{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:36:50Z","timestamp":1789079810992,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729911","type":"print"},{"value":"9783031729928","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72992-8_5","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"72-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Look Around and Learn: Self-training Object Detection by\u00a0Exploration"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3468-8902","authenticated-orcid":false,"given":"Gianluca","family":"Scarpellini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6458-6344","authenticated-orcid":false,"given":"Stefano","family":"Rosa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5259-1496","authenticated-orcid":false,"given":"Pietro","family":"Morerio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8777-5233","authenticated-orcid":false,"given":"Lorenzo","family":"Natale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2262-4872","authenticated-orcid":false,"given":"Alessio","family":"Del Bue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","volume":"76","author":"M Abdar","year":"2021","unstructured":"Abdar, M., et al.: A review of uncertainty quantification in deep learning: techniques, applications and challenges. Inf. Fusion 76, 243\u2013297 (2021)","journal-title":"Inf. Fusion"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Ahmadyan, A., Zhang, L., Ablavatski, A., Wei, J., Grundmann, M.: Objectron: a large scale dataset of object-centric videos in the wild with pose annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7822\u20137831 (2021)","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"5_CR3","doi-asserted-by":"publisher","unstructured":"Arazo, E., Ortego, D., Albert, P., O\u2019Connor, N.E., McGuinness, K.: Pseudo-labeling and confirmation bias in deep semi-supervised learning. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138 (2020). https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9207304","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Armeni, I., He, Z.Y., Gwak, J., Zamir, A.R., Fischer, M., Malik, J., Savarese, S.: 3D scene graph: a structure for unified semantics, 3D space, and camera. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5664\u20135673 (2019)","DOI":"10.1109\/ICCV.2019.00576"},{"issue":"2","key":"5_CR5","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s10514-017-9615-3","volume":"42","author":"R Bajcsy","year":"2018","unstructured":"Bajcsy, R., Aloimonos, Y., Tsotsos, J.K.: Revisiting active perception. Auton. Robot. 42(2), 177\u2013196 (2018)","journal-title":"Auton. Robot."},{"key":"5_CR6","unstructured":"Chaplot, D.S., Dalal, M., Gupta, S., Malik, J., Salakhutdinov, R.: SEAL: self-supervised embodied active learning using exploration and 3D consistency. In: Thirty-Fifth Conference on Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=guHXB1dcD3l"},{"key":"5_CR7","unstructured":"Chaplot, D.S., Gandhi, D., Gupta, S., Gupta, A., Salakhutdinov, R.: Learning to explore using active neural slam. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=HklXn1BKDH"},{"key":"5_CR8","unstructured":"Chaplot, D.S., Gandhi, D.P., Gupta, A., Salakhutdinov, R.R.: Object goal navigation using goal-oriented semantic exploration. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"},{"key":"5_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-030-58539-6_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"DS Chaplot","year":"2020","unstructured":"Chaplot, D.S., Jiang, H., Gupta, S., Gupta, A.: Semantic curiosity for active visual learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 309\u2013326. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_19"},{"issue":"3","key":"5_CR10","doi-asserted-by":"publisher","first-page":"4401","DOI":"10.1109\/LRA.2021.3068655","volume":"6","author":"AS Chen","year":"2021","unstructured":"Chen, A.S., Nam, H., Nair, S., Finn, C.: Batch exploration with examples for scalable robotic reinforcement learning. IEEE Robot. Autom. Lett. 6(3), 4401\u20134408 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"5_CR11","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":"5_CR12","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 22243\u201322255 (2020)"},{"key":"5_CR13","unstructured":"Fang, Z., Jain, A., Sarch, G., Harley, A.W., Fragkiadaki, K.: Move to see better: self-improving embodied object detection. arXiv preprint arXiv:2012.00057 (2020)"},{"key":"5_CR14","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050\u20131059. PMLR (2016)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Gibson, J.J.: The perception of the visual world (1950)","DOI":"10.2307\/1418003"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN (2018)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5_CR17","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015). http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Jing, Y., Kong, T.: Learning to explore informative trajectories and samples for embodied perception. In: IEEE International Conference on Robotics and Automation (ICRA) (2023)","DOI":"10.1109\/ICRA48891.2023.10160951"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Kotar, K., Mottaghi, R.: Interactron: embodied adaptive object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14860\u201314869 (2022)","DOI":"10.1109\/CVPR52688.2022.01444"},{"key":"5_CR20","unstructured":"Lee, D.H., et\u00a0al.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol.\u00a03, p.\u00a0896 (2013)"},{"key":"5_CR21","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":"5_CR22","doi-asserted-by":"publisher","unstructured":"Little, D., Sommer, F.: Learning and exploration in action-perception loops. Front. Neural Circ. 7 (2013). https:\/\/doi.org\/10.3389\/fncir.2013.00037. https:\/\/www.frontiersin.org\/article\/10.3389\/fncir.2013.00037","DOI":"10.3389\/fncir.2013.00037"},{"key":"5_CR23","unstructured":"Liu, Y.C., et al.: Unbiased teacher for semi-supervised object detection. In: International Conference on Learning Representations (2021)"},{"key":"5_CR24","doi-asserted-by":"publisher","unstructured":"Macenski, S., Foote, T., Gerkey, B., Lalancette, C., Woodall, W.: Robot operating system 2: design, architecture, and uses in the wild. Sci. Robot. 7(66), eabm6074 (2022). https:\/\/doi.org\/10.1126\/scirobotics.abm6074. https:\/\/www.science.org\/doi\/abs\/10.1126\/scirobotics.abm6074","DOI":"10.1126\/scirobotics.abm6074"},{"key":"5_CR25","unstructured":"Metta, G., et al.: YARP - yet another robot platform. www.yarp.it"},{"key":"5_CR26","unstructured":"Min, S.Y., et al.: Self-supervised object goal navigation with in-situ finetuning (2023). https:\/\/arxiv.org\/abs\/2212.05923"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Mohammadi, S.S., Wang, Y., Del\u00a0Bue, A.: PointView-GCN: 3D shape classification with multi-view point clouds. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3103\u20133107. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506426"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Parmiggiani, A., et\u00a0al.: The design and validation of the R1 personal humanoid. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 674\u2013680. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202224"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.K., Jayaraman, D., Grauman, K.: An exploration of embodied visual exploration (2020)","DOI":"10.1007\/s11263-021-01437-z"},{"key":"5_CR30","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28, pp. 91\u201399 (2015)"},{"key":"5_CR31","doi-asserted-by":"publisher","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015). https:\/\/doi.org\/10.1109\/cvpr.2015.7298682","DOI":"10.1109\/cvpr.2015.7298682"},{"key":"5_CR32","unstructured":"Smith, W.S.: Connected-components-3D (2022). GitHub. Note. https:\/\/pypi.org\/project\/connected-components-3d\/"},{"key":"5_CR33","unstructured":"Szot, A., et al.: Habitat 2.0: training home assistants to rearrange their habitat (2021)"},{"key":"5_CR34","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Xia, F., Zamir, A.R., He, Z.Y., Sax, A., Malik, J., Savarese, S.: Gibson ENV: real-world perception for embodied agents. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2018)","DOI":"10.1109\/CVPR.2018.00945"},{"key":"5_CR36","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation for consistency training. arXiv preprint arXiv:1904.12848 (2019)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves imagenet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687\u201310698 (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"5_CR38","unstructured":"Yalniz, I.Z., J\u00e9gou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019)"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Yamauchi, B.: Frontier-based exploration using multiple robots. In: Proceedings of the Second International Conference on Autonomous Agents, pp. 47\u201353 (1998)","DOI":"10.1145\/280765.280773"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Embodied amodal recognition: learning to move to perceive objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2040\u20132050 (2019)","DOI":"10.1109\/ICCV.2019.00213"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3357\u20133364. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989381"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72992-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:44:31Z","timestamp":1730191471000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 2024","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":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}