{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:43:57Z","timestamp":1775529837677,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586003","type":"print"},{"value":"9783030586010","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\/978-3-030-58601-0_39","type":"book-chapter","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T19:02:52Z","timestamp":1606503772000},"page":"663-678","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Multi-agent Embodied Question Answering in Interactive Environments"],"prefix":"10.1007","author":[{"given":"Sinan","family":"Tan","sequence":"first","affiliation":[]},{"given":"Weilai","family":"Xiang","sequence":"additional","affiliation":[]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Di","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Fuchun","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,28]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: Visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. arXiv preprint arXiv:1709.06158 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Curless, B., Levoy, M.: A volumetric method for building complex models from range images. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, pp. 303\u2013312 (1996)","DOI":"10.1145\/237170.237269"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Das, A., Datta, S., Gkioxari, G., Lee, S., Parikh, D., Batra, D.: Embodied question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2054\u20132063 (2018)","DOI":"10.1109\/CVPRW.2018.00279"},{"issue":"4","key":"39_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322942","volume":"38","author":"S Dong","year":"2019","unstructured":"Dong, S., et al.: Multi-robot collaborative dense scene reconstruction. ACM Trans. Graph. (TOG) 38(4), 1\u201316 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"39_CR6","unstructured":"Foerster, J., Assael, I.A., De Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2137\u20132145 (2016)"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Gordon, D., Kembhavi, A., Rastegari, M., Redmon, J., Fox, D., Farhadi, A.: IQA: visual question answering in interactive environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4089\u20134098 (2018)","DOI":"10.1109\/CVPR.2018.00430"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Graham, B., van der Maaten, L.: Submanifold sparse convolutional networks. arXiv preprint arXiv:1706.01307 (2017)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: The IEEE International Conference on Computer Vision (ICCV) October 2017","DOI":"10.1109\/ICCV.2017.322"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Hou, J., Dai, A., Niessner, M.: 3D-sis: 3D semantic instance segmentation of RGB-D scans. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2019","DOI":"10.1109\/CVPR.2019.00455"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: Deepmvs: learning multi-view stereopsis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2821\u20132830 (2018)","DOI":"10.1109\/CVPR.2018.00298"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Izadi, S., et al.: Kinectfusion: real-time 3D reconstruction and interaction using a moving depth camera. In: Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology, pp. 559\u2013568 (2011)","DOI":"10.1145\/2047196.2047270"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: TGIF-QA: toward spatio-temporal reasoning in visual question answering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) July 2017","DOI":"10.1109\/CVPR.2017.149"},{"key":"39_CR14","unstructured":"Kolve, E., et al.: Ai2-thor: an interactive 3D environment for visual AI. arXiv preprint arXiv:1712.05474 (2017)"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., Fritz, M.: Ask your neurons: a neural-based approach to answering questions about images. In: The IEEE International Conference on Computer Vision (ICCV) December 2015","DOI":"10.1109\/ICCV.2015.9"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Mousavi, H.K., Nazari, M., Tak\u00e1\u010d, M., Motee, N.: Multi-agent image classification via reinforcement learning. arXiv preprint arXiv:1905.04835 (2019)","DOI":"10.1109\/IROS40897.2019.8968129"},{"key":"39_CR17","unstructured":"Savva, M., et al.: Habitat: a platform for embodied AI research. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9339\u20139347 (2019)"},{"issue":"3","key":"39_CR18","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P Stone","year":"2000","unstructured":"Stone, P., Veloso, M.: Multiagent systems: a survey from a machine learning perspective. Autonom. Robot. 8(3), 345\u2013383 (2000)","journal-title":"Autonom. Robot."},{"key":"39_CR19","unstructured":"Sukhbaatar, S., Fergus, R., et al.: Learning multiagent communication with backpropagation. In: Advances in Neural Information Processing Systems, pp. 2244\u20132252 (2016)"},{"key":"39_CR20","unstructured":"Wu, Y., Wu, Y., Gkioxari, G., Tian, Y.: Building generalizable agents with a realistic and rich 3D environment. arXiv preprint arXiv:1801.02209 (2018)"},{"key":"39_CR21","unstructured":"Xia, F., et al.: Gibson Env V2: Embodied simulation environments for interactive navigation (2019)"},{"key":"39_CR22","unstructured":"Yang, W., Wang, X., Farhadi, A., Gupta, A., Mottaghi, R.: Visual semantic navigation using scene priors. arXiv preprint arXiv:1810.06543 (2018)"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Video question answering via hierarchical spatio-temporal attention networks. In: IJCAI, pp. 3518\u20133524 (2017)","DOI":"10.24963\/ijcai.2017\/492"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Zheng, L., et al.: Active scene understanding via online semantic reconstruction. In: Computer Graphics Forum. vol. 38, pp. 103\u2013114. Wiley Online Library (2019)","DOI":"10.1111\/cgf.13820"},{"key":"39_CR25","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 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58601-0_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:18:17Z","timestamp":1732666697000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58601-0_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586003","9783030586010"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58601-0_39","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":"28 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. 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)"}}]}}