{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T17:45:13Z","timestamp":1769622313886,"version":"3.49.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62473295"],"award-info":[{"award-number":["62473295"]}],"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":["62233013"],"award-info":[{"award-number":["62233013"]}],"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":["624B2105"],"award-info":[{"award-number":["624B2105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcsvt.2025.3596386","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:02:03Z","timestamp":1754503323000},"page":"913-929","source":"Crossref","is-referenced-by-count":0,"title":["NavComposer: Composing Language Instructions for Navigation Trajectories Through Action-Scene-Object Modularization"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2166-4450","authenticated-orcid":false,"given":"Zongtao","family":"He","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1368-0300","authenticated-orcid":false,"given":"Liuyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2257-6814","authenticated-orcid":false,"given":"Lu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7543-0855","authenticated-orcid":false,"given":"Chengju","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5644-1188","authenticated-orcid":false,"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref2","first-page":"80","article-title":"Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation","volume-title":"Proc. Conf. Robot Learn.","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2025.3574943"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01374-3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01106"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref12","article-title":"NaVid: Video-based VLM plans the next step for vision-and-language navigation","author":"Zhang","year":"Jul. 2024","journal-title":"Robot. Sci. Syst."},{"key":"ref13","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fried"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref15","first-page":"1","article-title":"Visual landmark selection for generating grounded and interpretable navigation instructions","volume-title":"Proc. CVPR workshop","volume":"3","author":"Agarwal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092686"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2021.3058314"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233554"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.splurobonlp-1.5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/164"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01248"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-024-01339-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802484"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107487"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00764"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103671"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3522295"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00727"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177320"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3399933"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref44","article-title":"InternVideo2.5: Empowering video MLLMs with long and rich context modeling","author":"Wang","year":"2025","journal-title":"arXiv:2501.12386"},{"key":"ref45","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref51","first-page":"331","article-title":"Fast approximate nearest neighbors with automatic algorithm configuration","volume-title":"VISAPP (1)","author":"Muja","year":"2009"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00088"},{"key":"ref53","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref55","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1080\/09296171003643098"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00536"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210080"},{"key":"ref61","article-title":"Standardizing the measurement of text diversity: A tool and a comparative analysis of scores","author":"Shaib","year":"2024","journal-title":"arXiv:2403.00553"},{"key":"ref62","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref65","volume-title":"LLaVA -Next: Improved Reasoning, OCR, and World Knowledge","author":"Liu","year":"2024"},{"key":"ref66","volume-title":"GPT-4O Mini: Advancing Cost-Efficient Intelligence","year":"2025"},{"key":"ref67","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref68","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv:2408.00118"},{"key":"ref69","article-title":"Qwen2.5 technical report","volume-title":"arXiv:2412.15115","author":"Yang","year":"2024"},{"key":"ref70","article-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04101"},{"key":"ref72","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"Aug. 2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref74","volume-title":"LLaVA -Next: A Strong Zero-Shot Video Understanding Model","author":"Zhang","year":"2024"},{"key":"ref75","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ramakrishnan"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.292"},{"key":"ref77","article-title":"GRUtopia: Dream general robots in a city at scale","author":"Wang","year":"2024","journal-title":"arXiv:2407.10943"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.41"},{"key":"ref81","article-title":"DIODE: A dense indoor and outdoor DEpth dataset","author":"Vasiljevic","year":"2019","journal-title":"arXiv:1908.00463"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11365019\/11115085.pdf?arnumber=11115085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T05:07:44Z","timestamp":1769576864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11115085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":84,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3596386","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}