{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T02:55:25Z","timestamp":1782788125718,"version":"3.54.5"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-20074-8_18","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"312-328","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["A Dataset for\u00a0Interactive Vision-Language Navigation with\u00a0Unknown Command Feasibility"],"prefix":"10.1007","author":[{"given":"Andrea","family":"Burns","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deniz","family":"Arsan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjna","family":"Agrawal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranjitha","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan A.","family":"Plummer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, T., Hoyle, R., Connelly, K., Crandall, D., Kapadia, A.: Privacy concerns and behaviors of people with visual impairments. In: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, CHI 2015, pp. 3523\u20133532. Association for Computing Machinery, New York (2015). https:\/\/doi.org\/10.1145\/2702123.2702334","DOI":"10.1145\/2702123.2702334"},{"key":"18_CR2","unstructured":"Akter, T., Dosono, B., Ahmed, T., Kapadia, A., Semaan, B.C.: \u201cI am uncomfortable sharing what I can\u2019t see\u201d: privacy concerns of the visually impaired with camera based assistive applications. In: USENIX Security Symposium (2020)"},{"key":"18_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 (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"18_CR5","unstructured":"Blukis, V., Paxton, C., Fox, D., Garg, A., Artzi, Y.: A persistent spatial semantic representation for high-level natural language instruction execution (2021)"},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"18_CR7","unstructured":"Conneau, A., Lample, G., Ranzato, M., Denoyer, L., J\u00e9gou, H.: Word translation without parallel data. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"18_CR8","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 (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00008"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Deka, B., et al.: Rico: a mobile app dataset for building data-driven design applications. In: 30th Annual Symposium on User Interface Software and Technology (UIST) (2017)","DOI":"10.1145\/3126594.3126651"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Deka, B., Huang, Z., Kumar, R.: Erica: Interaction mining mobile apps. In: 29th Annual Symposium on User Interface Software and Technology (UIST) (2016)","DOI":"10.1145\/2984511.2984581"},{"key":"18_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 x 16 words: transformers for image recognition at scale (2021)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Gardner, R., Varma, M., Zhu, C., Krishna, R.: Determining question-answer plausibility in crowdsourced datasets using multi-task learning. In: W-NUT@EMNLP (2020)","DOI":"10.18653\/v1\/2020.wnut-1.4"},{"key":"18_CR13","doi-asserted-by":"publisher","unstructured":"Gordon, D., Kembhavi, A., Rastegari, M., Redmon, J., Fox, D., Farhadi, A.: IQA: visual question answering in interactive environments. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4089\u20134098 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00430","DOI":"10.1109\/CVPR.2018.00430"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR16","doi-asserted-by":"publisher","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Irshad, M.Z., Ma, C.Y., Kira, Z.: Hierarchical cross-modal agent for robotics vision-and-language navigation. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (2021). https:\/\/arxiv.org\/abs\/2104.10674","DOI":"10.1109\/ICRA48506.2021.9561806"},{"key":"18_CR18","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision (2021)"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Ku, A., Anderson, P., Patel, R., Ie, E., Baldridge, J.: Room-across-room: Multilingual vision-and-language navigation with dense spatiotemporal grounding. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4392\u20134412. Association for Computational Linguistics, November 2020. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.356, https:\/\/aclanthology.org\/2020.emnlp-main.356","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Selfdoc: self-supervised document representation learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Li, T.J.J., Azaria, A., Myers, B.A.: Sugilite: creating multimodal smartphone automation by demonstration. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, CHI 2017, pp. 6038\u20136049. Association for Computing Machinery, New York (2017)","DOI":"10.1145\/3025453.3025483"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Li, T.J.J., Chen, J., Xia, H., Mitchell, T.M., Myers, B.A.: Multi-modal repairs of conversational breakdowns in task-oriented dialogs, pp. 1094\u20131107. Association for Computing Machinery, New York (2020)","DOI":"10.1145\/3379337.3415820"},{"key":"18_CR23","series-title":"Human\u2013Computer Interaction Series","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/978-3-030-82681-9_15","volume-title":"Artificial Intelligence for Human Computer Interaction: A Modern Approach","author":"TJ-J Li","year":"2021","unstructured":"Li, T.J.-J., Mitchell, T.M., Myers, B.A.: Demonstration + natural language: multimodal interfaces for GUI-based interactive task learning agents. In: Li, Y., Hilliges, O. (eds.) Artificial Intelligence for Human Computer Interaction: A Modern Approach. HIS, pp. 495\u2013537. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-82681-9_15"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Li, T.J.J., Popowski, L., Mitchell, T.M., Myers, B.A.: Screen2vec: semantic embedding of GUI screens and GUI components. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, CHI 2021 (2021)","DOI":"10.1145\/3411764.3445049"},{"key":"18_CR25","doi-asserted-by":"publisher","unstructured":"Li, Y., He, J., Zhou, X., Zhang, Y., Baldridge, J.: Mapping natural language instructions to mobile UI action sequences. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8198\u20138210. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.729, https:\/\/www.aclweb.org\/anthology\/2020.acl-main.729","DOI":"10.18653\/v1\/2020.acl-main.729"},{"key":"18_CR26","unstructured":"Li, Y., Li, G., Zhou, X., Dehghani, M., Gritsenko, A.A.: VUT: versatile UI transformer for multi-modal multi-task user interface modeling. CoRR abs\/2112.05692 (2021). https:\/\/arxiv.org\/abs\/2112.05692"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Liu, T.F., Craft, M., Situ, J., Yumer, E., Mech, R., Kumar, R.: Learning design semantics for mobile apps. In: 31st Annual Symposium on User Interface Software and Technology (UIST) (2018)","DOI":"10.1145\/3242587.3242650"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Lloyd, S.: Least squares quantization in PCM. In: IEEE Transactions on Information Theory (1982)","DOI":"10.1109\/TIT.1982.1056489"},{"key":"18_CR29","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008). http:\/\/www.jmlr.org\/papers\/v9\/vandermaaten08a.html"},{"key":"18_CR30","unstructured":"Massiceti, D., Dokania, P.K., Siddharth, N., Torr, P.H.S.: Visual dialogue without vision or dialogue. CoRR abs\/1812.06417 (2018). http:\/\/arxiv.org\/abs\/1812.06417"},{"key":"18_CR31","unstructured":"Min, S.Y., Chaplot, D.S., Ravikumar, P., Bisk, Y., Salakhutdinov, R.: Film: following instructions in language with modular methods (2021)"},{"key":"18_CR32","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. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2019","DOI":"10.18653\/v1\/D19-1063"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Pasupat, P., Jiang, T.S., Liu, E.Z., Guu, K., Liang, P.: Mapping natural language commands to web elements. In: Empirical Methods in Natural Language Processing (EMNLP) (2018)","DOI":"10.18653\/v1\/D18-1540"},{"key":"18_CR34","doi-asserted-by":"publisher","unstructured":"Puig, X., et al.: Virtualhome: simulating household activities via programs. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8494\u20138502. IEEE Computer Society, Los Alamitos, CA, USA, June 2018. https:\/\/doi.org\/10.1109\/CVPR.2018.00886, https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR.2018.00886","DOI":"10.1109\/CVPR.2018.00886"},{"key":"18_CR35","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. CoRR abs\/2103.00020 (2021). https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Ray, A., Christie, G., Bansal, M., Batra, D., Parikh, D.: Question relevance in VQQ: identifying non-visual and false-premise questions (2016)","DOI":"10.18653\/v1\/D16-1090"},{"key":"18_CR37","unstructured":"Shi, T., Karpathy, A., Fan, L., Hernandez, J., Liang, P.: World of bits: An open-domain platform for web-based agents. In: 34th International Conference on Machine Learning (ICML) (2015)"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Shridhar, M., et al.: ALFRED: a benchmark for interpreting grounded instructions for everyday tasks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https:\/\/arxiv.org\/abs\/1912.01734","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"18_CR39","unstructured":"Singh, K.P., Bhambri, S., Kim, B., Mottaghi, R., Choi, J.: Factorizing perception and policy for interactive instruction following. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. CoRR abs\/1707.02968 (2017). http:\/\/arxiv.org\/abs\/1707.02968","DOI":"10.1109\/ICCV.2017.97"},{"key":"18_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Vtyurina, A., Fourney, A., Morris, M.R., Findlater, L., White, R.W.: Bridging screen readers and voice assistants for enhanced eyes-free web search. In: International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) (2019)","DOI":"10.1145\/3308558.3314136"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Yamaguchi, K.: Canvasvae: learning to generate vector graphic documents. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00543"},{"key":"18_CR44","doi-asserted-by":"publisher","unstructured":"Zhu, F., Zhu, Y., Chang, X., Liang, X.: Vision-language navigation with self-supervised auxiliary reasoning tasks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10009\u201310019 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01003","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Visual semantic planning using deep successor representations. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.60"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20074-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:26:52Z","timestamp":1668198412000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"12 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}