{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T22:02:01Z","timestamp":1771538521417,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":["U25A20442"],"award-info":[{"award-number":["U25A20442"]}],"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":["62427808"],"award-info":[{"award-number":["62427808"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3652003","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:28Z","timestamp":1769634088000},"page":"1937-1950","source":"Crossref","is-referenced-by-count":0,"title":["ThinkMatter: Panoramic-Aware Instructional Semantics for Monocular Vision-and-Language Navigation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4111-9334","authenticated-orcid":false,"given":"Guangzhao","family":"Dai","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-1646","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7903-581X","authenticated-orcid":false,"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9213-2611","authenticated-orcid":false,"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University (SMU), 81 Victoria Street, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2689-317X","authenticated-orcid":false,"given":"Qianru","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University (SMU), 81 Victoria Street, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00998"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00284"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01305"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref14","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Anderson"},{"key":"ref15","first-page":"38149","article-title":"Weakly-supervised multi-granularity map learning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01447"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref19","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Bao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref22","first-page":"2982","article-title":"Sim-to-real transfer via 3D feature fields for vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref24","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref27","first-page":"2737","article-title":"BEVBert: Multimodal map pre-training for language-guided navigation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"An"},{"key":"ref28","article-title":"UnitedVLN: Generalizable Gaussian splatting for continuous vision-language navigation","author":"Dai","year":"2024","journal-title":"arXiv:2411.16053"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref30","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref31","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref32","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref33","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521658"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246147"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_12"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00807"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967584"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3573524"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3574929"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3560240"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3409052"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16180"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref47","first-page":"1","article-title":"An image is worth $16 \\times 16$\n words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00460"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref51","article-title":"MapNav: A novel memory representation via annotated semantic maps for vision-and-language navigation","author":"Zhang","year":"2025","journal-title":"arXiv:2502.13451"},{"key":"ref52","article-title":"VLN-r1: Vision-language navigation via reinforcement fine-tuning","author":"Qi","year":"2025","journal-title":"arXiv:2506.17221"},{"key":"ref53","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021","journal-title":"arXiv:2109.08238"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref55","first-page":"3866","article-title":"Mobility VLA: Multimodal instruction navigation with long-context VLMs and topological graphs","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Chiang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.013"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3658187"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11367385.pdf?arnumber=11367385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T21:01:15Z","timestamp":1771534875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11367385\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3652003","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}