@inproceedings{bb127300,
AUTHOR = "Silva, F.B. and Tabbone, S. and da Silva Torres, R.",
TITLE = "BoG: A New Approach for Graph Matching",
BOOKTITLE = ICPR14,
YEAR = "2014",
PAGES = "82-87",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT123484"}
@inproceedings{bb127301,
AUTHOR = "Penatti, O.A.B. and Valle, E. and da Silva Torres, R.",
TITLE = "Encoding Spatial Arrangement of Visual Words",
BOOKTITLE = CIARP11,
YEAR = "2011",
PAGES = "240-247",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT123485"}
@inproceedings{bb127302,
AUTHOR = "Peralta, B. and Soto, A.",
TITLE = "Mixing Hierarchical Contexts for Object Recognition",
BOOKTITLE = CIARP11,
YEAR = "2011",
PAGES = "232-239",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT123486"}
@inproceedings{bb127303,
AUTHOR = "Yao, B.P. and Niebles, J.C. and Fei Fei, L.",
TITLE = "Mining discriminative adjectives and prepositions for natural scene
recognition",
BOOKTITLE = VCL-ViSU09,
YEAR = "2009",
PAGES = "100-106",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT123487"}
@inproceedings{bb127304,
AUTHOR = "Shokoufandeh, A. and Dickinson, S.J. and Jonsson, C. and Bretzner, L. and Lindeberg, T.",
TITLE = "On the Representation and Matching of Qualitative Shape at Multiple
Scales",
BOOKTITLE = ECCV02,
YEAR = "2002",
PAGES = "III: 759 ff.",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT123488"}
@inproceedings{bb127305,
AUTHOR = "Yamaguchi, A. and Inokuchi, S. and Kochi, K.",
TITLE = "Stereo Matching for Stone Statues Using SRI Parameters
and Relational Graph",
BOOKTITLE = ICPR98,
YEAR = "1998",
PAGES = "Vol I: 785-787",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT123489"}
@inproceedings{bb127306,
AUTHOR = "Dubuisson Jolly, M.P. and Jain, A.K.",
TITLE = "A Modified Hausdorff Distance for Object Matching",
BOOKTITLE = ICPR94,
YEAR = "1994",
PAGES = "A:566-568",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT123490"}
@inproceedings{bb127307,
AUTHOR = "Enomoto, H. and Yonezaki, N. and Nitta, K.",
TITLE = "A Model for Perception of Structural Image Feature",
BOOKTITLE = IJCAI79,
YEAR = "1979",
PAGES = "257-259",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT123491"}
@article{bb127308,
AUTHOR = "Zhang, Z.C. and Wu, H.N. and Zhang, E. and Zhai, G.T. and Lin, W.S.",
TITLE = "Q-Bench+: A Benchmark for Multi-Modal Foundation Models on Low-Level
Vision From Single Images to Pairs",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "10404-10418",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123492"}
@article{bb127309,
AUTHOR = "Yu, T. and Fu, K. and Wang, S.H. and Huang, Q.M. and Yu, J.",
TITLE = "Prompting Video-Language Foundation Models With Domain-Specific
Fine-Grained Heuristics for Video Question Answering",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "2",
MONTH = "February",
PAGES = "1615-1630",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123493"}
@article{bb127310,
AUTHOR = "Hong, D.F. and Zhang, B. and Li, X.Y. and Li, Y.X. and Li, C.Y. and Yao, J. and Yokoya, N. and Li, H. and Ghamisi, P. and Jia, X.P. and Plaza, A. and Gamba, P. and Benediktsson, J.A. and Chanussot, J.",
TITLE = "SpectralGPT: Spectral Remote Sensing Foundation Model",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "8",
MONTH = "August",
PAGES = "5227-5244",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123494"}
@inproceedings{bb127311,
AUTHOR = "Li, X.Y. and Hong, D.F. and Chanussot, J.",
TITLE = "S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral
Remote Sensing Data",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27696-27705",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123495"}
@article{bb127312,
AUTHOR = "Li, C.Y. and Gan, Z. and Yang, Z.Y. and Yang, J.W. and Li, L.J. and Wang, L.J. and Gao, J.F.",
TITLE = "Multimodal Foundation Models:
From Specialists to General-Purpose Assistants",
JOURNAL = FTCGV,
VOLUME = "16",
YEAR = "2024",
NUMBER = "1-2",
PAGES = "1-214",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123496"}
@article{bb127313,
AUTHOR = "Liu, J.W. and Yang, C. and Lu, Z.Y. and Chen, J. and Li, Y. and Zhang, M. and Bai, T. and Fang, Y. and Sun, L.C. and Yu, P.S. and Shi, C.",
TITLE = "Graph Foundation Models: Concepts, Opportunities and Challenges",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "6",
MONTH = "June",
PAGES = "5023-5044",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123497"}
@article{bb127314,
AUTHOR = "Wu, J.W. and Huang, Z.W. and Liu, C.",
TITLE = "Advancing video self-supervised learning via image foundation models",
JOURNAL = PRL,
VOLUME = "192",
YEAR = "2025",
PAGES = "22-28",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123498"}
@article{bb127315,
AUTHOR = "Hu, M.Y. and Chang, H. and Shan, S.G. and Chen, X.L.",
TITLE = "Inference Calibration of Vision-Language Foundation Models for
Zero-Shot and Few-Shot Learning",
JOURNAL = PRL,
VOLUME = "192",
YEAR = "2025",
PAGES = "15-21",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123499"}
@article{bb127316,
AUTHOR = "Awais, M. and Naseer, M. and Khan, S. and Anwer, R.M. and Cholakkal, H. and Shah, M. and Yang, M.H. and Khan, F.S.",
TITLE = "Foundation Models Defining a New Era in Vision: A Survey and Outlook",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "2245-2264",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123500"}
@article{bb127317,
AUTHOR = "Luo, J.J. and Li, Y. and Pan, Y.W. and Yao, T. and Feng, J.L. and Chao, H.Y. and Mei, T.",
TITLE = "Exploring Vision-Language Foundation Model for Novel Object
Captioning",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "91-102",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123501"}
@article{bb127318,
AUTHOR = "Chettaoui, T. and Damer, N. and Boutros, F.",
TITLE = "FRoundation: Are foundation models ready for face recognition?",
JOURNAL = IVC,
VOLUME = "156",
YEAR = "2025",
PAGES = "105453",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123502"}
@article{bb127319,
AUTHOR = "Zhang, J.X. and Wan, G. and Gao, J.Q. and Ling, Z.H.",
TITLE = "Audio-visual representation learning via knowledge distillation from
speech foundation models",
JOURNAL = PR,
VOLUME = "162",
YEAR = "2025",
PAGES = "111432",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123503"}
@article{bb127320,
AUTHOR = "Tang, L. and Jiang, P.T. and Xiao, H. and Li, B.",
TITLE = "Towards Training-Free Open-World Segmentation via Image Prompt
Foundation Models",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "1-15",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123504"}
@article{bb127321,
AUTHOR = "Chen, H. and Wang, X. and Zeng, G. and Zhang, Y.P. and Zhou, Y.W. and Han, F. and Wu, Y.F. and Zhu, W.W.",
TITLE = "VideoDreamer: Customized Multi-Subject Text-to-Video Generation With
Disen-Mix Finetuning on Language-Video Foundation Models",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "2875-2885",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123505"}
@article{bb127322,
AUTHOR = "Wang, D. and Hu, M. and Jin, Y. and Miao, Y.C. and Yang, J.Q. and Xu, Y.C. and Qin, X.L. and Ma, J.Q. and Sun, L.Y. and Li, C.X. and Fu, C. and Chen, H. and Han, C.X. and Yokoya, N. and Zhang, J. and Xu, M.Q. and Liu, L. and Zhang, L. and Wu, C. and Du, B. and Tao, D.C. and Zhang, L.P.",
TITLE = "HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "6427-6444",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123506"}
@inproceedings{bb127323,
AUTHOR = "Hadgi, S. and Moschella, L. and Santilli, A. and Gomez, D. and Huang, Q.X. and Rodola, E. and Melzi, S. and Ovsjanikov, M.",
TITLE = "Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent
Spaces",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19825-19835",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123507"}
@inproceedings{bb127324,
AUTHOR = "Lin, H.T. and Peng, S. and Chen, J.X. and Peng, S.Y. and Sun, J.M. and Liu, M.H. and Bao, H.J. and Feng, J.S. and Zhou, X.W. and Kang, B.",
TITLE = "Prompting Depth Anything for 4K Resolution Accurate Metric Depth
Estimation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "17070-17080",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123508"}
@inproceedings{bb127325,
AUTHOR = "Liu, Z.C. and Qiao, L. and Chu, X.X. and Ma, L. and Jiang, T.T.",
TITLE = "Towards Efficient Foundation Model for Zero-shot Amodal Segmentation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "20254-20264",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123509"}
@inproceedings{bb127326,
AUTHOR = "Zheng, J.L. and Li, J.X. and Liu, D.X. and Zheng, Y. and Wang, Z.H. and Ou, Z. and Liu, Y. and Liu, J.J. and Zhang, Y.Q. and Zhan, X.Y.",
TITLE = "Universal Actions for Enhanced Embodied Foundation Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "22508-22519",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123510"}
@inproceedings{bb127327,
AUTHOR = "Hu, Z.X. and Wei, Y.X. and Shen, L. and Yuan, C. and Tao, D.C.",
TITLE = "LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual
Foundation Models by Recycling Pre-Tuned LoRAs",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25026-25037",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123511"}
@inproceedings{bb127328,
AUTHOR = "Chen, H.X. and Huang, Z.Z. and Hong, Y. and Wang, Y.S. and Lyu, Z.C. and Xu, Z. and Lan, J. and Gu, Z.X.",
TITLE = "Efficient Transfer Learning for Video-language Foundation Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29129-29138",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123512"}
@inproceedings{bb127329,
AUTHOR = "Li, J.T. and Liu, Y.Y. and Wang, X.Y. and Peng, Y.N. and Sun, C. and Wang, S. and Sun, Z.D. and Ke, T. and Jiang, X. and Lu, T.W. and Zhao, A. and Zhong, Y.F.",
TITLE = "HyperFree: A Channel-adaptive and Tuning-free Foundation Model for
Hyperspectral Remote Sensing Imagery",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23048-23058",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123513"}
@inproceedings{bb127330,
AUTHOR = "Tang, L. and Yuan, Y.X. and Chen, C.Q. and Zhang, Z. and Huang, Y. and Zhang, K.",
TITLE = "OCRT: Boosting Foundation Models in the Open World with
Object-Concept-Relation Triad",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25422-25433",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123514"}
@inproceedings{bb127331,
AUTHOR = "Chen, R. and Liang, S.Y. and Li, J.Z. and Liu, S.M. and Li, M. and Huang, Z. and Zhang, H. and Cao, X.C.",
TITLE = "Interpreting Object-level Foundation Models via Visual Precision
Search",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "30042-30052",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123515"}
@inproceedings{bb127332,
AUTHOR = "Cai, Y.C. and Yin, F. and Hammou, D. and Mantiuk, R.",
TITLE = "Do computer vision foundation models learn the low-level
characteristics of the human visual system?",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "20039-20048",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123516"}
@inproceedings{bb127333,
AUTHOR = "Yao, D.Y.F. and Zhai, A.J. and Wang, S.",
TITLE = "Uni4D: Unifying Visual Foundation Models for 4D Modeling from a
Single Video",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "1116-1126",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123517"}
@inproceedings{bb127334,
AUTHOR = "Koley, S. and Dutta, T.K. and Sain, A. and Chowdhury, P.N. and Bhunia, A.K. and Song, Y.Z.",
TITLE = "SketchFusion: Learning Universal Sketch Features through Fusing
Foundation Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2556-2567",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123518"}
@inproceedings{bb127335,
AUTHOR = "Yamaguchi, S. and Feng, D. and Kanai, S. and Adachi, K. and Chijiwa, D.",
TITLE = "Post-pre-training for Modality Alignment in Vision-Language
Foundation Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4256-4266",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123519"}
@inproceedings{bb127336,
AUTHOR = "Zhuang, W.M. and Chen, C. and Li, Z.Z. and Sajadmanesh, S. and Li, J.T. and Huang, J. and Sehwag, V. and Sharma, V. and Shinozaki, H. and Garcia, F.C. and Zhan, Y.H. and Adachi, N. and Eki, R. and Spranger, M. and Stone, P. and Lyu, L.",
TITLE = "Argus: A Compact and Versatile Foundation Model for Vision",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4418-4429",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123520"}
@inproceedings{bb127337,
AUTHOR = "Chen, Y. and Chen, X.Y. and Chen, A. and Pons Moll, G. and Xiu, Y.L.",
TITLE = "Feat2GS: Probing Visual Foundation Models with Gaussian Splatting",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6348-6361",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123521"}
@inproceedings{bb127338,
AUTHOR = "Li, J.Q. and Wang, Y.R. and Zheng, J.H. and Zhang, J. and Shen, L. and Liu, T.Q. and Cao, Z.G.",
TITLE = "CH3Depth: Efficient and Flexible Depth Foundation Model with Flow
Matching",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "7222-7232",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123522"}
@inproceedings{bb127339,
AUTHOR = "Do, M.K. and Han, K. and Lai, P. and Phan, K.T. and Xiang, W.",
TITLE = "RobSense: A Robust Multi-modal Foundation Model for Remote Sensing
with Static, Temporal, and Incomplete Data Adaptability",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "7427-7436",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123523"}
@inproceedings{bb127340,
AUTHOR = "Nakayama, K. and Ackermann, J. and Kesdogan, T.L. and Zheng, Y. and Korosteleva, M. and Sorkine Hornung, O. and Guibas, L.J. and Yang, G. and Wetzstein, G.",
TITLE = "AIpparel: A Multimodal Foundation Model for Digital Garments",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8138-8149",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123524"}
@inproceedings{bb127341,
AUTHOR = "Lu, D. and Kong, L.D. and Huang, T.X. and Lee, G.H.",
TITLE = "GEAL: Generalizable 3D Affordance Learning with Cross-Modal
Consistency",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "1680-1690",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123525"}
@inproceedings{bb127342,
AUTHOR = "Yang, J. and Tan, W.H. and Jin, C. and Yao, K. and Liu, B. and Fu, J.L. and Song, R.H. and Wu, G.S. and Wang, L.M.",
TITLE = "Transferring Foundation Models for Generalizable Robotic Manipulation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "1999-2010",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123526"}
@inproceedings{bb127343,
AUTHOR = "Singh, J. and Shrivastava, I. and Vatsa, M. and Singh, R. and Bharati, A.",
TITLE = "Learning the Power of 'No': Foundation Models with Negations",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8002-8012",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123527"}
@inproceedings{bb127344,
AUTHOR = "Rongali, S.B. and C, M.H.N. and Jha, A. and Bhargava, N. and Prasad, S. and Banerjee, B.",
TITLE = "Foundation Models and Adaptive Feature Selection:
A Synergistic Approach to Video Question Answering",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9269-9279",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123528"}
@inproceedings{bb127345,
AUTHOR = "Ranzinger, M. and Heinrich, G. and Kautz, J. and Molchanov, P.",
TITLE = "AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains
Into One",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12490-12500",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123529"}
@inproceedings{bb127346,
AUTHOR = "Li, S. and Fu, J.L. and Liu, K.Y. and Wang, W.T. and Lin, K.Y. and Wu, W.",
TITLE = "CosmicMan: A Text-to-Image Foundation Model for Humans",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6955-6965",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123530"}
@inproceedings{bb127347,
AUTHOR = "Li, J. and Wu, J.F. and Zhao, W.Z. and Bai, S. and Bai, X.",
TITLE = "Partglee: A Foundation Model for Recognizing and Parsing Any Objects",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXV: 475-494",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123531"}
@inproceedings{bb127348,
AUTHOR = "Guo, X. and Lao, J.W. and Dang, B. and Zhang, Y.Y. and Yu, L. and Ru, L.X. and Zhong, L. and Huang, Z.Y. and Wu, K. and Hu, D.X. and He, H.M. and Wang, J. and Chen, J.D. and Yang, M. and Zhang, Y.J. and Li, Y.S.",
TITLE = "SkySense: A Multi-Modal Remote Sensing Foundation Model Towards
Universal Interpretation for Earth Observation Imagery",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27662-27673",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123532"}
@inproceedings{bb127349,
AUTHOR = "Wu, J.F. and Jiang, Y. and Liu, Q.H. and Yuan, Z.H. and Bai, X. and Bai, S.",
TITLE = "General Object Foundation Model for Images and Videos at Scale",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "3783-3795",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123533"}
@inproceedings{bb127350,
AUTHOR = "Lei, T. and Yin, S.F. and Liu, Y.",
TITLE = "Exploring the Potential of Large Foundation Models for
Open-Vocabulary HOI Detection",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16657-16667",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123534"}
@inproceedings{bb127351,
AUTHOR = "Zhang, H.J. and Su, Y.Y. and Xu, X. and Jia, K.",
TITLE = "Improving the Generalization of Segmentation Foundation Model under
Distribution Shift via Weakly Supervised Adaptation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23385-23395",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123535"}
@inproceedings{bb127352,
AUTHOR = "Wu, H.N. and Zhang, Z.C. and Zhang, E. and Chen, C.F. and Liao, L. and Wang, A. and Xu, K.X. and Li, C.Y. and Hou, J.W. and Zhai, G.T. and Xue, G. and Sun, W.X. and Yan, Q. and Lin, W.S.",
TITLE = "Q-Instruct: Improving Low-Level Visual Abilities for Multi-Modality
Foundation Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "25490-25500",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123536"}
@inproceedings{bb127353,
AUTHOR = "Han, G.X. and Lim, S.N.",
TITLE = "Few-Shot Object Detection with Foundation Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28608-28618",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123537"}
@inproceedings{bb127354,
AUTHOR = "Chen, Z. and Wu, J.N. and Wang, W.H. and Su, W.J. and Chen, G. and Xing, S. and Zhong, M. and Zhang, Q.L. and Zhu, X.Z. and Lu, L.W. and Li, B. and Luo, P. and Lu, T. and Qiao, Y. and Dai, J.F.",
TITLE = "Intern VL: Scaling up Vision Foundation Models and Aligning for
Generic Visual-Linguistic Tasks",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24185-24198",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123538"}
@inproceedings{bb127355,
AUTHOR = "Stevens, S. and Wu, J. and Thompson, M.J. and Campolongo, E.G. and Song, C.H. and Carlyn, D.E. and Dong, L. and Dahdul, W.M. and Stewart, C. and Berger Wolf, T. and Chao, W.L. and Su, Y.",
TITLE = "BioCLIP: A Vision Foundation Model for the Tree of Life",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "19412-19424",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123539"}
@inproceedings{bb127356,
AUTHOR = "Li, G. and Sun, D.Q. and Sevilla Lara, L. and Jampani, V.",
TITLE = "One-Shot Open Affordance Learning with Foundation Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "3086-3096",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123540"}
@inproceedings{bb127357,
AUTHOR = "Ma, Z.X. and Hong, J. and Gul, M.O. and Gandhi, M. and Gao, I. and Krishna, R.",
TITLE = "@ CREPE: Can Vision-Language Foundation Models Reason
Compositionally?",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10910-10921",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123541"}
@inproceedings{bb127358,
AUTHOR = "Sun, X.M. and Zhang, P.C. and Zhang, P.Z. and Shah, H. and Saenko, K. and Xia, X.",
TITLE = "DIME-FM: DIstilling Multimodal and Efficient Foundation Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15475-15487",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123542"}
@inproceedings{bb127359,
AUTHOR = "Majumdar, A. and Ajay, A. and Zhang, X.H. and Putta, P. and Yenamandra, S. and Henaff, M. and Silwal, S. and Mcvay, P. and Maksymets, O. and Arnaud, S. and Yadav, K. and Li, Q. and Newman, B. and Sharma, M. and Berges, V. and Zhang, S.Q. and Agrawal, P. and Bisk, Y. and Batra, D. and Kalakrishnan, M. and Meier, F. and Paxton, C. and Sax, A. and Rajeswaran, A.",
TITLE = "OpenEQA: Embodied Question Answering in the Era of Foundation Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16488-16498",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123543"}
@inproceedings{bb127360,
AUTHOR = "Slyman, E. and Lee, S. and Cohen, S. and Kafle, K.",
TITLE = "FairDeDup: Detecting and Mitigating Vision-Language Fairness
Disparities in Semantic Dataset Deduplication",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13905-13916",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123544"}
@inproceedings{bb127361,
AUTHOR = "El Banani, M. and Raj, A. and Maninis, K.K. and Kar, A. and Li, Y.Z. and Rubinstein, M. and Sun, D.Q. and Guibas, L.J. and Johnson, J. and Jampani, V.",
TITLE = "Probing the 3D Awareness of Visual Foundation Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "21795-21806",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123545"}
@inproceedings{bb127362,
AUTHOR = "Taher, M.R.H. and Gotway, M.B. and Liang, J.M.",
TITLE = "Representing Part-Whole Hierarchies in Foundation Models by Learning
Localizability, Composability, and Decomposability from Anatomy via
Self-Supervision",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "11269-11281",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123546"}
@inproceedings{bb127363,
AUTHOR = "Hong, L.Y. and Yan, S.L. and Zhang, R.R. and Li, W.Y. and Zhou, X.Y. and Guo, P. and Jiang, K.X. and Chen, Y.T. and Li, J.L. and Chen, Z.Y. and Zhang, W.Q.",
TITLE = "OneTracker: Unifying Visual Object Tracking with Foundation Models
and Efficient Tuning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "19079-19091",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123547"}
@inproceedings{bb127364,
AUTHOR = "Zhong, F.W. and Wu, K. and Ci, H. and Wang, C. and Chen, H.",
TITLE = "Empowering Embodied Visual Tracking with Visual Foundation Models and
Offline RL",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXIII: 139-155",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123548"}
@inproceedings{bb127365,
AUTHOR = "Wang, Y. and Li, K.C. and Li, X.H. and Yu, J.S. and He, Y. and Chen, G. and Pei, B.Q. and Zheng, R.K. and Wang, Z. and Shi, Y.S. and Jiang, T.X. and Li, S.Z. and Xu, J. and Zhang, H.J. and Huang, Y.F. and Qiao, Y. and Wang, Y. and Wang, L.M.",
TITLE = "Internvideo2: Scaling Foundation Models for Multimodal Video
Understanding",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXV: 396-416",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123549"}
@inproceedings{bb127366,
AUTHOR = "Tian, Y. and Lu, G. and Zhai, G.T.",
TITLE = "Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised
Video Semantic Compression",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIX: 163-183",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123550"}
@inproceedings{bb127367,
AUTHOR = "Tian, Y. and Lu, G. and Zhai, G.T. and Gao, Z.Y.",
TITLE = "Non-Semantics Suppressed Mask Learning for Unsupervised Video
Semantic Compression",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13564-13576",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123551"}
@inproceedings{bb127368,
AUTHOR = "Zhang, C. and Wang, S.",
TITLE = "Good at captioning, bad at counting: Benchmarking GPT-4V on Earth
observation data",
BOOKTITLE = EarthVision24,
YEAR = "2024",
PAGES = "7839-7849",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123552"}
@inproceedings{bb127369,
AUTHOR = "Gao, Z.T. and Tong, Z. and Lin, K.Q. and Chen, J. and Shou, M.Z.",
TITLE = "Bootstrapping SparseFormers from Vision Foundation Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "17710-17721",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123553"}
@inproceedings{bb127370,
AUTHOR = "Chen, F. and Giuffrida, M.V. and Tsaftaris, S.A.",
TITLE = "Adapting Vision Foundation Models for Plant Phenotyping",
BOOKTITLE = CVPPA23,
YEAR = "2023",
PAGES = "604-613",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123554"}
@inproceedings{bb127371,
AUTHOR = "Wang, T. and Lin, K. and Li, L.J. and Lin, C.C. and Yang, Z.Y. and Zhang, H.W. and Liu, Z.C. and Wang, L.J.",
TITLE = "Equivariant Similarity for Vision-Language Foundation Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "11964-11974",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123555"}
@inproceedings{bb127372,
AUTHOR = "Ge, Y.Y. and Macaluso, A. and Li, L.E. and Luo, P. and Wang, X.L.",
TITLE = "Policy Adaptation from Foundation Model Feedback",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "19059-19069",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123556"}
@inproceedings{bb127373,
AUTHOR = "Dombrowski, M. and Reynaud, H. and Baugh, M. and Kainz, B.",
TITLE = "Foreground-Background Separation through Concept Distillation from
Generative Image Foundation Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "988-998",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123557"}
@inproceedings{bb127374,
AUTHOR = "Salin, E. and Ayache, S. and Favre, B.",
TITLE = "Towards an Exhaustive Evaluation of Vision-Language Foundation Models",
BOOKTITLE = MMFM23,
YEAR = "2023",
PAGES = "339-352",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123558"}
@inproceedings{bb127375,
AUTHOR = "Wang, W.H. and Dai, J.F. and Chen, Z. and Huang, Z.H. and Li, Z.Q. and Zhu, X.Z. and Hu, X.W. and Lu, T. and Lu, L.W. and Li, H.S. and Wang, X.G. and Qiao, Y.",
TITLE = "InternImage: Exploring Large-Scale Vision Foundation Models with
Deformable Convolutions",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14408-14419",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123559"}
@inproceedings{bb127376,
AUTHOR = "Shin, G. and Xie, W. and Albanie, S.",
TITLE = "NamedMask: Distilling Segmenters from Complementary Foundation Models",
BOOKTITLE = L3D-IVU23,
YEAR = "2023",
PAGES = "4961-4970",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT123560"}
@article{bb127377,
AUTHOR = "Al Shaykh, O.K. and Doherty, J.F.",
TITLE = "Invariant Image-Analysis Based on Radon-Transform and SVD",
JOURNAL = CirSysSignal,
VOLUME = "43",
YEAR = "1996",
NUMBER = "2",
MONTH = "February",
PAGES = "123-133",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123561"}
@article{bb127378,
AUTHOR = "Murase, H. and Nayar, S.K.",
TITLE = "Visual Learning And Recognition Of 3-D Objects From Appearance",
JOURNAL = IJCV,
VOLUME = "14",
YEAR = "1995",
NUMBER = "1",
MONTH = "January",
PAGES = "5-24",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123562"}
@inproceedings{bb127379,
AUTHOR = "Murase, H. and Nayar, S.K.",
TITLE = "Visual Learning Object Models from Appearance",
BOOKTITLE = DARPA93,
YEAR = "1993",
PAGES = "547-555",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123563"}
@inproceedings{bb127380,
AUTHOR = "Murase, H. and Nayar, S.K.",
TITLE = "Learning and Recognition of 3D Objects from Appearance",
BOOKTITLE = WQV93,
YEAR = "1993",
PAGES = "39-50",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123564"}
@inproceedings{bb127381,
AUTHOR = "Murase, H. and Nayar, S.K.",
TITLE = "Learning Object Models from Appearance",
BOOKTITLE = AAAI-93,
YEAR = "1993",
PAGES = "836-843",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123565"}
@article{bb127382,
AUTHOR = "Murase, H. and Nayar, S.K.",
TITLE = "Detection of 3D Objects in Cluttered Scenes
Using Hierarchical Eigenspace",
JOURNAL = PRL,
VOLUME = "18",
YEAR = "1997",
NUMBER = "4",
MONTH = "April",
PAGES = "375-384",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123566"}
@inproceedings{bb127383,
AUTHOR = "Murase, H. and Nayar, S.K.",
TITLE = "Learning by a Generation Approach to Appearance-Based
Object Recognition",
BOOKTITLE = ICPR96,
YEAR = "1996",
PAGES = "I: 24-29",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123567"}
@inproceedings{bb127384,
AUTHOR = "Murase, H. and Nayar, S.K.",
TITLE = "Image Spotting of 3D Objects Using Parametric Eigenspace Representation",
BOOKTITLE = SCIA95,
YEAR = "1995",
PAGES = "325-332",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123568"}
@article{bb127385,
AUTHOR = "Murase, H. and Shi, M. and Nayar, S.K.",
TITLE = "Parametric Eigenspace Representation for Visual Learning
and Recognition",
JOURNAL = SPIE,
VOLUME = "2031",
YEAR = "1993",
PAGES = "378-391",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123569"}
@inproceedings{bb127386,
AUTHOR = "Murase, H. and Nayar, S.K. and Nene, S.A.",
TITLE = "Software Library for Appearance Matching (SLAM)",
BOOKTITLE = ARPA94,
YEAR = "1994",
PAGES = "I:733-737",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123570"}
@inproceedings{bb127387,
AUTHOR = "Nayar, S.K. and Nene, S.A. and Murase, H.",
TITLE = "Real-Time 100 Object Recognition System",
BOOKTITLE = ARPA96,
YEAR = "1996",
PAGES = "1223-1228",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123571"}
@inproceedings{bb127388,
AUTHOR = "Murase, H. and Nene, S.A. and Nayar, S.K.",
TITLE = "Real-Time 100 Object Recognition System",
BOOKTITLE = CRA96,
YEAR = "1996",
PAGES = "III: 2321-2325",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123571"}
@inproceedings{bb127389,
AUTHOR = "Nene, S.A. and Nayar, S.K.",
TITLE = "Closest Point Search in High Dimensions",
BOOKTITLE = CVPR96,
YEAR = "1996",
PAGES = "859-865",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123572"}
@article{bb127390,
AUTHOR = "Nayar, S.K. and Nene, S.A. and Murase, H.",
TITLE = "Subspace Methods for Robot Vision",
JOURNAL = RA,
VOLUME = "12",
YEAR = "1996",
NUMBER = "5",
MONTH = "October",
PAGES = "750-758",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123573"}
@inproceedings{bb127391,
AUTHOR = "Murase, H. and Nayar, S.K. and Nene, S.A.",
TITLE = "General Learning Algorithm for Robot Vision",
BOOKTITLE = ARPA94,
YEAR = "1994",
PAGES = "I:753-763",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123574"}
@inproceedings{bb127392,
AUTHOR = "Mukherjee, S. and Nayar, S.K.",
TITLE = "Optimal RBF Networks for Visual Learning",
BOOKTITLE = ICCV95,
YEAR = "1995",
PAGES = "794-800",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123575"}
@string{Environmetrics = "Positive matrix factorization:
A non-negative factor model with optimal utilization of error
estimates of data values"}
@article{bb127394,
AUTHOR = "Flusser, J.",
TITLE = "Object Matching by Means of Matching Likelihood Coefficients",
JOURNAL = PRL,
VOLUME = "16",
YEAR = "1995",
PAGES = "893-900",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123577"}
@article{bb127395,
AUTHOR = "Chalmond, B. and Girard, S.C.",
TITLE = "Nonlinear Modeling of Scattered Multivariate Data and Its Application
to Shape Change",
JOURNAL = PAMI,
VOLUME = "21",
YEAR = "1999",
NUMBER = "5",
MONTH = "May",
PAGES = "422-432",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123578"}
@article{bb127396,
AUTHOR = "Huttenlocher, D.P. and Lilien, R.H. and Olson, C.F.",
TITLE = "View-Based Recognition Using an Eigenspace Approximation to the
Hausdorff Measure",
JOURNAL = PAMI,
VOLUME = "21",
YEAR = "1999",
NUMBER = "9",
MONTH = "September",
PAGES = "951-955",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123579"}
@inproceedings{bb127397,
AUTHOR = "Huttenlocher, D.P. and Lilien, R.H. and Olson, C.F.",
TITLE = "Approximate Hausdorff Matching Using Eigenspaces",
BOOKTITLE = ARPA96,
YEAR = "1996",
PAGES = "1181-1186",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123580"}
@inproceedings{bb127398,
AUTHOR = "Huttenlocher, D.P. and Lilien, R.H. and Olson, C.F.",
TITLE = "Object Recognition Using Subspace Methods",
BOOKTITLE = ECCV96,
YEAR = "1996",
PAGES = "I:536-545",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123581"}
@article{bb127399,
AUTHOR = "Leonardis, A. and Bischof, H.",
TITLE = "Robust Recognition Using Eigenimages",
JOURNAL = CVIU,
VOLUME = "78",
YEAR = "2000",
NUMBER = "1",
MONTH = "April",
PAGES = "99-118",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579.html#TT123582"}
Last update:Nov 2, 2025 at 14:03:07