{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:58:44Z","timestamp":1783439924022,"version":"3.54.6"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585389","type":"print"},{"value":"9783030585396","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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58539-6_5","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:02:46Z","timestamp":1604689366000},"page":"71-86","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler"],"prefix":"10.1007","author":[{"given":"Tsu-Jui","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin Eric","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew F.","family":"Peterson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott T.","family":"Grafton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miguel P.","family":"Eckstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Agmon, N.: Robotic strategic behavior in adversarial environments. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/731"},{"key":"5_CR2","unstructured":"Anderson, P., et al.: On evaluation of embodied navigation agents. arXiv:1807.06757 (2018)"},{"key":"5_CR3","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":"5_CR4","unstructured":"Angel, C., e al.: Matterport3D: learning from RGB-D data in indoor environments. In: 3DV (2017)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Antoniou, A., Storkey, A., Edwards, H.: Data augmentation generative adversarial networks. arXiv:1711.04340 (2017)","DOI":"10.1007\/978-3-030-01424-7_58"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Ashual, O., Wolf, L.: Specifying object attributes and relations in interactive scene generation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00466"},{"key":"5_CR7","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"5_CR8","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01282"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., He, X., Pu, S., Chang, S.F.: Counterfactual critic multi-agent training for scene graph generation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00471"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Chou, C.J., Chien, J.T., Chen, H.T.: Self adversarial training for human pose estimation. In: APSIPA (2018)","DOI":"10.23919\/APSIPA.2018.8659538"},{"key":"5_CR11","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: NeurIPS (2018)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Garg, S., Perot, V., Limtiaco, N., Taly, A., Chi, E.H., Beutel, A.: Counterfactual fairness in text classification through robustness. In: AIES (2019)","DOI":"10.1145\/3306618.3317950"},{"key":"5_CR13","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. In: NeurIPS (2014)"},{"key":"5_CR14","unstructured":"Goyal, Y., Wu, Z., Ernst, J., Batra, D., Parikh, D., Lee, S.: Counterfactual visual explanations. In: ICML (2019)"},{"key":"5_CR15","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":"5_CR16","doi-asserted-by":"crossref","unstructured":"Hemachandra, S., Duvallet, F., Howard, T.M., Stentz, A., Roy, N., Walter, M.R.: learning models for following natural language directions in unknown environments. In: ICRA (2015)","DOI":"10.1109\/ICRA.2015.7139984"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. In: Neural Computation (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"5_CR18","unstructured":"Hong, Z.W., Fu, T.J., Shann, T.Y., Chang, Y.H., Lee, C.Y.: Adversarial active exploration for inverse dynamics model learning. In: CoRL (2019)"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Huang, H., Jain, V., Mehta, H., Baldridge, J., Ie, E.: Multi-modal discriminative model for vision-and-language navigation. In: NAACL Workshop (2019)","DOI":"10.18653\/v1\/W19-1605"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Huang, H., Jain, V., Mehta, H., Ku, A., Magalhaes, G., Baldridge, J., Ie, E.: Transferable representation learning in vision-and-language navigation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00750"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Jain, V., Magalhaes, G., Ku, A., Vaswani, A., Ie, E., Baldridge, J.: Stay on the path: instruction fidelity in vision-and-language navigation. arXiv:1905.12255 (2019)","DOI":"10.18653\/v1\/P19-1181"},{"key":"5_CR22","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":"5_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"5_CR24","unstructured":"Kusner, M., Loftus, J., Russell, C., Silva, R.: Counterfactual fairness. In: NeurIPS (2017)"},{"key":"5_CR25","unstructured":"Ma, C.Y., et al.: Self-monitoring navigation agent via auxiliary progress estimation. In: ICLR (2019)"},{"key":"5_CR26","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":"5_CR27","unstructured":"Miyato, T., Dai, A.M., Goodfellow, I.: Adversarial training methods for semi-supervised text classification. In: ICLR (2017)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Qi, Y., et al.: REVERIE: remote embodied visual referring expression in real indoor environments. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01000"},{"issue":"1","key":"5_CR30","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1037\/0033-2909.121.1.133","volume":"121","author":"NJ Roese","year":"1997","unstructured":"Roese, N.J.: Counterfactual thinking. Psychol. Bull. 121(1), 133\u2013148 (1997)","journal-title":"Psychol. Bull."},{"key":"5_CR31","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: NeurIPS (2000)"},{"key":"5_CR32","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":"5_CR33","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":"5_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Jain, V., Ie, E., Wang, W., Kozareva, Z., Ravi, S.: Environment-agnostic multitask learning for natural language grounded navigation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58586-0_25"},{"key":"5_CR35","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\u2014ECCV 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.) Computer Vision\u2014ECCV 2018. Lecture Notes in Computer Science, vol. 11220, pp. 38\u201355. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_3"},{"key":"5_CR36","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Y., Bamman, D., Russell, S.: Adversarial training for relation extraction. In: EMNLP (2017)","DOI":"10.18653\/v1\/D17-1187"},{"key":"5_CR38","unstructured":"Zhang, R., Che, T., Ghahramani, Z., Bengio, Y., Song, Y.: MetaGAN: an adversarial approach to few-shot learning. In: NeurIPS (2018)"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Zmigrod, R., Mielke, S.J., Wallach, H., Cotterell, R.: Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1161"}],"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\/978-3-030-58539-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:05:20Z","timestamp":1730851520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58539-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585389","9783030585396"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58539-6_5","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)"}}]}}