{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:08:22Z","timestamp":1778080102911,"version":"3.51.4"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585648","type":"print"},{"value":"9783030585655","type":"electronic"}],"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\/978-3-030-58565-5_3","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"36-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Self-supervised Keypoint Correspondences for Multi-person Pose Estimation and Tracking in Videos"],"prefix":"10.1007","author":[{"given":"Umer","family":"Rafi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Doering","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bastian","family":"Leibe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juergen","family":"Gall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"3_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":"3_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Bao, Q., Liu, W., Cheng, Y., Zhou, B., Mei, T.: Pose-guided tracking-by-detection: Robust multi-person pose tracking. IEEE Trans. Multimedia (2020)","DOI":"10.1109\/TMM.2020.2980194"},{"key":"3_CR4","unstructured":"Bertasius, G., Feichtenhofer, C., Tran, D., Shi, J., Torresani, L.: Learning temporal pose estimation from sparsely-labeled videos. In: NeurIPS (2019)"},{"key":"3_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional Siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"3_CR7","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":"3_CR8","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":"3_CR9","unstructured":"Choy, C., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: NIPS (2016)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Dantone, M., Gall, J., Leistner, C., van Gool, L.: Body parts dependent joint regressors for human pose estimation in still images. TPAMI (2014)","DOI":"10.1109\/TPAMI.2014.2318702"},{"key":"3_CR11","unstructured":"Doering, A., Iqbal, U., Gall, J.: Joint flow: Temporal flow fields for multi person tracking. In: BMVC (2018)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV (2005)","DOI":"10.1023\/B:VISI.0000042934.15159.49"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Gkioxari, G., Torresani, L., Paluri, M., Tran, D.: Detect-and-track: efficient pose estimation in videos. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00044"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Guo, H., Tang, T., Luo, G., Chen, R., Lu, Y., Wen, L.: Multi-domain pose network for multi-person pose estimation and tracking. In: CVPR (2018)","DOI":"10.1007\/978-3-030-11012-3_17"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Han, K., Rezende, R., Ham, B., Wong, K.Y., Cho, M., Schmid, C., Ponce., J.: Scnet: learning semantic correspondence. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.203"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Hwang, J., Lee, J., Park, S., Kwak, N.: Pose estimator and tracker using temporal flow maps for limbs. In: IJCNN (2019)","DOI":"10.1109\/IJCNN.2019.8851734"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Insafutdinov, E., et al.: ArtTrack: articulated multi-person tracking in the wild. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.142"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Milan, A., Gall, J.: Posetrack: Joint multi-person pose estimation and tracking. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.495"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Jin, S., Liu, W., Ouyang, W., Qian, C.: Multi-person articulated tracking with spatial and temporal embeddings. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00581"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Kim, S., Min, D., Ham, B., Jeon, S., Lin, S., Sohn, K.: Fully convolutional self-similarity for dense semantic correspondence. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.73"},{"key":"3_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/978-3-030-01252-6_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Kocabas","year":"2018","unstructured":"Kocabas, M., Karagoz, S., Akbas, E.: MultiPoseNet: fast multi-person pose estimation using pose residual network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 437\u2013453. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_26"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with Siamese region proposal network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"3_CR25","unstructured":"Li, W., et al.: Rethinking on multi-stage networks for human pose estimation. arXiv preprint (2019)"},{"key":"3_CR26","unstructured":"Li, X., Liu, S., Mello, S.D., Wang, X., Kautz, J., Yang, M.H.: Joint-task self-supervised learning for temporal correspondence. In: NeurIPS (2019)"},{"key":"3_CR27","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":"3_CR28","doi-asserted-by":"crossref","unstructured":"Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: CVPR Workshop (2019)","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"3_CR29","unstructured":"Moon, G., Chang, J.Y., Lee, K.M.: Multi-scale aggregation R-CNN for 2D multi-person pose estimation. In: CVPR Workshop (2019)"},{"key":"3_CR30","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. In: NIPS (2017)"},{"key":"3_CR31","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":"3_CR32","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Xing, J., Yan, S.: Generative partition networks for multi-person pose estimation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01228-1_42"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Ning, G., Huang, H.: Lighttrack: a generic framework for online top-down human pose tracking. arXiv preprint (2019)","DOI":"10.1109\/CVPRW50498.2020.00525"},{"key":"3_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-030-11012-3_20","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"G Ning","year":"2019","unstructured":"Ning, G., Liu, P., Fan, X., Zhang, C.: A top-down approach to articulated human pose estimation and tracking. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 227\u2013234. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_20"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Raaj, Y., Idrees, H., Hidalgo, G., Sheikh, Y.: Efficient online multi-person 2D pose tracking with recurrent spatio-temporal affinity fields. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00475"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Ruan, W., Liu, W., Bao, Q., Chen, J., Cheng, Y., Mei, T.: POINet: pose-guided ovonic insight network for multi-person pose tracking. In: International Conference on Multimedia (2019)","DOI":"10.1145\/3343031.3350984"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"3_CR38","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":"3_CR39","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Jabri, A., Efros, A.A.: Learning correspondence from the cycle-consistency of time. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00267"},{"key":"3_CR41","unstructured":"Wu, J., et al.: AI challenger: a large-scale dataset for going deeper in image understanding. arXiv preprint (2017)"},{"key":"3_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-01231-1_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Xiao","year":"2018","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472\u2013487. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29"},{"key":"3_CR43","unstructured":"Xiu, Y., Li, J., Wang, H., Fang, Y., Lu, C.: Pose Flow: Efficient online pose tracking. In: BMVC (2018)"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.144"},{"key":"3_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/978-3-030-11012-3_19","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"D Yu","year":"2019","unstructured":"Yu, D., Su, K., Sun, J., Wang, C.: Multi-person pose estimation for pose tracking with enhanced cascaded pyramid network. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 221\u2013226. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_19"},{"key":"3_CR46","unstructured":"Zhang, R., et al.: Exploiting offset-guided network for pose estimation and tracking. In: CVPR (2019)"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Wang, Q.: Deeper and wider Siamese networks for real-time visual tracking. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00472"},{"key":"3_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/978-3-030-01240-3_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Zhu","year":"2018","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware Siamese networks for visual object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 103\u2013119. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_7"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58565-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:03:12Z","timestamp":1731283392000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 November 2020","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.","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)"}}]}}