{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:11:53Z","timestamp":1775578313524,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225207"],"award-info":[{"award-number":["62225207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276243"],"award-info":[{"award-number":["62276243"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3358112","type":"journal-article","created":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T18:40:49Z","timestamp":1706121649000},"page":"8406-8418","source":"Crossref","is-referenced-by-count":9,"title":["Vision-and-Language Navigation via Latent Semantic Alignment Learning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9752-258X","authenticated-orcid":false,"given":"Siying","family":"Wu","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8036-4071","authenticated-orcid":false,"given":"Xueyang","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-5579","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fried","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref7","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref12","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref15","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548283"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/21.44033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/70.88137"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1995.525695"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/70.938381"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001500"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2913324"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00284"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref28","article-title":"Semi-parametric topological memory for navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Savinov","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref34","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hong","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060948"},{"key":"ref45","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref49","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref50","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref51","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref53","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref54","first-page":"5926","article-title":"Mass: Masked sequence to sequence pre-training for language generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song","year":"2019"},{"issue":"140","key":"ref55","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume-title":"J. Mach. Learn. Res.","volume":"21","author":"Raffel","year":"2020"},{"key":"ref56","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref59","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref60","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. ViGIL Workshop","author":"Ilharco","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10414007.pdf?arnumber=10414007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T07:55:02Z","timestamp":1722585302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10414007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3358112","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}