{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:16:36Z","timestamp":1774124196496,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585419","type":"print"},{"value":"9783030585426","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\/978-3-030-58542-6_19","type":"book-chapter","created":{"date-parts":[[2020,11,16]],"date-time":"2020-11-16T17:06:34Z","timestamp":1605546394000},"page":"307-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":48,"title":["Active Visual Information Gathering for Vision-Language Navigation"],"prefix":"10.1007","author":[{"given":"Hanqing","family":"Wang","sequence":"first","affiliation":[]},{"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tianmin","family":"Shu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,17]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Andreas, J., Klein, D.: Alignment-based compositional semantics for instruction following. In: EMNLP (2015)","DOI":"10.18653\/v1\/D15-1138"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D.L., Mooney, R.J.: Learning to interpret natural language navigation instructions from observations. In: AAAI (2011)","DOI":"10.1609\/aaai.v25i1.7974"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"19_CR7","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: NeurIPS (2018)"},{"key":"19_CR8","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":"19_CR9","doi-asserted-by":"crossref","unstructured":"Hu, R., Fried, D., Rohrbach, A., Klein, D., Darrell, T., Saenko, K.: Are you looking? Grounding to multiple modalities in vision-and-language navigation. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1655"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Transferable representation learning in vision-and-language navigation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00750"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Ke, L., et al.: Tactical rewind: self-correction via backtracking in vision-and-language navigation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00690"},{"key":"19_CR12","unstructured":"Ma, C.Y., et al.: Self-monitoring navigation agent via auxiliary progress estimation. In: ICLR (2019)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Ma, C.Y., Wu, Z., AlRegib, G., Xiong, C., Kira, Z.: The regretful agent: heuristic-aided navigation through progress estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00689"},{"key":"19_CR14","unstructured":"MacMahon, M., Stankiewicz, B., Kuipers, B.: Walk the talk: connecting language, knowledge, and action in route instructions. In: AAAI (2006)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Mei, H., Bansal, M., Walter, M.R.: Listen, attend, and walk: neural mapping of navigational instructions to action sequences. In: AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10364"},{"key":"19_CR16","unstructured":"Mirowski, P., et al.: Learning to navigate in complex environments. In: ICLR (2017)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Misra, D., Bennett, A., Blukis, V., Niklasson, E., Shatkhin, M., Artzi, Y.: Mapping instructions to actions in 3D environments with visual goal prediction. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1287"},{"key":"19_CR18","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML (2016)"},{"issue":"3","key":"19_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Internat. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Internat. J. Comput. Vis."},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Tan, H., Yu, L., Bansal, M.: Learning to navigate unseen environments: back translation with environmental dropout. In: NAACL (2019)","DOI":"10.18653\/v1\/N19-1268"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Tellex, S., et al.: Understanding natural language commands for robotic navigation and mobile manipulation. In: AAAI (2011)","DOI":"10.1609\/aaai.v25i1.7979"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Thomason, J., Gordon, D., Bisk, Y.: Shifting the baseline: single modality performance on visual navigation & QA. In: NAACL (2019)","DOI":"10.18653\/v1\/N19-1197"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Xiong, W., Wang, H., Yang Wang, W.: Look before you leap: bridging model-free and model-based reinforcement learning for planned-ahead vision-and-language navigation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"19_CR25","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"19_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, W., Qi, S., Zhu, S.C.: Reasoning visual dialogs with structural and partial observations. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00683"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, F., Zhu, Y., Chang, X., Liang, X.: Vision-language navigation with self-supervised auxiliary reasoning tasks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: ICRA (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\/978-3-030-58542-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:06:59Z","timestamp":1731715619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58542-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585419","9783030585426"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58542-6_19","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":"17 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)"}}]}}