{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:03:01Z","timestamp":1777654981820,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Guangdong Provincial Key Laboratory of Information Security Technology","award":["2023B1212060026"],"award-info":[{"award-number":["2023B1212060026"]}]},{"name":"Guangdong NSF Project","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]},{"name":"Guangzhou Basic and Applied Basic Research Scheme","award":["2024A04J4067"],"award-info":[{"award-number":["2024A04J4067"]}]},{"name":"NSFC","award":["62206315"],"award-info":[{"award-number":["62206315"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681518","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"4073-4081","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Loc4Plan: Locating Before Planning for Outdoor Vision and Language Navigation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2154-4829","authenticated-orcid":false,"given":"Huilin","family":"Tian","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9131-5808","authenticated-orcid":false,"given":"Jingke","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University & Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, & Guangdong Provincial Key Laboratory of Information Security Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5914-5605","authenticated-orcid":false,"given":"Yuan-Ming","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6531-0070","authenticated-orcid":false,"given":"Junkai","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2228-0395","authenticated-orcid":false,"given":"Yunong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00115"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"e_1_3_2_1_6_1","unstructured":"Shizhe Chen Pierre-Louis Guhur Cordelia Schmid and Ivan Laptev. 2021. History aware multimodal transformer for vision-and-language navigation. In Advances in Neural Information Processing Systems (NeurIPS). 5834--5847."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"e_1_3_2_1_8_1","unstructured":"Daniel Fried Ronghang Hu Volkan Cirik Anna Rohrbach Jacob Andreas Louis-Philippe Morency Taylor Berg-Kirkpatrick Kate Saenko Dan Klein and Trevor Darrell. 2018. Speaker-follower models for vision-and-language navigation. In Advances in Neural Information Processing Systems (NeurIPS). 3318--3329."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/11550907_126"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"e_1_3_2_1_11_1","volume-title":"Long short-term memory. Neural Computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural Computation (1997), 1735--1780."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.271"},{"key":"e_1_3_2_1_13_1","volume-title":"Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation","author":"Hu Ronghang","unstructured":"Ronghang Hu, Daniel Fried, Anna Rohrbach, Dan Klein, Trevor Darrell, and Kate Saenko. 2019. Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation. In Association for Computational Linguistics (ACL). 6551--6557."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5220\/0010797400003116"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29813"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV). 274--290","author":"Lin Yan-Bo","year":"2020","unstructured":"Yan-Bo Lin and Yu-Chiang Frank Wang. 2020. Audiovisual transformer with instance attention for audio-visual event localization. In Proceedings of the Asian Conference on Computer Vision (ACCV). 274--290."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"e_1_3_2_1_20_1","volume-title":"Keith Anderson, Denis Teplyashin, Karen Simonyan, Andrew Zisserman, Raia Hadsell, et al.","author":"Mirowski Piotr","year":"2018","unstructured":"Piotr Mirowski, Matt Grimes, Mateusz Malinowski, Karl Moritz Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, Andrew Zisserman, Raia Hadsell, et al. 2018. Learning to navigate in cities without a map. In Advances in Neural Information Processing Systems (NeurIPS). 2424--2435."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 15418--15427","author":"Qiao Yanyuan","year":"2022","unstructured":"Yanyuan Qiao, Yuankai Qi, Yicong Hong, Zheng Yu, Peng Wang, and Qi Wu. 2022. Hop: History-and-order aware pre-training for vision-and-language navigation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 15418--15427."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00212"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International Journal of Computer Vision (IJCV) (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.41"},{"key":"e_1_3_2_1_25_1","volume-title":"Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas","author":"Schumann Raphael","unstructured":"Raphael Schumann and Stefan Riezler. 2022. Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas. In Association for Computational Linguistics (ACL). 7519--7532."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00999"},{"key":"e_1_3_2_1_27_1","volume-title":"Embodied bert: A transformer model for embodied, language-guided visual task completion. arXiv preprint arXiv:2108.04927","author":"Suglia Alessandro","year":"2021","unstructured":"Alessandro Suglia, Qiaozi Gao, Jesse Thomason, Govind Thattai, and Gaurav Sukhatme. 2021. Embodied bert: A transformer model for embodied, language-guided visual task completion. arXiv preprint arXiv:2108.04927 (2021)."},{"key":"e_1_3_2_1_28_1","volume-title":"Outdoor Vision-and-Language Navigation Needs Object-Level Alignment. Sensors","author":"Sun Yanjun","year":"2023","unstructured":"Yanjun Sun, Yue Qiu, Yoshimitsu Aoki, and Hirokatsu Kataoka. 2023. Outdoor Vision-and-Language Navigation Needs Object-Level Alignment. Sensors (2023), 6028."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"e_1_3_2_1_30_1","volume-title":"J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov.","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal transformer for unaligned multimodal language sequences. In Association for Computational Linguistics (ACL). 6558--6569."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01374-3"},{"key":"e_1_3_2_1_33_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS). 5998--6008."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"e_1_3_2_1_37_1","volume-title":"Xin Eric Wang, and William Yang Wang","author":"Xiang Jiannan","year":"2020","unstructured":"Jiannan Xiang, Xin Eric Wang, and William Yang Wang. 2020. Learning to stop: A simple yet effective approach to urban vision-language navigation. arXiv preprint arXiv:2009.13112 (2020)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"e_1_3_2_1_39_1","volume-title":"Babywalk: Going farther in vision-and-language navigation by taking baby steps. arXiv preprint arXiv:2005.04625","author":"Zhu Wang","year":"2020","unstructured":"Wang Zhu, Hexiang Hu, Jiacheng Chen, Zhiwei Deng, Vihan Jain, Eugene Ie, and Fei Sha. 2020. Babywalk: Going farther in vision-and-language navigation by taking baby steps. arXiv preprint arXiv:2005.04625 (2020)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.103"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681518","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681518"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":40,"alternative-id":["10.1145\/3664647.3681518","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681518","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}