@article{bb174500,
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#TT170173"}
@inproceedings{bb174501,
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#TT170174"}
@inproceedings{bb174502,
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#TT170175"}
@inproceedings{bb174503,
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#TT170176"}
@inproceedings{bb174504,
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#TT170177"}
@inproceedings{bb174505,
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#TT170178"}
@inproceedings{bb174506,
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#TT170179"}
@inproceedings{bb174507,
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#TT170180"}
@inproceedings{bb174508,
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#TT170181"}
@inproceedings{bb174509,
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#TT170182"}
@inproceedings{bb174510,
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#TT170183"}
@inproceedings{bb174511,
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#TT170184"}
@inproceedings{bb174512,
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#TT170185"}
@inproceedings{bb174513,
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#TT170186"}
@inproceedings{bb174514,
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#TT170187"}
@inproceedings{bb174515,
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#TT170188"}
@inproceedings{bb174516,
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#TT170189"}
@inproceedings{bb174517,
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#TT170190"}
@inproceedings{bb174518,
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#TT170191"}
@inproceedings{bb174519,
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#TT170192"}
@inproceedings{bb174520,
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#TT170193"}
@inproceedings{bb174521,
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#TT170194"}
@inproceedings{bb174522,
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#TT170195"}
@inproceedings{bb174523,
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#TT170196"}
@inproceedings{bb174524,
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#TT170197"}
@inproceedings{bb174525,
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#TT170198"}
@inproceedings{bb174526,
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#TT170199"}
@inproceedings{bb174527,
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#TT170200"}
@inproceedings{bb174528,
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#TT170201"}
@inproceedings{bb174529,
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#TT170202"}
@inproceedings{bb174530,
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#TT170203"}
@inproceedings{bb174531,
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#TT170204"}
@inproceedings{bb174532,
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#TT170205"}
@inproceedings{bb174533,
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#TT170206"}
@inproceedings{bb174534,
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#TT170207"}
@inproceedings{bb174535,
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#TT170208"}
@inproceedings{bb174536,
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#TT170209"}
@inproceedings{bb174537,
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#TT170210"}
@inproceedings{bb174538,
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#TT170211"}
@inproceedings{bb174539,
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#TT170212"}
@inproceedings{bb174540,
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#TT170213"}
@inproceedings{bb174541,
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#TT170214"}
@inproceedings{bb174542,
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#TT170215"}
@inproceedings{bb174543,
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#TT170216"}
@inproceedings{bb174544,
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#TT170217"}
@inproceedings{bb174545,
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#TT170218"}
@inproceedings{bb174546,
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#TT170219"}
@inproceedings{bb174547,
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#TT170220"}
@inproceedings{bb174548,
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#TT170221"}
@inproceedings{bb174549,
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#TT170222"}
@inproceedings{bb174550,
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#TT170223"}
@inproceedings{bb174551,
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#TT170224"}
@inproceedings{bb174552,
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#TT170225"}
@inproceedings{bb174553,
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#TT170226"}
@inproceedings{bb174554,
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#TT170227"}
@inproceedings{bb174555,
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#TT170228"}
@inproceedings{bb174556,
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#TT170229"}
@inproceedings{bb174557,
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#TT170230"}
@inproceedings{bb174558,
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#TT170231"}
@inproceedings{bb174559,
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#TT170232"}
@inproceedings{bb174560,
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#TT170233"}
@inproceedings{bb174561,
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#TT170234"}
@inproceedings{bb174562,
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#TT170235"}
@inproceedings{bb174563,
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#TT170236"}
@inproceedings{bb174564,
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#TT170237"}
@inproceedings{bb174565,
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#TT170238"}
@inproceedings{bb174566,
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#TT170239"}
@inproceedings{bb174567,
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#TT170240"}
@inproceedings{bb174568,
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#TT170241"}
@inproceedings{bb174569,
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#TT170242"}
@inproceedings{bb174570,
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#TT170243"}
@inproceedings{bb174571,
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#TT170244"}
@inproceedings{bb174572,
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#TT170245"}
@inproceedings{bb174573,
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#TT170246"}
@inproceedings{bb174574,
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#TT170247"}
@inproceedings{bb174575,
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#TT170248"}
@inproceedings{bb174576,
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#TT170249"}
@inproceedings{bb174577,
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#TT170250"}
@inproceedings{bb174578,
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#TT170251"}
@inproceedings{bb174579,
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#TT170252"}
@inproceedings{bb174580,
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#TT170253"}
@inproceedings{bb174581,
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#TT170254"}
@inproceedings{bb174582,
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#TT170255"}
@inproceedings{bb174583,
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#TT170256"}
@inproceedings{bb174584,
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#TT170257"}
@inproceedings{bb174585,
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#TT170258"}
@inproceedings{bb174586,
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#TT170259"}
@inproceedings{bb174587,
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#TT170260"}
@inproceedings{bb174588,
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#TT170261"}
@inproceedings{bb174589,
AUTHOR = "Chen, H. and Suhr, A. and Misra, D. and Snavely, N. and Artzi, Y.",
TITLE = "TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual
Street Environments",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "12530-12539",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT170262"}
@inproceedings{bb174590,
AUTHOR = "Khoshelham, K. and Diaz Vilarino, L.",
TITLE = "3D Modelling of Interior Spaces:
Learning the Language of Indoor Architecture",
BOOKTITLE = CloseRange14,
YEAR = "2014",
PAGES = "321-326",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT170263"}
@inproceedings{bb174591,
AUTHOR = "van Laere, O. and Schockaert, S. and Dhoedt, B.",
TITLE = "Finding locations of Flickr resources using language models and
similarity search",
BOOKTITLE = ICMR11,
YEAR = "2011",
PAGES = "48",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680vln2.html#TT170264"}
@article{bb174592,
AUTHOR = "Guivant, J.E. and Nebot, E.",
TITLE = "Optimization of the Simultaneous Localization and Map Building Algorithm
for Real Time Implementation",
JOURNAL = RA,
VOLUME = "17",
YEAR = "2001",
NUMBER = "3",
MONTH = "May",
PAGES = "242-257",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680.html#TT170266"}
@article{bb174593,
AUTHOR = "Li, X.S. and Guivant, J.E.",
TITLE = "Efficient and Accurate Object Detection With Simultaneous
Classification and Tracking Under Limited Computing Power",
JOURNAL = ITS,
VOLUME = "24",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "5740-5751",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680.html#TT170267"}
@article{bb174594,
AUTHOR = "Dissanayake, G. and Newman, P.M. and Durrant Whyte, H.F. and Clark, S. and Csorba, M.",
TITLE = "A Solution to the Simultaneous Location and Map Building (SLAM) Problem",
JOURNAL = RA,
VOLUME = "17",
YEAR = "2001",
NUMBER = "2",
MONTH = "May",
PAGES = "229-241",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680.html#TT170268"}
@inproceedings{bb174595,
AUTHOR = "Madhavan, R. and Dissanayake, G. and Durrant Whyte, H.F.",
TITLE = "Map-Building and Map-Based Localization in an Underground-Mine
by Statistical Pattern Matching",
BOOKTITLE = ICPR98,
YEAR = "1998",
PAGES = "Vol II: 1744-1746",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680.html#TT170269"}
@article{bb174596,
AUTHOR = "Davison, A.J. and Murray, D.W.",
TITLE = "Simultaneous Localization and Map-Building Using Active Vision",
JOURNAL = PAMI,
VOLUME = "24",
YEAR = "2002",
NUMBER = "7",
MONTH = "July",
PAGES = "865-880",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680.html#TT170270"}
@inproceedings{bb174597,
AUTHOR = "Davison, A.J. and Murray, D.W.",
TITLE = "Mobile robot localisation using active vision",
BOOKTITLE = ECCV98,
YEAR = "1998",
PAGES = "II: 809",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680.html#TT170271"}
@inproceedings{bb174598,
AUTHOR = "Chli, M. and Davison, A.J.",
TITLE = "Active Matching",
BOOKTITLE = ECCV08,
YEAR = "2008",
PAGES = "I: 72-85",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680.html#TT170272"}
@inproceedings{bb174599,
AUTHOR = "Davison, A.J.",
TITLE = "Active Search for Real-Time Vision",
BOOKTITLE = ICCV05,
YEAR = "2005",
PAGES = "I: 66-73",
BIBSOURCE = "http://www.visionbib.com/bibliography/active680.html#TT170273"}
Last update:Feb 26, 2026 at 10:58:24