{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:23:03Z","timestamp":1778257383263,"version":"3.51.4"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728471","type":"print"},{"value":"9783031728488","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72848-8_5","type":"book-chapter","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T13:38:09Z","timestamp":1732801089000},"page":"72-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["PRET: Planning with\u00a0Directed Fidelity Trajectory for\u00a0Vision and\u00a0Language Navigation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7808-3497","authenticated-orcid":false,"given":"Renjie","family":"Lu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5437-3070","authenticated-orcid":false,"given":"Jingke","family":"Meng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"An, D., Qi, Y., Huang, Y., Wu, Q., Wang, L., Tan, T.: Neighbor-view enhanced model for vision and language navigation. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475282"},{"key":"5_CR2","unstructured":"An, D., et al.: BEVBert: multimodal map pre-training for language-guided navigation. In: ICCV (2023)"},{"key":"5_CR3","unstructured":"Anderson, P., et al.: On evaluation of embodied navigation agents. CoRR (2018)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., Wu, Q., 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_CR5","unstructured":"Chaplot, D.S., Gandhi, D., Gupta, A., Salakhutdinov, R.: Object goal navigation using goal-oriented semantic exploration. In: NeurIPS (2020)"},{"key":"5_CR6","unstructured":"Chaplot, D.S., Gandhi, D., Gupta, S., Gupta, A., Salakhutdinov, R.: Learning to explore using active neural SLAM. In: ICLR (2020)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Guhur, P.L., Schmid, C., Laptev, I.: History aware multimodal transformer for vision-and-language navigation. In: NeurIPS (2021)","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S., Guhur, P., Tapaswi, M., Schmid, C., Laptev, I.: Think global, act local: dual-scale graph transformer for vision-and-language navigation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"5_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., Li, L., Yu, L., El Kholy, A., Ahmed, F., Gan, Z., Cheng, Yu., Liu, J.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"5_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"5_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Dou, Z., Gao, F., Peng, N.: Masked path modeling for vision-and-language navigation. CoRR (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.1019"},{"key":"5_CR14","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: NeurIPS (2018)"},{"key":"5_CR15","unstructured":"Fuentes-Pacheco, J., Ascencio, J.R., Rend\u00f3n-Mancha, J.M.: Visual simultaneous localization and mapping: a survey. Artif. Intell. Rev. (2015)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Gao, C., et al.: Adaptive zone-aware hierarchical planner for vision-language navigation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01432"},{"key":"5_CR17","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Hong, Y., Wu, Q., Qi, Y., Rodriguez-Opazo, C., Gould, S.: VLN BERT: a recurrent vision-and-language BERT for navigation. In: CVPR, pp. 1643\u20131653 (2021)","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Huo, J., Sun, Q., Jiang, B., Lin, H., Fu, Y.: GeoVLN: learning geometry-enhanced visual representation with slot attention for vision-and-language navigation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02223"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Hwang, M., Jeong, J., Kim, M., Oh, Y., Oh, S.: Meta-explore: exploratory hierarchical vision-and-language navigation using scene object spectrum grounding. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00646"},{"key":"5_CR21","unstructured":"Ilharco, G., Jain, V., Ku, A., Ie, E., Baldridge, J.: General evaluation for instruction conditioned navigation using dynamic time warping. In: NeurIPS Workshop (2019)"},{"key":"5_CR22","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: ICML (2021)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Ku, A., Anderson, P., Patel, R., Ie, E., Baldridge, J.: Room-across-room: multilingual vision-and-language navigation with dense spatiotemporal grounding. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Li, J., Tan, H., Bansal, M.: EnvEdit: environment editing for vision-and-language navigation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"5_CR25","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: NeurIPS (2021)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Robust navigation with language pretraining and stochastic sampling. In: EMNLP-IJCNLP (2019)","DOI":"10.18653\/v1\/D19-1159"},{"key":"5_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1007\/978-3-031-20059-5_22","volume-title":"Computer Vision \u2013 ECCV 2022","author":"C Lin","year":"2022","unstructured":"Lin, C., Jiang, Y., Cai, J., Qu, L., Haffari, G., Yuan, Z.: Multimodal transformer with variable-length memory for vision-and-language navigation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 380\u2013397. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_22"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Liu, C., Zhu, F., Chang, X., Liang, X., Ge, Z., Shen, Y.: Vision-language navigation with random environmental mixup. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"5_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"5_CR30","unstructured":"Ma, C.Y., et al.: Self-monitoring navigation agent via auxiliary progress estimation. In: ICLR (2019)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Ma, C., 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_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/978-3-030-58539-6_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Majumdar","year":"2020","unstructured":"Majumdar, A., Shrivastava, A., Lee, S., Anderson, P., Parikh, D., Batra, D.: Improving vision-and-language navigation with image-text pairs from the web. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 259\u2013274. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_16"},{"key":"5_CR33","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. CoRR (2023)"},{"key":"5_CR34","unstructured":"Pope, R., et al.: Efficiently scaling transformer inference. CoRR (2022)"},{"key":"5_CR35","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"},{"key":"5_CR36","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1009"},{"key":"5_CR38","unstructured":"Shen, S., et al.: How much can CLIP benefit vision-and-language tasks? In: ICLR (2022)"},{"key":"5_CR39","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_CR40","unstructured":"Thomason, J., Murray, M., Cakmak, M., Zettlemoyer, L.: Vision-and-dialog navigation. In: CoRL (2020)"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Thrun, S.: Learning metric-topological maps for indoor mobile robot navigation. Artif. Intell. (1998)","DOI":"10.1016\/S0004-3702(97)00078-7"},{"key":"5_CR42","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, W., Liang, W., Xiong, C., Shen, J.: Structured scene memory for vision-language navigation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Wang, S., et al.: Less is more: generating grounded navigation instructions from landmarks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"5_CR45","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_CR46","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: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, F., Zhu, Y., Chang, X., Liang, X.: Vision-language navigation with self-supervised auxiliary reasoning tasks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01003"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72848-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T14:03:55Z","timestamp":1732802635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72848-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"ISBN":["9783031728471","9783031728488"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72848-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"assertion":[{"value":"29 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}