{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:22:43Z","timestamp":1778257363273,"version":"3.51.4"},"reference-count":85,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62376199,62206170,6243000159,62102416"],"award-info":[{"award-number":["62376199,62206170,6243000159,62102416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00523","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5511-5522","source":"Crossref","is-referenced-by-count":1,"title":["COSMO: Combination of Selective Memorization for Low-Cost Vision-and-Language Navigation"],"prefix":"10.1109","author":[{"given":"Siqi","family":"Zhang","sequence":"first","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyuan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Ecole polytechnique fédérale de Lausanne"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qunbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zike","family":"Yan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihua","family":"Wei","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2737","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","volume-title":"In Int. Conf. Comput. Vis.","author":"An","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_34"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01501"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2764"},{"key":"ref8","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","author":"Chen","year":"2021","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_37"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01106"},{"key":"ref12","first-page":"1004110071","article-title":"Transformers are ssms: generalized models and efficient algorithms through structured state space duality","volume-title":"In Int. Conf. Mach. Learn.","author":"Dao","year":"2024"},{"key":"ref13","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16 x16 words: Transformers for image recognition at scale"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref15","first-page":"33183329","article-title":"Speaker-follower models for vision-and-language navigation","author":"Fried","year":"2018","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref16","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"In Int. Conf. Learn. Represent.","author":"Fu","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01432"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref20","author":"Gu","year":"2023","journal-title":"Mamba: Linear-time sequence modeling with selective state spaces"},{"key":"ref21","first-page":"14741487","article-title":"Hippo: Recurrent memory with optimal polynomial projections","volume":"33","author":"Gu","year":"2020","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref22","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"In Int. Conf. Learn. Represent.","author":"Gu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2607"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1670"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref28","article-title":"Liquid structural state-space models","volume-title":"In Int. Conf. Learn. Represent.","author":"Hasani","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00284"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02223"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icpr56361.2022.9956561"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01447"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01488"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25223"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref44","author":"Li","year":"2024","journal-title":"Mambadfuse: A mamba-based dual-phase model for multi-modality image fusion"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25243"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01544"},{"key":"ref49","author":"Liu","year":"2024","journal-title":"Vmamba: Visual state space model"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2307\/jj.36032637.26"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref52","article-title":"Long range language modeling via gated state spaces","volume-title":"In Int. Conf. Learn. Represent.","author":"Mehta","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28223"},{"key":"ref54","article-title":"Graspmamba: A mamba-based languagedriven grasp detection framework with hierarchical feature learning","volume":"abs\/2409.14403","author":"Hoang Nguyen","year":"2024","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3496073"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01416"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_27"},{"key":"ref61","author":"Qiao","year":"2024","journal-title":"Vl-mamba: Exploring state space models for multimodal learning"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3767748"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref64","article-title":"Simplified state space layers for sequence modeling","volume-title":"In Int. Conf. Learn. Represent.","author":"Smith","year":"2022"},{"key":"ref65","article-title":"Simplified state space layers for sequence modeling","volume-title":"In Int. Conf. Learn. Represent.","author":"Smith","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref67","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref69","author":"Waleffe","year":"2024","journal-title":"An empirical study of mamba-based language models"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00998"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01248"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01305"},{"key":"ref76","author":"Wang","year":"2024","journal-title":"Mamba-unet: Unet-like pure visual mamba for medical image segmentation"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"ref79","first-page":"2005520080","article-title":"Mambatalk: Efficient holistic gesture synthesis with selective state space models","volume-title":"Adv. Neural Inform. Process. Syst.","volume":"37","author":"Xu","year":"2025"},{"key":"ref80","author":"Zhang","year":"2024","journal-title":"Vision-and-language navigation today and tomorrow: A survey in the era of foundation models"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref85","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"In Int. Conf. Mach. Learn.","author":"Zhu"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444018.pdf?arnumber=11444018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:25:04Z","timestamp":1777613104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00523","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}