{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:18:45Z","timestamp":1743031125268,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434204"},{"type":"electronic","value":"9783031434211"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43421-1_37","type":"book-chapter","created":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:37:24Z","timestamp":1694983044000},"page":"629-644","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Geometric Representations of\u00a0Objects via\u00a0Interaction"],"prefix":"10.1007","author":[{"given":"Alfredo","family":"Reichlin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni Luca","family":"Marchetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasiia","family":"Varava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,18]]},"reference":[{"issue":"8","key":"37_CR1","doi-asserted-by":"publisher","first-page":"966","DOI":"10.1109\/5.5968","volume":"76","author":"R Bajcsy","year":"1988","unstructured":"Bajcsy, R.: Active perception. Proc. IEEE 76(8), 966\u20131005 (1988)","journal-title":"Proc. IEEE"},{"key":"37_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/11744023_32","volume-title":"Computer Vision \u2013 ECCV 2006","author":"H Bay","year":"2006","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404\u2013417. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_32"},{"issue":"8","key":"37_CR3","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Bj\u00f6rkman, M., Bekiroglu, Y., H\u00f6gman, V., Kragic, D.: Enhancing visual perception of shape through tactile glances. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3180\u20133186 (2013)","DOI":"10.1109\/IROS.2013.6696808"},{"issue":"6","key":"37_CR5","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1109\/TRO.2017.2721939","volume":"33","author":"J Bohg","year":"2017","unstructured":"Bohg, J., et al.: Interactive perception: leveraging action in perception and perception in action. IEEE Trans. Rob. 33(6), 1273\u20131291 (2017)","journal-title":"IEEE Trans. Rob."},{"key":"37_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"37_CR7","unstructured":"Gibson, J.J., Carmichael, L.: The Senses Considered as Perceptual Systems, vol. 2. Houghton Mifflin, Boston (1966)"},{"key":"37_CR8","unstructured":"Gopalakrishnan, A., van Steenkiste, S., Schmidhuber, J.: Unsupervised object keypoint learning using local spatial predictability. In: ICLR 2021 (2020)"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Guo, X., Zhu, E., Liu, X., Yin, J.: Affine equivariant autoencoder. In: IJCAI, pp. 2413\u20132419 (2019)","DOI":"10.24963\/ijcai.2019\/335"},{"key":"37_CR10","unstructured":"Ha, D., Schmidhuber, J.: World models. arXiv preprint arXiv:1803.10122 (2018)"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5","key":"37_CR12","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1037\/h0040546","volume":"56","author":"R Held","year":"1963","unstructured":"Held, R., Hein, A.: Movement-produced stimulation in the development of visually guided behavior. J. Comparat. Physiol. Psychol. 56(5), 872 (1963)","journal-title":"J. Comparat. Physiol. Psychol."},{"issue":"2","key":"37_CR13","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1177\/0278364913497816","volume":"33","author":"J Ilonen","year":"2014","unstructured":"Ilonen, J., Bohg, J., Kyrki, V.: Three-dimensional object reconstruction of symmetric objects by fusing visual and tactile sensing. Int. J. Rob. Res. 33(2), 321\u2013341 (2014)","journal-title":"Int. J. Rob. Res."},{"key":"37_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"37_CR15","unstructured":"Kipf, T., van der Pol, E., Welling, M.: Contrastive learning of structured world models. arXiv preprint arXiv:1911.12247 (2019)"},{"key":"37_CR16","first-page":"1","volume":"32","author":"TD Kulkarni","year":"2019","unstructured":"Kulkarni, T.D., et al.: Unsupervised learning of object keypoints for perception and control. Adv. Neural Inf. Process. Syst. 32, 1\u201311 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"37_CR17","doi-asserted-by":"publisher","first-page":"e253","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":"37_CR18","unstructured":"Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations. In: International Conference on Machine Learning, pp. 4114\u20134124. PMLR (2019)"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150\u20131157. IEEE (1999)","DOI":"10.1109\/ICCV.1999.790410"},{"key":"37_CR20","unstructured":"Marchetti, G.L., Tegn\u00e9r, G., Varava, A., Kragic, D.: Equivariant representation learning via class-pose decomposition. arXiv preprint arXiv:2207.03116 (2022)"},{"key":"37_CR21","unstructured":"Mondal, A.K., Jain, V., Siddiqi, K., Ravanbakhsh, S.: Eqr: equivariant representations for data-efficient reinforcement learning. In: International Conference on Machine Learning, pp. 15908\u201315926. PMLR (2022)"},{"key":"37_CR22","unstructured":"Mondal, A.K., Nair, P., Siddiqi, K.: Group equivariant deep reinforcement learning. arXiv preprint arXiv:2007.03437 (2020)"},{"key":"37_CR23","volume-title":"Action in Perception","author":"A No\u00eb","year":"2004","unstructured":"No\u00eb, A., No\u00eb, A., et al.: Action in Perception. MIT press, Cambridge (2004)"},{"issue":"1","key":"37_CR24","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62\u201366 (1979)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"37_CR25","unstructured":"Park, J.Y., Biza, O., Zhao, L., van de Meent, J.W., Walters, R.: Learning symmetric embeddings for equivariant world models. arXiv preprint arXiv:2204.11371 (2022)"},{"key":"37_CR26","unstructured":"van der Pol, E., Kipf, T., Oliehoek, F.A., Welling, M.: Plannable approximations to mdp homomorphisms: Equivariance under actions. arXiv preprint arXiv:2002.11963 (2020)"},{"key":"37_CR27","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: International Conference on Machine Learning, pp. 1278\u20131286. PMLR (2014)"},{"issue":"5","key":"37_CR28","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1177\/1059712313484502","volume":"21","author":"D Schiebener","year":"2013","unstructured":"Schiebener, D., Morimoto, J., Asfour, T., Ude, A.: Integrating visual perception and manipulation for autonomous learning of object representations. Adapt. Behav. 21(5), 328\u2013345 (2013)","journal-title":"Adapt. Behav."},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"37_CR30","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"37_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/3-540-44480-7_21","volume-title":"Vision Algorithms: Theory and Practice","author":"B Triggs","year":"2000","unstructured":"Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment\u2014a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) IWVA 1999. LNCS, vol. 1883, pp. 298\u2013372. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-44480-7_21"},{"issue":"3","key":"37_CR32","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1109\/70.88140","volume":"7","author":"C Tsikos","year":"1991","unstructured":"Tsikos, C., Bajcsy, R.: Segmentation via manipulation. IEEE Trans. Rob. Autom. 7(3), 306\u2013319 (1991)","journal-title":"IEEE Trans. Rob. Autom."},{"key":"37_CR33","first-page":"1","volume":"28","author":"M Watter","year":"2015","unstructured":"Watter, M., Springenberg, J., Boedecker, J., Riedmiller, M.: Embed to control: a locally linear latent dynamics model for control from raw images. Adv. Neural Inf. Process. Syst. 28, 1\u20139 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43421-1_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:47:53Z","timestamp":1694983673000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43421-1_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434204","9783031434211"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43421-1_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"We believe that the present work does not raise specific ethical concerns. Generally speaking, however, any system endowing artificial agents with intelligent behavior may be misused e.g., for military applications. Since we propose a representation learning method enabling an agent to locate objects in an environment, this can be potentially embedded into intelligent harmful systems and deployed for unethical applications.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Statement"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","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":"829","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":"196","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":"24% - 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":"3.63","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":"4.5","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":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","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)"}}]}}