{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:13:23Z","timestamp":1775578403115,"version":"3.50.1"},"reference-count":90,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.01103","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"11975-11986","source":"Crossref","is-referenced-by-count":49,"title":["Scaling Data Generation in Vision-and-Language Navigation"],"prefix":"10.1109","author":[{"given":"Zun","family":"Wang","sequence":"first","affiliation":[{"name":"The Australian National University"}]},{"given":"Jialu","family":"Li","sequence":"additional","affiliation":[{"name":"UNC,Chapel Hill"}]},{"given":"Yicong","family":"Hong","sequence":"additional","affiliation":[{"name":"The Australian National University"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,OpenGVLab"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Adelaide"}]},{"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[{"name":"UNC,Chapel Hill"}]},{"given":"Stephen","family":"Gould","sequence":"additional","affiliation":[{"name":"The Australian National University"}]},{"given":"Hao","family":"Tan","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,OpenGVLab"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Are We Making Real Progress in Simulated Environments? Measuring the Sim2Real Gap in Embodied Visual Navigation","author":"Kadian","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref3","article-title":"Bevbert: Topo-metric map pre-training for language-guided navigation","author":"An","year":"2022"},{"key":"ref4","article-title":"Etpnav: Evolving topological planning for vision-language navigation in continuous environments","author":"An","year":"2023"},{"key":"ref5","article-title":"1st place solutions for rxr-habitat vision-and-language navigation competition (cvpr 2022)","author":"An","year":"2022"},{"key":"ref6","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref7","article-title":"Chasing ghosts: Instruction following as bayesian state tracking","volume":"32","author":"Anderson","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"671","article-title":"Simto-real transfer for vision-and-language navigation","volume-title":"Conference on Robot Learning","author":"Anderson"},{"key":"ref9","first-page":"671","article-title":"Simto-real transfer for vision-and-language navigation","volume-title":"Conference on Robot Learning","author":"Anderson"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref11","article-title":"Rearrangement: A challenge for embodied ai","author":"Batra","year":"2020"},{"key":"ref12","article-title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","author":"Batra","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01501"},{"key":"ref15","article-title":"Weakly-supervised multi-granularity map learning for vision-and-language navigation","author":"Chen","year":"2022"},{"key":"ref16","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_37"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref19","article-title":"Talk the walk: Navigating new york city through grounded dialogue","author":"De Vries","year":"2018"},{"key":"ref20","article-title":"Procthor: Large-scale embodied ai using procedural generation","author":"Deitke","year":"2022"},{"key":"ref21","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume":"33","author":"Deng","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.322"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00447"},{"key":"ref25","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Advances in Neural Information Processing Systems","author":"Fried"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref29","article-title":"Language and visual entity relationship graph for agent navigation","volume":"33","author":"Hong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00284"},{"key":"ref33","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","author":"Ilharco","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.293"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01041"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.518"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25199"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01433"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref46","article-title":"Professor forcing: A new algorithm for training recurrent networks","volume":"29","author":"Lamb","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_22"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref51","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Ma"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092686"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981090"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01498"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref62","article-title":"Explore the potential performance of vision-and-language navigation model: a snapshot ensemble method","author":"Qin","year":"2021"},{"key":"ref63","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"issue":"8","key":"ref64","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref65","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Ramakrishnan"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref68","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to noregret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Ross"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref70","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","author":"Shah","year":"2022"},{"key":"ref71","article-title":"How much can clip benefit vision-and-language tasks?","volume-title":"International Conference on Learning Representations","author":"Shen"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref73","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_19"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_25"},{"key":"ref79","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2021.3058314"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183287"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/124"},{"key":"ref84","article-title":"Large scale image completion via co-modulated generative adversarial networks","author":"Zhao","year":"2021"},{"key":"ref85","article-title":"Large scale image completion via co-modulated generative adversarial networks","author":"Zhao","year":"2021"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref87","article-title":"Navgpt: Explicit reasoning in vision-and-language navigation with large language models","author":"Zhou","year":"2023"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00162"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Paris, France","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10378395.pdf?arnumber=10378395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:41:36Z","timestamp":1705542096000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/10378395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":90,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1109\/iccv51070.2023.01103","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}