{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:57:40Z","timestamp":1791914260348,"version":"4.3.4"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585853","type":"print"},{"value":"9783030585860","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\/978-3-030-58586-0_25","type":"book-chapter","created":{"date-parts":[[2020,11,29]],"date-time":"2020-11-29T17:02:42Z","timestamp":1606669362000},"page":"413-430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Environment-Agnostic Multitask Learning for Natural Language Grounded Navigation"],"prefix":"10.1007","author":[{"given":"Xin Eric","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vihan","family":"Jain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugene","family":"Ie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zornitsa","family":"Kozareva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sujith","family":"Ravi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,30]]},"reference":[{"key":"25_CR1","unstructured":"Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2016), pp. 265\u2013283 (2016). https:\/\/www.usenix.org\/system\/files\/conference\/osdi16\/osdi16-abadi.pdf"},{"key":"25_CR2","unstructured":"Anderson, P., et al.: On evaluation of embodied navigation agents (2018). arXiv:1807.06757 [cs.AI]"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Bain, M., Sammut, C.: A framework for behavioural cloning. In: Machine Intelligence 15, Intelligent Agents, St. Catherine\u2019s College, Oxford, July 1995, pp. 103\u2013129. Oxford University, Oxford (1999). http:\/\/dl.acm.org\/citation.cfm?id=647636.733043","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Caruana, R.: Multitask learning: a knowledge-based source of inductive bias. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 41\u201348. Morgan Kaufmann (1993)","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Suhr, A., Misra, D., Snavely, N., Artzi, Y.: Touchdown: natural language navigation and spatial reasoning in visual street environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12538\u201312547 (2019)","DOI":"10.1109\/CVPR.2019.01282"},{"key":"25_CR8","doi-asserted-by":"publisher","unstructured":"Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning, ICML 2008, pp. 160\u2013167. ACM, New York (2008). https:\/\/doi.org\/10.1145\/1390156.1390177","DOI":"10.1145\/1390156.1390177"},{"key":"25_CR9","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"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"25_CR11","doi-asserted-by":"publisher","unstructured":"Deng, L., Hinton, G., Kingsbury, B.: New types of deep neural network learning for speech recognition and related applications: an overview. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8599\u20138603 (2013). https:\/\/doi.org\/10.1109\/ICASSP.2013.6639344","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"25_CR12","unstructured":"Espeholt, L., et al.: IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, PMLR, Stockholmsm\u00e4ssan, Stockholm Sweden, 10\u201315 July 2018, vol. 80, pp. 1407\u20131416. http:\/\/proceedings.mlr.press\/v80\/espeholt18a.html"},{"key":"25_CR13","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. Volume 70, pp. 1126\u20131135. JMLR. org (2017)"},{"key":"25_CR14","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Fu, T.J., Wang, X., Peterson, M., Grafton, S., Eckstein, M., Wang, W.Y.: Counterfactual vision-and-language navigation via adversarial path sampling. arXiv preprint arXiv:1911.07308 (2019)","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"25_CR16","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32Nd International Conference on International Conference on Machine Learning, ICML 2015, vol. 37, pp. 1180\u20131189. JMLR.org (2015). http:\/\/dl.acm.org\/citation.cfm?id=3045118.3045244"},{"key":"25_CR17","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Hemachandra, S., Duvallet, F., Howard, T.M., Roy, N., Stentz, A., Walter, M.R.: Learning models for following natural language directions in unknown environments. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 5608\u20135615. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7139984"},{"key":"25_CR19","doi-asserted-by":"publisher","unstructured":"Huang, H., Jain, V., Mehta, H., Baldridge, J., Ie, E.: Multi-modal discriminative model for vision-and-language navigation. In: Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP), pp. 40\u201349. Association for Computational Linguistics, Minneapolis (2019). https:\/\/doi.org\/10.18653\/v1\/W19-1605, https:\/\/www.aclweb.org\/anthology\/W19-1605","DOI":"10.18653\/v1\/W19-1605"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Transferable representation learning in vision-and-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), vol. 178 (2019)","DOI":"10.1109\/ICCV.2019.00750"},{"key":"25_CR21","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 (2019)","DOI":"10.18653\/v1\/P19-1181"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Ke, L., et al.: Tactical rewind: self-correction via backtracking in vision-and-language navigation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6741\u20136749 (2019)","DOI":"10.1109\/CVPR.2019.00690"},{"key":"25_CR23","unstructured":"Kolve, E., et al.: AI2-THOR: An Interactive 3D Environment for Visual AI. arXiv (2017)"},{"key":"25_CR24","unstructured":"Lansing, L., Jain, V., Mehta, H., Huang, H., Ie, E.: VALAN: vision and language agent navigation. ArXiv abs\/1912.03241 (2019)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Unsupervised reinforcement learning of transferable meta-skills for embodied navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12123\u201312132 (2020)","DOI":"10.1109\/CVPR42600.2020.01214"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Baldwin, T., Cohn, T.: What\u2019s in a Domain? Learning Domain-Robust Text Representations using Adversarial Training. In: NAACL-HLT (2018)","DOI":"10.18653\/v1\/N18-2076"},{"key":"25_CR27","unstructured":"Liu, A.H., Liu, Y.C., Yeh, Y.Y., Wang, Y.C.F.: A unified feature disentangler for multi-domain image translation and manipulation. In: Advances in Neural Information Processing Systems, pp. 2590\u20132599 (2018)"},{"key":"25_CR28","unstructured":"Ma, C.Y., et al.: Self-monitoring navigation agent via auxiliary progress estimation. arXiv preprint arXiv:1901.03035 (2019)"},{"key":"25_CR29","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6732\u20136740 (2019)","DOI":"10.1109\/CVPR.2019.00689"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Savva, M., et al.: Habitat: a platform for embodied AI research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"25_CR31","unstructured":"Mirowski, P., et al.: Learning to navigate in cities without a map. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31, pp. 2419\u20132430. Curran Associates, Inc. (2018). http:\/\/papers.nips.cc\/paper\/7509-learning-to-navigate-in-cities-without-a-map.pdf"},{"key":"25_CR32","unstructured":"Mirowski, P.W., et al.: Learning to navigate in complex environments. ArXiv abs\/1611.03673 (2016)"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Daum\u00e9 III, H.: Help, anna! visual navigation with natural multimodal assistance via retrospective curiosity-encouraging imitation learning. arXiv preprint arXiv:1909.01871 (2019)","DOI":"10.18653\/v1\/D19-1063"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Dey, D., Brockett, C., Dolan, B.: Vision-based navigation with language-based assistance via imitation learning with indirect intervention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12527\u201312537 (2019)","DOI":"10.1109\/CVPR.2019.01281"},{"key":"25_CR35","unstructured":"Peng, X., Huang, Z., Sun, X., Saenko, K.: Domain agnostic learning with disentangled representations. In: Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, California, USA, 9\u201315 June 2019, pp. 5102\u20135112 (2019)"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Qi, Y., et al.: Reverie: remote embodied visual referring expression in real indoor environments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9982\u20139991 (2020)","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"25_CR37","unstructured":"Ramsundar, B., Kearnes, S.M., Riley, P., Webster, D., Konerding, D.E., Pande, V.S.: Massively multitask networks for drug discovery. ArXiv abs\/1502.02072 (2015)"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Romijnders, R., Meletis, P., Dubbelman, G.: A domain agnostic normalization layer for unsupervised adversarial domain adaptation. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1866\u20131875. IEEE (2019)","DOI":"10.1109\/WACV.2019.00203"},{"key":"25_CR39","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"25_CR40","doi-asserted-by":"publisher","unstructured":"Tan, H., Yu, L., Bansal, M.: Learning to navigate unseen environments: back translation with environmental dropout. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 2610\u20132621. Association for Computational Linguistics, Minneapolis (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1268","DOI":"10.18653\/v1\/N19-1268"},{"key":"25_CR41","unstructured":"Teh, Y., et al.: Distral: robust multitask reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 4496\u20134506 (2017)"},{"key":"25_CR42","unstructured":"Thomason, J., Murray, M., Cakmak, M., Zettlemoyer, L.: Vision-and-dialog navigation. In: Conference on Robot Learning (CoRL) (2019)"},{"key":"25_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"25_CR44","unstructured":"de Vries, H., Shuster, K., Batra, D., Parikh, D., Weston, J., Kiela, D.: Talk the walk: navigating New York City through grounded dialogue. arXiv preprint arXiv:1807.03367 (2018)"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6629\u20136638 (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"25_CR46","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"},{"issue":"3","key":"25_CR47","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3), 229\u2013256 (1992). https:\/\/doi.org\/10.1007\/BF00992696","journal-title":"Mach. Learn."},{"key":"25_CR48","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":"25_CR49","unstructured":"Wu, Y., Wu, Y., Tamar, A., Russell, S., Gkioxari, G., Tian, Y.: Learning and planning with a semantic model. arXiv preprint arXiv:1809.10842 (2018)"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Xia, F., R. Zamir, A., 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"}],"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\/978-3-030-58586-0_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:11:02Z","timestamp":1732839062000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58586-0_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585853","9783030585860"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58586-0_25","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":"30 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)"}}]}}