{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:16:48Z","timestamp":1774124208388,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819981779","type":"print"},{"value":"9789819981786","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8178-6_39","type":"book-chapter","created":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T10:02:54Z","timestamp":1701252174000},"page":"518-529","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sub-Instruction and\u00a0Local Map Relationship Enhanced Model for\u00a0Vision and\u00a0Language Navigation"],"prefix":"10.1007","author":[{"given":"Yong","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yinlin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jihe","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Mo","family":"Tao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"39_CR1","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":"39_CR2","doi-asserted-by":"crossref","unstructured":"Chen, K., Chen, J.K., Chuang, J., V\u00e1zquez, M., Savarese, S.: Topological planning with transformers for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11276\u201311286 (2021)","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Guhur, P.L., Tapaswi, M., Schmid, C., Laptev, I.: Think global, act local: dual-scale graph transformer for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16537\u201316547 (2022)","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"39_CR4","unstructured":"Fried, D., et al.: Speaker-follower models for vision- and-language navigation. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Georgakis, G., et al.: Cross-modal map learning for vision and language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15460\u201315470 (2022)","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Hao, W., Li, C., Li, X., Carin, L., Gao, J.: Towards learning a generic agent for vision-and-language navigation via pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13137\u201313146 (2020)","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"39_CR7","unstructured":"He, Z., Wang, L., Li, S., Yan, Q., Liu, C., Chen, Q.: MLANet: multi-level attention network with sub-instruction for continuous vision-and-language navigation. arXiv preprint arXiv:2303.01396 (2023)"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Hong, Y., Rodriguez, C., Wu, Q., Gould, S.: Sub-instruction aware vision-and-language navigation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3360\u20133376 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.271"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Irshad, M.Z., Mithun, N.C., Seymour, Z., Chiu, H.P., Samarasekera, S., Kumar, R.: Semantically-aware spatio-temporal reasoning agent for vision-and-language navigation in continuous environments. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 4065\u20134071. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956561"},{"key":"39_CR10","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Krantz, J., Gokaslan, A., Batra, D., Lee, S., Maksymets, O.: Waypoint models for instruction-guided navigation in continuous environments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15162\u201315171 (2021)","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"39_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58604-1_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Krantz","year":"2020","unstructured":"Krantz, J., Wijmans, E., Majumdar, A., Batra, D., Lee, S.: Beyond the Nav-Graph: vision-and-language navigation in continuous environments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_7"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"39_CR14","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, W., Liang, W., Xiong, C., Shen, J.: Structured scene memory for vision-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8455\u20138464 (2021)","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"39_CR16","unstructured":"Wijmans, E., et al.: DD-PPO: learning near-perfect pointgoal navigators from 2.5 billion frames. arXiv preprint arXiv:1911.00357 (2019)"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Guo, Q., Kordjamshidi, P.: Towards navigation by reasoning over spatial configurations. In: Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics, pp. 42\u201352 (2021)","DOI":"10.18653\/v1\/2021.splurobonlp-1.5"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Zhu, W., et al.: BabyWalk: going farther in vision-and-language navigation by taking baby steps. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2539\u20132556 (2020)","DOI":"10.18653\/v1\/2020.acl-main.229"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8178-6_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:33:53Z","timestamp":1709829233000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8178-6_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"ISBN":["9789819981779","9789819981786"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8178-6_39","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,30]]},"assertion":[{"value":"30 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}