{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:58:52Z","timestamp":1783439932365,"version":"3.54.6"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586065","type":"print"},{"value":"9783030586072","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\/978-3-030-58607-2_18","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T08:04:11Z","timestamp":1604649851000},"page":"303-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":71,"title":["Object-and-Action Aware Model for Visual Language Navigation"],"prefix":"10.1007","author":[{"given":"Yuankai","family":"Qi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zizheng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"van den Hengel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"18_CR1","unstructured":"Anderson, P., et al.: On evaluation of embodied navigation agents. CoRR abs\/1807.06757 (2018)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: CVPR, pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering. In: NAACL, pp. 1545\u20131554 (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"18_CR4","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: NeurIPS, pp. 3318\u20133329 (2018)"},{"key":"18_CR5","unstructured":"Fu, T., Wang, X., Peterson, M., Grafton, S., Eckstein, M.P., Wang, W.Y.: Counterfactual vision-and-language navigation via adversarial path sampling. CoRR abs\/1911.07308 (2019)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: end-to-end module networks for visual question answering. In: ICCV, pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"18_CR8","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: Proceedings of the 57th Conference of the Association for Computational Linguistics, Long Papers, ACL 2019, Florence, Italy, 28 July\u20132 August 2019, vol. 1, pp. 6551\u20136557 (2019)","DOI":"10.18653\/v1\/P19-1655"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Andreas, J., Darrell, T., Saenko, K.: Modeling relationships in referential expressions with compositional modular networks. In: CVPR, pp. 4418\u20134427 (2017)","DOI":"10.1109\/CVPR.2017.470"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Transferable representation learning in vision-and-language navigation. In: ICCV, pp. 7403\u20137412 (2019)","DOI":"10.1109\/ICCV.2019.00750"},{"key":"18_CR11","unstructured":"Ilharco, G., Jain, V., Ku, A., Ie, E., Baldridge, J.: General evaluation for instruction conditioned navigation using dynamic time warping. In: Visually Grounded Interaction and Language (ViGIL), NeurIPS 2019 Workshop, Vancouver, Canada, 13 December 2019 (2019)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Jain, V., Magalh\u00e3es, G., Ku, A., Vaswani, A., Ie, E., Baldridge, J.: Stay on the path: instruction fidelity in vision-and-language navigation. In: ACL, pp. 1862\u20131872 (2019)","DOI":"10.18653\/v1\/P19-1181"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Ke, L., et al.: Tactical rewind: self-correction via backtracking in vision-and-language navigation. In: CVPR, pp. 6741\u20136749 (2019)","DOI":"10.1109\/CVPR.2019.00690"},{"key":"18_CR14","unstructured":"Landi, F., Baraldi, L., Cornia, M., Corsini, M., Cucchiara, R.: Perceive, transform, and act: multi-modal attention networks for vision-and-language navigation. CoRR abs\/1911.12377 (2019)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Robust navigation with language pretraining and stochastic sampling. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) EMNLP, pp. 1494\u20131499 (2019)","DOI":"10.18653\/v1\/D19-1159"},{"key":"18_CR16","unstructured":"Ma, C.Y., et al.: Self-monitoring navigation agent via auxiliary progress estimation. In: ICLR (2019)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Ma, C., Wu, Z., AlRegib, G., Xiong, C., Kira, Z.: The regretful agent: heuristic-aided navigation through progress estimation. In: CVPR, pp. 6732\u20136740 (2019)","DOI":"10.1109\/CVPR.2019.00689"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Tan, H., Yu, L., Bansal, M.: Learning to navigate unseen environments: back translation with environmental dropout. In: NAACL, pp. 2610\u20132621 (2019)","DOI":"10.18653\/v1\/N19-1268"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: CVPR, pp. 6629\u20136638 (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Wang, X., Jain, V., Ie, E., Wang, W.Y., Kozareva, Z., Ravi, S.: Environment-agnostic multitask learning for natural language grounded navigation. CoRR abs\/2003.00443 (2020)","DOI":"10.1007\/978-3-030-58586-0_25"},{"key":"18_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-01270-0_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Xiong, W., Wang, H., Wang, W.Y.: Look before you leap: bridging model-free and model-based reinforcement learning for planned-ahead vision-and-language navigation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 38\u201355. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_3"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MattNet: modular attention network for referring expression comprehension. In: CVPR, pp. 1307\u20131315 (2018)","DOI":"10.1109\/CVPR.2018.00142"}],"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\/978-3-030-58607-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:44:46Z","timestamp":1730853886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58607-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586065","9783030586072"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58607-2_18","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":"7 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.","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)"}}]}}