@inproceedings{bb179500,
        AUTHOR = "Chapoulie, A. and Rives, P. and Filliat, D.",
        TITLE = "A spherical representation for efficient visual loop closing",
        BOOKTITLE = OMNIVIS11,
        YEAR = "2011",
        PAGES = "335-342",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680lcl3.html#TT175155"}

@inproceedings{bb179501,
        AUTHOR = "Pradeep, V. and Medioni, G. and Weiland, J.",
        TITLE = "Visual loop closing using multi-resolution SIFT grids in
metric-topological SLAM",
        BOOKTITLE = CVPR09,
        YEAR = "2009",
        PAGES = "1438-1445",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680lcl3.html#TT175156"}

@inproceedings{bb179502,
        AUTHOR = "Kumar, A. and Tardif, J.P. and Anati, R. and Daniilidis, K.",
        TITLE = "Experiments on visual loop closing using vocabulary trees",
        BOOKTITLE = VisLoc08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680lcl3.html#TT175157"}

@inproceedings{bb179503,
        AUTHOR = "Triebel, R. and Pfaff, P. and Burgard, W.",
        TITLE = "Multi level surface maps
for outdoor terrain mapping and loop closing",
        BOOKTITLE = IROS06,
        YEAR = "2006",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680lcl3.html#TT175158"}

@inproceedings{bb179504,
        AUTHOR = "Bajcsy, R. and Nagel, H.H.",
        TITLE = "Descriptive and Prescriptive Languages for Mobility Tasks:
Are They Different?",
        BOOKTITLE = AIU96,
        YEAR = "1996",
        PAGES = "280-300",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175159"}

@article{bb179505,
        AUTHOR = "Zhu, M. and Chen, W. and Xia, J. and Ma, Y. and Zhang, Y. and Luo, Y. and Huang, Z. and Liu, L.",
        TITLE = "Location2Vec: A Situation-Aware Representation for Visual Exploration
of Urban Locations",
        JOURNAL = ITS,
        VOLUME = "20",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "3981-3990",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175160"}

@article{bb179506,
        AUTHOR = "Zhang, W.X. and Ma, C. and Wu, Q. and Yang, X.K.",
        TITLE = "Language-Guided Navigation via Cross-Modal Grounding and Alternate
Adversarial Learning",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "3469-3481",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175161"}

@article{bb179507,
        AUTHOR = "Li, P. and Li, X. and Li, X.H. and Pan, H. and Khyam, M.O. and Noor A Rahim, M. and Ge, S.Z.S.",
        TITLE = "Place perception from the fusion of different image representation",
        JOURNAL = PR,
        VOLUME = "110",
        YEAR = "2021",
        PAGES = "107680",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175162"}

@article{bb179508,
        AUTHOR = "Wu, Z.K. and Liu, Z. and Wang, T. and Wang, D.L.",
        TITLE = "Improved Speaker and Navigator for Vision-and-Language Navigation",
        JOURNAL = MultMedMag,
        VOLUME = "28",
        YEAR = "2021",
        NUMBER = "4",
        MONTH = "October",
        PAGES = "55-63",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175163"}

@article{bb179509,
        AUTHOR = "Wang, X. and Huang, Q.Y. and Celikyilmaz, A. and Gao, J.F. and Shen, D. and Wang, Y.F. and Wang, W.Y. and Zhang, L.",
        TITLE = "Vision-Language Navigation Policy Learning and Adaptation",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "4205-4216",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175164"}

@inproceedings{bb179510,
        AUTHOR = "Wang, X. and Huang, Q.Y. and Celikyilmaz, A. and Gao, J.F. and Shen, D. and Wang, Y.F. and Wang, W.Y. and Zhang, L.",
        TITLE = "Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning
for Vision-Language Navigation",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6622-6631",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175165"}

@article{bb179511,
        AUTHOR = "Lin, B.Q. and Zhu, Y. and Long, Y.X. and Liang, X.D. and Ye, Q.X. and Lin, L.",
        TITLE = "Adversarial Reinforced Instruction Attacker for Robust
Vision-Language Navigation",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "7175-7189",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175166"}

@article{bb179512,
        AUTHOR = "Wang, H.Q. and Wang, W.G. and Liang, W. and Hoi, S.C.H. and Shen, J.B. and Van Gool, L.J.",
        TITLE = "Active Perception for Visual-Language Navigation",
        JOURNAL = IJCV,
        VOLUME = "131",
        YEAR = "2023",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "607-625",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175167"}

@article{bb179513,
        AUTHOR = "Ding, H.H. and Liu, C. and Wang, S. and Jiang, X.D.",
        TITLE = "VLT: Vision-Language Transformer and Query Generation for Referring
Segmentation",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "7900-7916",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175168"}

@inproceedings{bb179514,
        AUTHOR = "Ding, H.H. and Liu, C. and Wang, S. and Jiang, X.D.",
        TITLE = "Vision-Language Transformer and Query Generation for Referring
Segmentation",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "16301-16310",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175169"}

@article{bb179515,
        AUTHOR = "Zeng, H.T. and Song, X.H. and Jiang, S.Q.",
        TITLE = "Multi-Object Navigation Using Potential Target Position Policy
Function",
        JOURNAL = IP,
        VOLUME = "32",
        YEAR = "2023",
        PAGES = "2608-2619",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175170"}

@article{bb179516,
        AUTHOR = "Qiao, Y.Y. and Qi, Y.K. and Hong, Y.C. and Yu, Z. and Wang, P. and Wu, Q.",
        TITLE = "HOP+: History-Enhanced and Order-Aware Pre-Training for
Vision-and-Language Navigation",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "8524-8537",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175171"}

@inproceedings{bb179517,
        AUTHOR = "Qiao, Y.Y. and Qi, Y.K. and Hong, Y.C. and Yu, Z. and Wang, P. and Wu, Q.",
        TITLE = "HOP: History-and-Order Aware Pretraining for Vision-and-Language
Navigation",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "15397-15406",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175172"}

@article{bb179518,
        AUTHOR = "Wang, L. and He, Z.T. and Dang, R.H. and Chen, H. and Liu, C.J. and Chen, Q.J.",
        TITLE = "RES-StS: Referring Expression Speaker via Self-Training With Scorer
for Goal-Oriented Vision-Language Navigation",
        JOURNAL = CirSysVideo,
        VOLUME = "33",
        YEAR = "2023",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "3441-3454",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175173"}

@article{bb179519,
        AUTHOR = "Lin, B.Q. and Long, Y.X. and Zhu, Y. and Zhu, F.D. and Liang, X.D. and Ye, Q.X. and Lin, L.",
        TITLE = "Towards Deviation-Robust Agent Navigation via Perturbation-Aware
Contrastive Learning",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "12535-12549",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175174"}

@article{bb179520,
        AUTHOR = "He, K. and Jing, Y. and Huang, Y. and Lu, Z. and An, D. and Wang, L.",
        TITLE = "Memory-Adaptive Vision-and-Language Navigation",
        JOURNAL = PR,
        VOLUME = "153",
        YEAR = "2024",
        PAGES = "110511",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175175"}

@article{bb179521,
        AUTHOR = "Wu, S.Y. and Fu, X.Y. and Wu, F. and Zha, Z.J.",
        TITLE = "Vision-and-Language Navigation via Latent Semantic Alignment Learning",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "8406-8418",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175176"}

@article{bb179522,
        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#TT175177"}

@article{bb179523,
        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#TT175178"}

@article{bb179524,
        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#TT175179"}

@article{bb179525,
        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#TT175180"}

@article{bb179526,
        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#TT175181"}

@article{bb179527,
        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#TT175182"}

@article{bb179528,
        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#TT175183"}

@article{bb179529,
        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#TT175184"}

@article{bb179530,
        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#TT175185"}

@article{bb179531,
        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#TT175186"}

@article{bb179532,
        AUTHOR = "Qiao, G. and Yi, D. and Wu, L.X. and Wu, H.X. and Wang, J.Q.",
        TITLE = "Enhancing Visual Aligning and Grounding for Aerial Vision-and-Dialog
Navigation",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "2853-2857",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175187"}

@article{bb179533,
        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#TT175188"}

@article{bb179534,
        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#TT175189"}

@article{bb179535,
        AUTHOR = "Dai, G.Z. and Wang, S. and Zhao, H. and Zhu, B. and Sun, Q. and Shu, X.B.",
        TITLE = "ThinkMatter: Panoramic-Aware Instructional Semantics for Monocular
Vision-and-Language Navigation",
        JOURNAL = IP,
        VOLUME = "35",
        YEAR = "2026",
        PAGES = "1937-1950",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175190"}

@article{bb179536,
        AUTHOR = "Panek, V. and Zhou, Q.J. and Ding, Y.Q. and Agostinho, S. and Kukelova, Z. and Sattler, T. and Leal Taixe, L.",
        TITLE = "A Guide to Structureless Visual Localization",
        JOURNAL = IJCV,
        VOLUME = "134",
        YEAR = "2026",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "263",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175191"}

@inproceedings{bb179537,
        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#TT175192"}

@article{bb179538,
        AUTHOR = "He, K. and Huang, Y. and Jing, Y. and Wu, Q. and Wang, L.",
        TITLE = "Fine-Grained Alignment Supervision Matters in Vision-and-Language
Navigation",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "6525-6540",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175193"}

@article{bb179539,
        AUTHOR = "Yuan, S. and Zhang, H.X. and Liu, L. and Zhu, L. and Dong, X.F.",
        TITLE = "SPENav: Dynamic Object Filtering With Spatial Perception Enhancement
for Vision-Language Navigation",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "6905-6919",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175194"}

@article{bb179540,
        AUTHOR = "Han, Y.X. and Wu, K. and Shao, Q.Y. and Xiao, R. and Wang, Z. and Jiang, C. and Xiao, Y. and Hu, L. and Lou, Y.J.",
        TITLE = "AppleVLM: End-to-End Autonomous Driving With Advanced Perception and
Planning-Enhanced Vision-Language Models",
        JOURNAL = ITS,
        VOLUME = "27",
        YEAR = "2026",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "7028-7043",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175195"}

@article{bb179541,
        AUTHOR = "Xu, Y.Z. and Pan, Y.Y. and Liu, Z.",
        TITLE = "Dream to Recall: Imagination-Guided Experience Retrieval for
Memory-Persistent Vision-and-Language Navigation",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "9035-9049",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175196"}

@article{bb179542,
        AUTHOR = "Zhong, Z. and Lu, J. and Liu, X.C. and Yu, R.Z. and Zheng, X. and Liu, Z. and Wang, H.S. and Li, H.A.",
        TITLE = "Spatial-Aware and Viewpoint-Robust Vision-Language Navigation",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "11717-11728",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175197"}

@article{bb179543,
        AUTHOR = "Wang, T. and Zhao, X. and Cai, W.Z. and Sun, C.Y.",
        TITLE = "ImagineNav++: Prompting Vision-Language Models as Embodied Navigator
Through Scene Imagination",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "11166-11182",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175198"}

@article{bb179544,
        AUTHOR = "Wang, L.Y. and He, Z.T. and Shen, M.J. and Yang, J.W. and Liu, C.J. and Chen, Q.J.",
        TITLE = "MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for
Effective-and-Efficient Vision-and-Language Navigation",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "11477-11493",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175199"}

@article{bb179545,
        AUTHOR = "Yin, L. and Fan, Y. and Sun, Y. and Mi, B.",
        TITLE = "UTPTrack: Unlocking Text Potential via cascaded alignment and
adaptive temporal modeling for Vision-Language Tracking",
        JOURNAL = PR,
        VOLUME = "181",
        YEAR = "2027",
        PAGES = "114652",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175200"}

@article{bb179546,
        AUTHOR = "Zhang, H.L. and Li, Z. and Zhu, L. and Jiang, B. and Zhang, J. and Wan, R. and Nie, C.",
        TITLE = "Dynamic multi-modal prompt generation for Visual-Language Tracking",
        JOURNAL = SP:IC,
        VOLUME = "148",
        YEAR = "2026",
        PAGES = "117583",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175201"}

@inproceedings{bb179547,
        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#TT175202"}

@inproceedings{bb179548,
        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#TT175203"}

@inproceedings{bb179549,
        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#TT175204"}

@inproceedings{bb179550,
        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#TT175205"}

@inproceedings{bb179551,
        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#TT175206"}

@inproceedings{bb179552,
        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#TT175207"}

@inproceedings{bb179553,
        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#TT175208"}

@inproceedings{bb179554,
        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#TT175209"}

@inproceedings{bb179555,
        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#TT175210"}

@inproceedings{bb179556,
        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#TT175211"}

@inproceedings{bb179557,
        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#TT175212"}

@inproceedings{bb179558,
        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#TT175213"}

@inproceedings{bb179559,
        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#TT175214"}

@inproceedings{bb179560,
        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#TT175215"}

@inproceedings{bb179561,
        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#TT175216"}

@inproceedings{bb179562,
        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#TT175217"}

@inproceedings{bb179563,
        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#TT175218"}

@inproceedings{bb179564,
        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#TT175219"}

@inproceedings{bb179565,
        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#TT175220"}

@inproceedings{bb179566,
        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#TT175221"}

@inproceedings{bb179567,
        AUTHOR = "Zhang, C. and Li, M. and Budvytis, I. and Liwicki, S.",
        TITLE = "DiaLoc: An Iterative Approach to Embodied Dialog Localization",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "12585-12593",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175222"}

@inproceedings{bb179568,
        AUTHOR = "Hwang, M.Y. and Jeong, J.Y. and Kim, M.S. and Oh, Y. and Oh, S.H.",
        TITLE = "Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation
Using Scene Object Spectrum Grounding",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "6683-6693",
        BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT175223"}

@inproceedings{bb179569,
        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#TT175224"}

@inproceedings{bb179570,
        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#TT175225"}

@inproceedings{bb179571,
        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#TT175226"}

@inproceedings{bb179572,
        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#TT175227"}

@inproceedings{bb179573,
        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#TT175228"}

@inproceedings{bb179574,
        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#TT175229"}

@inproceedings{bb179575,
        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#TT175230"}

@inproceedings{bb179576,
        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#TT175231"}

@inproceedings{bb179577,
        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#TT175232"}

@inproceedings{bb179578,
        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#TT175233"}

@inproceedings{bb179579,
        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#TT175234"}

@inproceedings{bb179580,
        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#TT175235"}

@inproceedings{bb179581,
        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#TT175236"}

@inproceedings{bb179582,
        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#TT175237"}

@inproceedings{bb179583,
        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#TT175238"}

@inproceedings{bb179584,
        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#TT175239"}

@inproceedings{bb179585,
        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#TT175240"}

@inproceedings{bb179586,
        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#TT175241"}

@inproceedings{bb179587,
        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#TT175242"}

@inproceedings{bb179588,
        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#TT175243"}

@inproceedings{bb179589,
        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#TT175244"}

@inproceedings{bb179590,
        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#TT175245"}

@inproceedings{bb179591,
        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#TT175246"}

@inproceedings{bb179592,
        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#TT175247"}

@inproceedings{bb179593,
        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#TT175248"}

@inproceedings{bb179594,
        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#TT175249"}

@inproceedings{bb179595,
        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#TT175250"}

@inproceedings{bb179596,
        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#TT175251"}

@inproceedings{bb179597,
        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#TT175252"}

@inproceedings{bb179598,
        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#TT175253"}

@inproceedings{bb179599,
        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#TT175254"}