{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:36:42Z","timestamp":1743147402286,"version":"3.40.3"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031198083"},{"type":"electronic","value":"9783031198090"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19809-0_31","type":"book-chapter","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T07:03:04Z","timestamp":1667199784000},"page":"545-561","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Discovering Deformable Keypoint Pyramids"],"prefix":"10.1007","author":[{"given":"Jianing","family":"Qian","sequence":"first","affiliation":[]},{"given":"Anastasios","family":"Panagopoulos","sequence":"additional","affiliation":[]},{"given":"Dinesh","family":"Jayaraman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,1]]},"reference":[{"key":"31_CR1","unstructured":"Burgess, C.P., et al.: Monet: unsupervised scene decomposition and representation. ArXiv:abs\/1901.11390 (2019)"},{"key":"31_CR2","unstructured":"Chen, B., Abbeel, P., Pathak, D.: Unsupervised learning of visual 3D keypoints for control, June 2021"},{"issue":"6","key":"31_CR3","doi-asserted-by":"publisher","first-page":"663","DOI":"10.26599\/TST.2018.9010100","volume":"24","author":"Q Dang","year":"2019","unstructured":"Dang, Q., Yin, J., Wang, B., Zheng, W.: Deep learning based 2D human pose estimation: a survey. Tsinghua Sci. Technol. 24(6), 663\u2013676 (2019)","journal-title":"Tsinghua Sci. Technol."},{"key":"31_CR4","unstructured":"Das, N., Bechtle, S., Davchev, T., Jayaraman, D., Rai, A., Meier, F.: Model-based inverse reinforcement learning from visual demonstrations. CORL (2020)"},{"key":"31_CR5","unstructured":"Engelcke, M., Jones, O.P., Posner, I.: Reconstruction bottlenecks in Object-Centric generative models, July 2020"},{"key":"31_CR6","unstructured":"Engelcke, M., Kosiorek, A.R., Jones, O.P., Posner, I.: Genesis: generative scene inference and sampling with object-centric latent representations. ArXiv, abs\/1907.13052 (2020)"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587597"},{"issue":"1","key":"31_CR8","doi-asserted-by":"publisher","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.: Pictorial structures for object recognition. Int. J. Comput. Vis. 61(1), 55\u201379 (2005)","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"31_CR9","doi-asserted-by":"publisher","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.: Pictorial structures for object recognition. Int. J. Comput. Vision 61(1), 55\u201379 (2005)","journal-title":"Int. J. Comput. Vision"},{"issue":"1","key":"31_CR10","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/T-C.1973.223602","volume":"100","author":"MA Fischler","year":"1973","unstructured":"Fischler, M.A., Elschlager, R.A.: The representation and matching of pictorial structures. IEEE Trans. Comput. 100(1), 67\u201392 (1973)","journal-title":"IEEE Trans. Comput."},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Fowlkes, C.C.: Occlusion coherence: localizing occluded faces with a hierarchical deformable part model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2385\u20132392 (2014)","DOI":"10.1109\/CVPR.2014.306"},{"key":"31_CR12","unstructured":"Gopalakrishnan, A., van Steenkiste, S., Schmidhuber, J.: Unsupervised object keypoint learning using local spatial predictability. arXiv:abs\/2011.12930 (2021)"},{"key":"31_CR13","unstructured":"Gopalakrishnan, A., van Steenkiste, S., Schmidhuber, J.: Unsupervised object keypoint learning using local spatial predictability. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=GJwMHetHc73"},{"key":"31_CR14","unstructured":"Greff, K., et al.: Multi-object representation learning with iterative variational inference. arXiv:abs\/1903.00450 (2019)"},{"key":"31_CR15","unstructured":"Greff, K., Van Steenkiste, S., Schmidhuber, J.: On the binding problem in artificial neural networks. arXiv preprint arXiv:2012.05208 (2020)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Huang, S., Gong, M., Tao, D.: A coarse-fine network for keypoint localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pages 3047\u20133056 (2017)","DOI":"10.1109\/ICCV.2017.329"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Huang, S., Gong, M., Tao, D.: A coarse-fine network for keypoint localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3028\u20133037 (2017)","DOI":"10.1109\/ICCV.2017.329"},{"issue":"7","key":"31_CR18","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR19","unstructured":"Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks through conditional image generation. In: NeurIPS (2018)"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Self-supervised learning of interpretable keypoints from unlabelled videos. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8784\u20138794 (2020)","DOI":"10.1109\/CVPR42600.2020.00881"},{"key":"31_CR21","unstructured":"Jiang, J., Janghorbani, S., de Melo, G., Ahn, S.: Scalable object-oriented sequential generative models. CoRR, abs\/1910.02384 (2019). arxiv.org\/abs\/1910.02384"},{"key":"31_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/978-3-030-58571-6_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S., et al.: Differentiable hierarchical graph grouping for multi-person pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 718\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_42"},{"key":"31_CR23","unstructured":"Kipf, T., van der Pol, E., Welling, M.: Contrastive learning of structured world models. arXiv:abs\/1911.12247 (2020)"},{"key":"31_CR24","unstructured":"Kulkarni, T.D., et al.: Unsupervised learning of object keypoints for perception and control. Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"31_CR25","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837","volume":"40","author":"BM Lake","year":"2017","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017)","journal-title":"Behav. Brain Sci."},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Lambeta, M., et al.: Digit: a novel design for a low-cost compact high-resolution tactile sensor with application to in-hand manipulation. In: ICRA and IEEE RA-L (2020)","DOI":"10.1109\/LRA.2020.2977257"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Li, S., Chan, A.B.: 3D human pose estimation from monocular images with deep convolutional neural network. In: ACCV (2014)","DOI":"10.1007\/978-3-319-16808-1_23"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"31_CR29","unstructured":"Lin, Z., et al.: SPACE: unsupervised object-oriented scene representation via spatial attention and decomposition. CoRR, abs\/2001.02407 (2020). https:\/\/arxiv.org\/abs\/2001.02407"},{"key":"31_CR30","unstructured":"Locatello, F., et al.: Object-centric learning with slot attention. arXiv:abs\/2006.15055 (2020)"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Lorenz, D., Bereska, L., Milbich, T., Ommer, B.: Unsupervised part-based disentangling of object shape and appearance. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10947\u201310956 (2019)","DOI":"10.1109\/CVPR.2019.01121"},{"key":"31_CR32","unstructured":"Manuelli, L., Li, Y., Florence, P.R., Tedrake, R.: Keypoints into the future: Self-supervised correspondence in model-based reinforcement learning. In: CoRL (2020)"},{"issue":"9","key":"31_CR33","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1038\/s41593-018-0209-y","volume":"21","author":"A Mathis","year":"2018","unstructured":"Mathis, A., et al.: Deeplabcut: markerless pose estimation of user-defined body parts with deep learning. Nat. Neurosci. 21(9), 1281\u20131289 (2018)","journal-title":"Nat. Neurosci."},{"issue":"1","key":"31_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-007-0085-5","volume":"79","author":"AS Mian","year":"2008","unstructured":"Mian, A.S., Bennamoun, M., Owens, R.: Keypoint detection and local feature matching for textured 3D face recognition. Int. J. Comput. Vision 79(1), 1\u201312 (2008)","journal-title":"Int. J. Comput. Vision"},{"key":"31_CR35","unstructured":"Minderer, M., Sun, C., Villegas, R., Cole, F., Murphy, K., Lee, H.: Unsupervised learning of object structure and dynamics from videos, June 2019"},{"key":"31_CR36","unstructured":"Minderer, M., Sun, C., Villegas, R., Cole, F., Murphy, K.P., Lee, H.: Unsupervised learning of object structure and dynamics from videos. ArXiv:abs\/1906.07889 (2019)"},{"key":"31_CR37","unstructured":"Mrowca, D., et al.: Flexible neural representation for physics prediction. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Paschalidou, D., Katharopoulos, A., Geiger, A., Fidler, S.: Neural parts: learning expressive 3D shape abstractions with invertible neural networks. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3203\u20133214 (2021)","DOI":"10.1109\/CVPR46437.2021.00322"},{"key":"31_CR39","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Chan, A., Derpanis, K.G., Daniilidis, K.: 6-dof object pose from semantic keypoints. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2011\u20132018. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989233"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Qin, Z., Fang, K., Zhu, Y., Fei-Fei, L., Savarese, S.: Learning keypoint representations for tool manipulation, KETO, October 2019","DOI":"10.1109\/ICRA40945.2020.9196971"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Samet, N., Akbas, E.: Hprnet: hierarchical point regression for whole-body human pose estimation. arXiv:abs\/2106.04269 (2021)","DOI":"10.1016\/j.imavis.2021.104285"},{"key":"31_CR42","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Roy, S., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: Motion-supervised co-part segmentation. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9650\u20139657 (2021)","DOI":"10.1109\/ICPR48806.2021.9412520"},{"key":"31_CR43","doi-asserted-by":"crossref","unstructured":"Stani\u0107, A., van Steenkiste, S., Schmidhuber, J.: Hierarchical relational inference. arXiv preprint arXiv:2010.03635 (2020)","DOI":"10.1609\/aaai.v35i11.17170"},{"key":"31_CR44","doi-asserted-by":"crossref","unstructured":"Thewlis, J., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks by factorized spatial embeddings. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3229\u20133238 (2017)","DOI":"10.1109\/ICCV.2017.348"},{"key":"31_CR45","unstructured":"Veerapaneni, R., et al.: Entity abstraction in visual model-based reinforcement learning. arXiv:abs\/1910.12827 (2019)"},{"key":"31_CR46","doi-asserted-by":"crossref","unstructured":"Xiong, H., Li, Q., Chen, Y.-C., Bharadhwaj, H., Sinha, S., Garg, A.: Learning by watching: physical imitation of manipulation skills from human videos. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7827\u20137834 (2021)","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"31_CR47","unstructured":"Xu, Z., et al.: Unsupervised discovery of parts, structure, and dynamics. arXiv:abs\/1903.05136 (2019)"},{"key":"31_CR48","doi-asserted-by":"crossref","unstructured":"Yang, J., Zhang, J., Settle, C., Rai, A., Antonova, R., Bohg, J.: Learning periodic tasks from human demonstrations. arXiv:abs\/2109.14078 (2022)","DOI":"10.1109\/ICRA46639.2022.9812402"},{"key":"31_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Guo, Y., Jin, Y., Luo, Y., He, Z., Lee, H.: Unsupervised discovery of object landmarks as structural representations. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2694\u20132703 (2018)","DOI":"10.1109\/CVPR.2018.00285"},{"key":"31_CR50","doi-asserted-by":"crossref","unstructured":"Zoran, D., Kabra, R., Lerchner, A., Rezende, D.J.: Parts: unsupervised segmentation with slots, attention and independence maximization. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10419\u201310427 (2021)","DOI":"10.1109\/ICCV48922.2021.01027"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19809-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T22:18:15Z","timestamp":1728253095000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19809-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198083","9783031198090"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19809-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}