@article{bb173900,
AUTHOR = "Lin, B.Q. and Nie, Y. and Wei, Z.M. and Zhu, Y. and Xu, H. and Ma, S.K. and Liu, J.Z. and Liang, X.D.",
TITLE = "Correctable Landmark Discovery via Large Models for Vision-Language
Navigation",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "8534-8548",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169573"}
@article{bb173901,
AUTHOR = "Zhan, Z.H. and Qin, J.H. and Zhuo, W. and Tan, G.",
TITLE = "Enhancing Vision and Language Navigation With Prompt-Based Scene
Knowledge",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "10",
MONTH = "October",
PAGES = "9745-9756",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169574"}
@article{bb173902,
AUTHOR = "Zheng, Q. and Liu, D.Q. and Wang, C.Y. and Zhang, J. and Wang, D.D. and Tao, D.C.",
TITLE = "ESceme: Vision-and-Language Navigation with Episodic Scene Memory",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "254-274",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169575"}
@article{bb173903,
AUTHOR = "An, D. and Wang, H.Q. and Wang, W.G. and Wang, Z. and Huang, Y. and He, K. and Wang, L.",
TITLE = "ETPNav: Evolving Topological Planning for Vision-Language Navigation
in Continuous Environments",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "5130-5145",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169576"}
@article{bb173904,
AUTHOR = "Shi, Y.H. and Liu, J.Y. and Sun, L. and Zheng, X.",
TITLE = "E²BA: Environment Exploration and Backtracking Agent for Visual
Language Object Navigation",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "6231-6244",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169577"}
@article{bb173905,
AUTHOR = "Tan, M.K. and Chen, P.H. and Zhi, H.Y. and Mai, J.J. and Rosman, B. and Ji, D.Y. and Zeng, R.",
TITLE = "Source-Free Elastic Model Adaptation for Vision-and-Language
Navigation",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "3953-3965",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169578"}
@article{bb173906,
AUTHOR = "Zhang, S.Q. and Qiao, Y.Y. and Wang, Q. and Guo, L.T. and Wei, Z.H. and Liu, J.",
TITLE = "FlexVLN: Flexible Adaptation for Diverse Vision-and-Language
Navigation Tasks",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "6307-6318",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169579"}
@article{bb173907,
AUTHOR = "Yu, T. and Wu, Y.F. and Cui, Q.J. and Huang, Q.M. and Yu, J.",
TITLE = "MossVLN: Memory-Observation Synergistic System for Continuous
Vision-Language Navigation",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "6690-6704",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169580"}
@article{bb173908,
AUTHOR = "Chen, K. and An, D. and Huang, Y. and Xu, R.T. and Su, Y.F. and Ling, Y.G. and Reid, I. and Wang, L.",
TITLE = "Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous
Environments",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "10441-10456",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169581"}
@article{bb173909,
AUTHOR = "Huang, B. and Zheng, Y.W. and Sui, D.C. and Lan, C. and Zhao, X.P. and Zhang, X. and Meng, J. and Xiao, M.B. and Zou, Y.F. and Yu, D.X.",
TITLE = "Temporal-Spatial Object Relations Modeling for Vision-and-Language
Navigation",
JOURNAL = ITS,
VOLUME = "26",
YEAR = "2025",
NUMBER = "10",
MONTH = "October",
PAGES = "15631-15645",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169582"}
@article{bb173910,
AUTHOR = "Mohammadi, B. and Abbasnejad, E. and Qi, Y.K. and Wu, Q. and van den Hengel, A. and Shi, J.Q.F.",
TITLE = "Parameter-efficient action planning with large language models for
vision-and-language navigation",
JOURNAL = PR,
VOLUME = "172",
YEAR = "2026",
PAGES = "112462",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169583"}
@article{bb173911,
AUTHOR = "Li, L.X. and Fan, J.C. and Ni, X.H. and Qin, S.J. and Li, W.M. and Gao, F.",
TITLE = "SVA: Towards speech-Enabled vision-Language-Action model",
JOURNAL = PR,
VOLUME = "173",
YEAR = "2026",
PAGES = "112915",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169584"}
@inproceedings{bb173912,
AUTHOR = "Zhou, L. and Xue, R. and Luo, X.Y.",
TITLE = "Structured Instruction Parsing and Scene Alignment For UAV
Vision-Language Navigation",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "2600-2605",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169585"}
@inproceedings{bb173913,
AUTHOR = "Srinivasan, T. and Patapati, S.",
TITLE = "PhysNav-DG: A Novel Adaptive Framework for Robust VLM-Sensor Fusion
in Navigation Applications",
BOOKTITLE = DomainFuture25,
YEAR = "2025",
PAGES = "6566-6574",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169586"}
@inproceedings{bb173914,
AUTHOR = "Sohn, T.S. and Dillitzer, M. and Bach, J. and Corso, J.J. and Bruhl, T. and Schwager, R. and Eberhardt, T.D. and Sax, E.",
TITLE = "Drive4C: A Closed-Loop Benchmark on what Foundation Models Really
Need to be Capable of for Language-Guided Autonomous Driving",
BOOKTITLE = DistillDrive24,
YEAR = "2024",
PAGES = "3859-3869",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169587"}
@inproceedings{bb173915,
AUTHOR = "Cusipuma, D. and Ortega, D. and Flores Benites, V. and Deza, A.",
TITLE = "Robusto-1 Dataset: Comparing Humans and VLMs on Real
Out-Of-Distribution Autonomous Driving VQA from Peru",
BOOKTITLE = DistillDrive24,
YEAR = "2024",
PAGES = "3817-3828",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169588"}
@inproceedings{bb173916,
AUTHOR = "Chen, X.S. and Huang, L. and Ma, T. and Fang, R.Y. and Shi, S.S. and Li, H.S.",
TITLE = "SOLVE: Synergy of Language-Vision and End-to-End Networks for
Autonomous Driving",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "12068-12077",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169589"}
@inproceedings{bb173917,
AUTHOR = "Song, X.S. and Chen, W.X. and Liu, Y. and Chen, W.K. and Li, G.B. and Lin, L.",
TITLE = "Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark
and Method",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "12078-12088",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169590"}
@inproceedings{bb173918,
AUTHOR = "Liang, H. and Cao, J.L. and Goel, V. and Qian, G. and Korolev, S. and Terzopoulos, D. and Plataniotis, K.N. and Tulyakov, S. and Ren, J.",
TITLE = "Wonderland: Navigating 3D Scenes From a Single Image",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "798-810",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169591"}
@inproceedings{bb173919,
AUTHOR = "Perincherry, A. and Krantz, J. and Lee, S.",
TITLE = "Do Visual Imaginations Improve Vision-and-Language Navigation Agents?",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3846-3855",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169592"}
@inproceedings{bb173920,
AUTHOR = "Han, M.F. and Ma, L. and Zhumakhanova, K. and Radionova, E. and Zhang, J.Y. and Chang, X.J. and Liang, X.D. and Laptev, I.",
TITLE = "RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied
Navigation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "27586-27596",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169593"}
@inproceedings{bb173921,
AUTHOR = "Abraham, S.S. and Garg, S. and Dayoub, F.",
TITLE = "To Ask or Not to Ask? Detecting Absence of Information in Vision and
Language Navigation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "7480-7489",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169594"}
@inproceedings{bb173922,
AUTHOR = "Yang, Z.J. and Shi, X.X. and Slyman, E. and Lee, S.",
TITLE = "Hijacking Vision-and-Language Navigation Agents with Adversarial
Environmental Attacks",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6094-6103",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169595"}
@inproceedings{bb173923,
AUTHOR = "Ma, Y.Z. and Cao, Y.L. and Sun, J.C. and Pavone, M. and Xiao, C.W.",
TITLE = "Dolphins: Multimodal Language Model for Driving",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLV: 403-420",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169596"}
@inproceedings{bb173924,
AUTHOR = "Lu, R.J. and Meng, J. and Zheng, W.S.",
TITLE = "PRET: Planning with Directed Fidelity Trajectory for Vision and
Language Navigation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXVI: 72-88",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169597"}
@inproceedings{bb173925,
AUTHOR = "Qu, T.Y. and Tuytelaars, T. and Moens, M.F.",
TITLE = "Introducing Routing Functions to Vision-language Parameter-efficient
Fine-tuning with Low-rank Bottlenecks",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXVIII: 291-308",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169598"}
@inproceedings{bb173926,
AUTHOR = "Ding, P.X. and Zhao, H. and Zhang, W.J. and Song, W.X. and Zhang, M. and Huang, S. and Yang, N.X. and Wang, D.L.",
TITLE = "QUAR-VLA: Vision-language-action Model for Quadruped Robots",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "V: 352-367",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169599"}
@inproceedings{bb173927,
AUTHOR = "Doughty, H. and Thoker, F.M. and Snoek, C.G.M.",
TITLE = "Locomotion: Learning Motion-focused Video-language Representations",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 3-24",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169600"}
@inproceedings{bb173928,
AUTHOR = "Rawal, N. and Bigazzi, R. and Baraldi, L. and Cucchiara, R.",
TITLE = "AIGeN: An Adversarial Approach for Instruction Generation in VLN",
BOOKTITLE = MULA24,
YEAR = "2024",
PAGES = "2070-2080",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169601"}
@inproceedings{bb173929,
AUTHOR = "Wang, L. and He, Z.T. and Dang, R.H. and Shen, M.J. and Liu, C.J. and Chen, Q.J.",
TITLE = "Vision-and-Language Navigation via Causal Learning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13139-13150",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169602"}
@inproceedings{bb173930,
AUTHOR = "Wang, Z. and Xiang Yang, L. and Yang, J.H. and Liu, Y.Q. and Jun Jie, H. and Jiang, M. and Jiang, S.Q.",
TITLE = "Lookahead Exploration with Neural Radiance Representation for
Continuous Vision-Language Navigation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13753-13762",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169603"}
@inproceedings{bb173931,
AUTHOR = "Liu, R. and Wang, W.G. and Yang, Y.",
TITLE = "Volumetric Environment Representation for Vision-Language Navigation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16317-16328",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169604"}
@inproceedings{bb173932,
AUTHOR = "Krantz, J. and Gervet, T. and Yadav, K. and Wang, A. and Paxton, C. and Mottaghi, R. and Batra, D. and Malik, J. and Lee, S. and Chaplot, D.S.",
TITLE = "Navigating to Objects Specified by Images",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10882-10891",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169605"}
@inproceedings{bb173933,
AUTHOR = "Yang, X. and Li, Z.Z. and Xu, H.Y. and Zhang, H.W. and Ye, Q.H. and Li, C.L. and Yan, M. and Zhang, Y. and Huang, F. and Huang, S.F.",
TITLE = "Learning Trajectory-Word Alignments for Video-Language Tasks",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2504-2514",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169606"}
@inproceedings{bb173934,
AUTHOR = "Lin, K. and Chen, P.H. and Huang, D. and Li, T.H. and Tan, M.K. and Gan, C.",
TITLE = "Learning Vision-and-Language Navigation from YouTube Videos",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "8283-8292",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169607"}
@inproceedings{bb173935,
AUTHOR = "Wang, Z. and Li, J. and Hong, Y.C. and Wang, Y. and Wu, Q. and Bansal, M. and Gould, S. and Tan, H. and Qiao, Y.",
TITLE = "Scaling Data Generation in Vision-and-Language Navigation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "11975-11986",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169608"}
@inproceedings{bb173936,
AUTHOR = "Cui, Y. and Xie, L. and Zhang, Y.K. and Zhang, M. and Yan, Y. and Yin, E.",
TITLE = "Grounded Entity-Landmark Adaptive Pre-training for
Vision-and-Language Navigation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "12009-12019",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169609"}
@inproceedings{bb173937,
AUTHOR = "Patel, D. and Eghbalzadeh, H. and Kamra, N. and Iuzzolino, M.L. and Jain, U. and Desai, R.",
TITLE = "Pretrained Language Models as Visual Planners for Human Assistance",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15256-15268",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169610"}
@inproceedings{bb173938,
AUTHOR = "Liu, S. and Zhang, H.S. and Qi, Y.K. and Wang, P. and Zhang, Y.N. and Wu, Q.",
TITLE = "AerialVLN: Vision-and-Language Navigation for UAVs",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15338-15348",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169611"}
@inproceedings{bb173939,
AUTHOR = "Wang, Z. and Li, X.Y. and Yang, J.H. and Liu, Y.Q. and Jiang, S.Q.",
TITLE = "GridMM: Grid Memory Map for Vision-and-Language Navigation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15579-15590",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169612"}
@inproceedings{bb173940,
AUTHOR = "Wang, H.Q. and Liang, W. and Van Gool, L.J. and Wang, W.G.",
TITLE = "Dreamwalker: Mental Planning for Continuous Vision-Language
Navigation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10839-10849",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169613"}
@inproceedings{bb173941,
AUTHOR = "Qiao, Y.Y. and Yu, Z. and Wu, Q.",
TITLE = "VLN-PETL: Parameter-Efficient Transfer Learning for
Vision-and-Language Navigation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15397-15406",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169614"}
@inproceedings{bb173942,
AUTHOR = "Huo, J.Y. and Sun, Q. and Jiang, B. and Lin, H.T. and Fu, Y.W.",
TITLE = "GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot
Attention for Vision-and-Language Navigation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "23212-23221",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169615"}
@inproceedings{bb173943,
AUTHOR = "Mu, Y. and Yao, S. and Ding, M.Y. and Luo, P. and Gan, C.",
TITLE = "EC2: Emergent Communication for Embodied Control",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6704-6714",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169616"}
@inproceedings{bb173944,
AUTHOR = "Zhang, J.Z. and Dai, L. and Meng, F.P. and Fan, Q.N. and Chen, X.L. and Xu, K. and Wang, H.",
TITLE = "3D-Aware Object Goal Navigation via Simultaneous Exploration and
Identification",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6672-6682",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169617"}
@inproceedings{bb173945,
AUTHOR = "Wang, X.H. and Wang, W.G. and Shao, J.Y. and Yang, Y.",
TITLE = "LANA: A Language-Capable Navigator for Instruction Following and
Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "19048-19058",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169618"}
@inproceedings{bb173946,
AUTHOR = "Krantz, J. and Banerjee, S. and Zhu, W. and Corso, J. and Anderson, P. and Lee, S. and Thomason, J.",
TITLE = "Iterative Vision-and-Language Navigation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14921-14930",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169619"}
@inproceedings{bb173947,
AUTHOR = "Li, X.Y. and Wang, Z. and Yang, J.H. and Wang, Y.W. and Jiang, S.Q.",
TITLE = "KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2583-2592",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169620"}
@inproceedings{bb173948,
AUTHOR = "Yang, Z. and Majumdar, A. and Lee, S.",
TITLE = "Behavioral Analysis of Vision-and-Language Navigation Agents",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2574-2582",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169621"}
@inproceedings{bb173949,
AUTHOR = "Gadre, S.Y. and Wortsman, M. and Ilharco, G. and Schmidt, L. and Song, S.",
TITLE = "CoWs on Pasture: Baselines and Benchmarks for Language-Driven
Zero-Shot Object Navigation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "23171-23181",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169622"}
@inproceedings{bb173950,
AUTHOR = "Li, J. and Bansal, M.",
TITLE = "Improving Vision-and-Language Navigation by Generating Future-View
Image Semantics",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10803-10812",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169623"}
@inproceedings{bb173951,
AUTHOR = "Kamath, A. and Anderson, P. and Wang, S. and Koh, J.Y. and Ku, A. and Waters, A. and Yang, Y.F. and Baldridge, J. and Parekh, Z.",
TITLE = "A New Path: Scaling Vision-and-Language Navigation with Synthetic
Instructions and Imitation Learning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10813-10823",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169624"}
@inproceedings{bb173952,
AUTHOR = "Tang, S.K. and Wang, Y.Q. and Kong, Z.L. and Zhang, T.C. and Li, Y. and Ding, C.W. and Wang, Y.Z. and Liang, Y. and Xu, D.K.",
TITLE = "You Need Multiple Exiting: Dynamic Early Exiting for Accelerating
Unified Vision Language Model",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10781-10791",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169625"}
@inproceedings{bb173953,
AUTHOR = "Armitage, J. and Impett, L. and Sennrich, R.",
TITLE = "A Priority Map for Vision-and-Language Navigation with Trajectory
Plans and Feature-Location Cues",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "1094-1103",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169626"}
@inproceedings{bb173954,
AUTHOR = "Kuo, C.W. and Ma, C.Y. and Hoffman, J. and Kira, Z.",
TITLE = "Structure-Encoding Auxiliary Tasks for Improved Visual Representation
in Vision-and-Language Navigation",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "1104-1113",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169627"}
@inproceedings{bb173955,
AUTHOR = "Irshad, M.Z. and Mithun, N.C. and Seymour, Z. and Chiu, H.P. and Samarasekera, S. and Kumar, R.",
TITLE = "Semantically-aware Spatio-temporal Reasoning Agent for
Vision-and-Language Navigation in Continuous Environments",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "4065-4071",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169628"}
@inproceedings{bb173956,
AUTHOR = "Ossandon, J. and Earle, B. and Soto, A.",
TITLE = "Bridging the Visual Semantic Gap in VLN via Semantically Richer
Instructions",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:54-69",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169629"}
@inproceedings{bb173957,
AUTHOR = "Burns, A. and Arsan, D. and Agrawal, S. and Kumar, R. and Saenko, K. and Plummer, B.A.",
TITLE = "A Dataset for Interactive Vision-Language Navigation with Unknown
Command Feasibility",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "VIII:312-328",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169630"}
@inproceedings{bb173958,
AUTHOR = "Huang, Z.M. and Shangguan, Z.K. and Zhang, J.Y. and Bar, G. and Boyd, M. and Ohn Bar, E.",
TITLE = "ASSISTER: Assistive Navigation via Conditional Instruction Generation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:271-289",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169631"}
@inproceedings{bb173959,
AUTHOR = "Zhou, K.W. and Wang, X.E.",
TITLE = "FedVLN: Privacy-Preserving Federated Vision-and-Language Navigation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:682-699",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169632"}
@inproceedings{bb173960,
AUTHOR = "Chen, S.Z. and Guhur, P.L. and Tapaswi, M. and Schmid, C. and Laptev, I.",
TITLE = "Learning from Unlabeled 3D Environments for Vision-and-Language
Navigation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:638-655",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169633"}
@inproceedings{bb173961,
AUTHOR = "Krantz, J. and Lee, S.",
TITLE = "Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous
Environments",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:588-603",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169634"}
@inproceedings{bb173962,
AUTHOR = "Lin, C. and Jiang, Y. and Cai, J.F. and Qu, L.Z. and Haffari, G. and Yuan, Z.H.",
TITLE = "Multimodal Transformer with Variable-Length Memory for
Vision-and-Language Navigation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:380-397",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169635"}
@inproceedings{bb173963,
AUTHOR = "Cheng, W.H. and Dong, X.P. and Khan, S. and Shen, J.B.",
TITLE = "Learning Disentanglement with Decoupled Labels for Vision-Language
Navigation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:309-329",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169636"}
@inproceedings{bb173964,
AUTHOR = "Kolmet, M. and Zhou, Q. and Osep, A. and Leal Taixe, L.",
TITLE = "Text2Pos: Text-to-Point-Cloud Cross-Modal Localization",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "6677-6686",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169637"}
@inproceedings{bb173965,
AUTHOR = "Partsey, R. and Wijmans, E. and Yokoyama, N. and Dobosevych, O. and Batra, D. and Maksymets, O.",
TITLE = "Is Mapping Necessary for Realistic PointGoal Navigation?",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17211-17220",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169638"}
@inproceedings{bb173966,
AUTHOR = "Ramakrishnan, S.K. and Chaplot, D.S. and Al Halah, Z. and Malik, J. and Grauman, K.",
TITLE = "PONI: Potential Functions for ObjectGoal Navigation with
Interaction-free Learning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18868-18878",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169639"}
@inproceedings{bb173967,
AUTHOR = "Chen, S.Z. and Guhur, P.L. and Tapaswi, M. and Schmid, C. and Laptev, I.",
TITLE = "Think Global, Act Local: Dual-scale Graph Transformer for
Vision-and-Language Navigation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16516-16526",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169640"}
@inproceedings{bb173968,
AUTHOR = "Zhou, M.Y. and Yu, L.C. and Singh, A. and Wang, M.J. and Yu, Z. and Zhang, N.",
TITLE = "Unsupervised Vision-and-Language Pretraining via Retrieval-based
Multi-Granular Alignment",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16464-16473",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169641"}
@inproceedings{bb173969,
AUTHOR = "Wang, S. and Montgomery, C. and Orbay, J. and Birodkar, V. and Faust, A. and Gur, I. and Jaques, N. and Waters, A. and Baldridge, J. and Anderson, P.",
TITLE = "Less is More: Generating Grounded Navigation Instructions from
Landmarks",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15407-15417",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169642"}
@inproceedings{bb173970,
AUTHOR = "Hong, Y.C. and Wang, Z. and Wu, Q. and Gould, S.",
TITLE = "Bridging the Gap Between Learning in Discrete and Continuous
Environments for Vision-and-Language Navigation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15418-15428",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169643"}
@inproceedings{bb173971,
AUTHOR = "Chen, J. and Gao, C. and Meng, E. and Zhang, Q. and Liu, S.",
TITLE = "Reinforced Structured State-Evolution for Vision-Language Navigation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15429-15438",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169644"}
@inproceedings{bb173972,
AUTHOR = "Georgakis, G. and Schmeckpeper, K. and Wanchoo, K. and Dan, S. and Miltsakaki, E. and Roth, D. and Daniilidis, K.",
TITLE = "Cross-modal Map Learning for Vision and Language Navigation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15439-15449",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169645"}
@inproceedings{bb173973,
AUTHOR = "Wang, H.Q. and Liang, W. and Shen, J.B. and Van Gool, L.J. and Wang, W.G.",
TITLE = "Counterfactual Cycle-Consistent Learning for Instruction Following
and Generation in Vision-Language Navigation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15450-15460",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169646"}
@inproceedings{bb173974,
AUTHOR = "Song, C.H. and Kil, J. and Pan, T.Y. and Sadler, B.M. and Chao, W.L. and Su, Y.",
TITLE = "One Step at a Time: Long-Horizon Vision-and-Language Navigation with
Milestones",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15461-15470",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169647"}
@inproceedings{bb173975,
AUTHOR = "Guhur, P.L. and Tapaswi, M. and Chen, S.Z. and Laptev, I. and Schmid, C.",
TITLE = "Airbert: In-Domain Pretraining for Vision-and-Language Navigation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1614-1623",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169648"}
@inproceedings{bb173976,
AUTHOR = "Liu, C. and Zhu, F. and Chang, X.J. and Liang, X.D. and Ge, Z.Y. and Shen, Y.D.",
TITLE = "Vision-Language Navigation with Random Environmental Mixup",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1624-1634",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169649"}
@inproceedings{bb173977,
AUTHOR = "Qi, Y.K. and Pan, Z.Z. and Hong, Y.C. and Yang, M.H. and van den Hengel, A.J. and Wu, Q.",
TITLE = "The Road to Know-Where: An Object-and-Room Informed Sequential BERT
for Indoor Vision-Language Navigation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1635-1644",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169650"}
@inproceedings{bb173978,
AUTHOR = "Liu, Z.Y. and Rodriguez Opazo, C. and Teney, D. and Gould, S.",
TITLE = "Image Retrieval on Real-life Images with Pre-trained
Vision-and-Language Models",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "2105-2114",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169651"}
@inproceedings{bb173979,
AUTHOR = "Pashevich, A. and Schmid, C. and Sun, C.",
TITLE = "Episodic Transformer for Vision-and-Language Navigation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "15922-15932",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169652"}
@inproceedings{bb173980,
AUTHOR = "Chen, K. and Chen, J.K. and Chuang, J. and Vazquez, M. and Savarese, S.",
TITLE = "Topological Planning with Transformers for Vision-and-Language
Navigation",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "11271-11281",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169653"}
@inproceedings{bb173981,
AUTHOR = "Badki, A. and Gallo, O. and Kautz, J. and Sen, P.",
TITLE = "Binary TTC: A Temporal Geofence for Autonomous Navigation",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "12941-12950",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169654"}
@inproceedings{bb173982,
AUTHOR = "Wang, H.Q. and Wang, W.G. and Liang, W. and Xiong, C.M. and Shen, J.B.",
TITLE = "Structured Scene Memory for Vision-Language Navigation",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "8451-8460",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169655"}
@inproceedings{bb173983,
AUTHOR = "Wang, H.Q. and Wang, W.G. and Shu, T.M. and Liang, W. and Shen, J.B.",
TITLE = "Active Visual Information Gathering for Vision-language Navigation",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XXII:307-322",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169656"}
@inproceedings{bb173984,
AUTHOR = "Cao, J. and Gan, Z. and Cheng, Y. and Yu, L.C. and Chen, Y.C. and Liu, J.J.",
TITLE = "Behind the Scene: Revealing the Secrets of Pre-trained
Vision-and-language Models",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "VI:565-580",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169657"}
@inproceedings{bb173985,
AUTHOR = "Moghaddam, M.K. and Abbasnejad, E. and Wu, Q. and Shi, J.Q.F. and van den Hengel, A.J.",
TITLE = "ForeSI: Success-Aware Visual Navigation Agent",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "3401-3410",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169658"}
@inproceedings{bb173986,
AUTHOR = "Qi, Y. and Wu, Q. and Anderson, P. and Wang, X. and Wang, W.Y. and Shen, C. and van den Hengel, A.J.",
TITLE = "REVERIE: Remote Embodied Visual Referring Expression in Real Indoor
Environments",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "9979-9988",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169659"}
@inproceedings{bb173987,
AUTHOR = "Qi, Y.K. and Pan, Z.Z. and Zhang, S.P. and van den Hengel, A.J. and Wu, Q.",
TITLE = "Object-and-action Aware Model for Visual Language Navigation",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "X:303-317",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169660"}
@inproceedings{bb173988,
AUTHOR = "Krantz, J. and Wijmans, E. and Majumdar, A. and Batra, D. and Lee, S.",
TITLE = "Beyond the Nav-Graph:
Vision-and-Language Navigation in Continuous Environments",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XXVIII:104-120",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169661"}
@inproceedings{bb173989,
AUTHOR = "Wang, H. and Wu, Q. and Shen, C.H.",
TITLE = "Soft Expert Reward Learning for Vision-and-Language Navigation",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "IX:126-141",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169662"}
@inproceedings{bb173990,
AUTHOR = "Kim, J. and Moon, S. and Rohrbach, A. and Darrell, T.J. and Canny, J.",
TITLE = "Advisable Learning for Self-Driving Vehicles by Internalizing
Observation-to-Action Rules",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "9658-9667",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169663"}
@inproceedings{bb173991,
AUTHOR = "Fu, T.J. and Wang, X.E. and Peterson, M.F. and Grafton, S.T. and Eckstein, M.P. and Wang, W.Y.",
TITLE = "Counterfactual Vision-and-Language Navigation via Adversarial Path
Sampler",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "VI:71-86",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169664"}
@inproceedings{bb173992,
AUTHOR = "Majumdar, A. and Shrivastava, A. and Lee, S. and Anderson, P. and Parikh, D. and Batra, D.",
TITLE = "Improving Vision-and-language Navigation with Image-text Pairs from the
Web",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "VI:259-274",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169665"}
@inproceedings{bb173993,
AUTHOR = "Zhu, F.D. and Zhu, Y. and Chang, X.J. and Liang, X.D.",
TITLE = "Vision-Language Navigation With Self-Supervised Auxiliary Reasoning
Tasks",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10009-10019",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169666"}
@inproceedings{bb173994,
AUTHOR = "Hao, W. and Li, C. and Li, X. and Carin, L. and Gao, J.",
TITLE = "Towards Learning a Generic Agent for Vision-and-Language Navigation
via Pre-Training",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "13134-13143",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169667"}
@inproceedings{bb173995,
AUTHOR = "Yu, F. and Deng, Z. and Narasimhan, K. and Russakovsky, O.",
TITLE = "Take the Scenic Route: Improving Generalization in
Vision-and-Language Navigation",
BOOKTITLE = VL3W20,
YEAR = "2020",
PAGES = "4000-4004",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169668"}
@inproceedings{bb173996,
AUTHOR = "Ma, C.Y. and Wu, Z.X. and Al Regib, G. and Xiong, C.M. and Kira, Z.",
TITLE = "The Regretful Agent: Heuristic-Aided Navigation Through Progress
Estimation",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6725-6733",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169669"}
@inproceedings{bb173997,
AUTHOR = "Ke, L.Y.M. and Li, X.J. and Bisk, Y. and Holtzman, A. and Gan, Z. and Liu, J.J. and Gao, J.F. and Choi, Y.J. and Srinivasa, S.",
TITLE = "Tactical Rewind: Self-Correction via Backtracking in
Vision-And-Language Navigation",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6734-6742",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169670"}
@inproceedings{bb173998,
AUTHOR = "Wang, X. and Xiong, W.H. and Wang, H.M. and Wang, W.Y.",
TITLE = "Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement
Learning for Planned-Ahead Vision-and-Language Navigation",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XVI: 38-55",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169671"}
@inproceedings{bb173999,
AUTHOR = "Anderson, P. and Wu, Q. and Teney, D. and Bruce, J. and Johnson, M. and Sunderhauf, N. and Reid, I.D. and Gould, S. and van den Hengel, A.J.",
TITLE = "Vision-and-Language Navigation: Interpreting Visually-Grounded
Navigation Instructions in Real Environments",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "3674-3683",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT169672"}
Last update:Jan 23, 2026 at 20:54:10