matching-CNN meets KNN: Quasi-parametric human parsing. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298748"},{"key":"33_CR28","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. In: NIPS (2017)"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Chen, L.C., Gidaris, S., Tompson, J., Murphy, K.: PersonLab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. arXiv Preprint arXiv:1803.08225 (2018)","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"33_CR31","unstructured":"Xia, F., Wang, P., Chen, L.C., Yuille, A.L.: Zoom better to see clearer: human part segmentation with auto zoom net. In: ECCV (2016)"},{"key":"33_CR32","first-page":"536","volume":"32","author":"S Xia","year":"2017","unstructured":"Xia, S., Gao, L., Lai, Y.K., Yuan, M.Z., Chai, J.: A survey on human performance capture and animation. JCST 32, 536\u2013554 (2017)","journal-title":"JCST"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Yang, L., Song, Q., Wang, Z., Jiang, M.: Parsing R-CNN for instance-level human analysis. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00045"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, S.H., et al.: Pose2Seg: detection free human instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00098"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, J., et al.: Understanding humans in crowded scenes: deep nested adversarial learning and a new benchmark for multi-human parsing. arXiv preprint arXiv 1804.03287 (2018)","DOI":"10.1145\/3240508.3240509"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Liang, X., Gong, K., Lin, L.: Adaptive temporal encoding network for video instance-level human parsing. In: ACM MM (2018)","DOI":"10.1145\/3240508.3240660"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66096-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:13:53Z","timestamp":1735776833000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66096-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030660956","9783030660963"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66096-3_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 January 2021","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}