{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T19:40:14Z","timestamp":1783021214306,"version":"3.54.6"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045546","type":"print"},{"value":"9783032045553","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04555-3_14","type":"book-chapter","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T08:55:56Z","timestamp":1757580956000},"page":"166-178","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Process Adaptive Learning for\u00a0Visual-Language Navigation"],"prefix":"10.1007","author":[{"given":"Chaoqi","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"14_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":"14_CR2","doi-asserted-by":"crossref","unstructured":"Wang, L., He, Z., Dang, R., Shen, M., Liu, C., Chen, Q.: Vision-and-language navigation via causal learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13139\u201313150 (2024)","DOI":"10.1109\/CVPR52733.2024.01248"},{"key":"14_CR3","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":"14_CR4","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":"14_CR5","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"14_CR6","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":"14_CR7","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6629\u20136638 (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Yu, L., Chen, X., Gkioxari, G., Bansal, M., Berg, T.L., Batra, D.: Multi-target embodied question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6309\u20136318 (2019)","DOI":"10.1109\/CVPR.2019.00647"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3d: learning from rgb-d data in indoor environments, arXiv preprint arXiv:1709.06158 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers, arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"issue":"7","key":"14_CR11","first-page":"8524","volume":"45","author":"Y Qiao","year":"2023","unstructured":"Qiao, Y., Qi, Y., Hong, Y., Yu, Z., Wang, P., Wu, Q.: Hop+: history-enhanced and order-aware pre-training for vision-and-language navigation. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8524\u20138537 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Cui, Y., et al.: Grounded entity-landmark adaptive pre-training for vision-and-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12043\u201312053 (2023)","DOI":"10.1109\/ICCV51070.2023.01106"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, X., Yang, J., Liu, Y., Jiang, S.: Gridmm: grid memory map for vision-and-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15625\u201315636 (2023)","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"14_CR14","first-page":"20660","volume":"33","author":"Z Deng","year":"2020","unstructured":"Deng, Z., Narasimhan, K., Russakovsky, O.: Evolving graphical planner: contextual global planning for vision-and-language navigation. Adv. Neural. Inf. Process. Syst. 33, 20660\u201320672 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Tan, H., Bansal, M.: Envedit: environment editing for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15407\u201315417 (2022)","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Du, M., et al.: DELAN: dual-level alignment for vision-and-language navigation by cross-modal contrastive learning, arXiv preprint arXiv:2404.01994 (2024)","DOI":"10.63317\/52b9qg8h9pwv"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Liu, R., Wang, X., Wang, W., Yang, Y.: Bird\u2019s-eye-view scene graph for vision-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10968\u201310980 (2023)","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"14_CR18","unstructured":"An, D., et al.: Bevbert: multimodal map pre-training for language-guided navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2737\u20132748 (2023)"},{"key":"14_CR19","unstructured":"Devlin, J.: Bert: pre-training of deep bidirectional transformers for language understanding, arXiv preprint arXiv:1810.04805 (2018)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, Y., Chen, Z., Liang, X., Liu, J., Liang, X.: Adapt: vision-language navigation with modality-aligned action prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15396\u201315406 (2022)","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: A dual semantic-aware recurrent global-adaptive network for vision-and-language navigation, arXiv preprint arXiv:2305.03602 (2023)","DOI":"10.24963\/ijcai.2023\/164"},{"key":"14_CR22","unstructured":"Liu, Y.: Roberta: a robustly optimized bert pretraining approach, arXiv preprint arXiv:1907.11692, vol. 364 (2019)"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Dou, Z.-Y., et al.: An empirical study of training end-to-end vision-and-language transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18166\u201318176 (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"14_CR24","first-page":"5834","volume":"34","author":"S Chen","year":"2021","unstructured":"Chen, S., Guhur, P.-L., Schmid, C., Laptev, I.: History aware multimodal transformer for vision-and-language navigation. Adv. Neural. Inf. Process. Syst. 34, 5834\u20135847 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Lin, K., Chen, P., Huang, D., Li, T.H., Tan, M., Gan, C.: Learning vision-and-language navigation from youtube videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8317\u20138326 (2023)","DOI":"10.1109\/ICCV51070.2023.00764"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04555-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T18:45:23Z","timestamp":1783017923000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04555-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"ISBN":["9783032045546","9783032045553"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04555-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"12 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}