@inproceedings{bb129500,
AUTHOR = "Jiang, Y. and Saxena, A.",
TITLE = "Infinite Latent Conditional Random Fields",
BOOKTITLE = PGMs13,
YEAR = "2013",
PAGES = "262-266",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578m1.html#TT125644"}
@inproceedings{bb129501,
AUTHOR = "Yu, W. and Ashraf, A.B. and Chang, Y.J. and Li, C.C. and Chen, T.H.",
TITLE = "3D augmented Markov random field for object recognition",
BOOKTITLE = ICIP10,
YEAR = "2010",
PAGES = "3889-3892",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578m1.html#TT125645"}
@inproceedings{bb129502,
AUTHOR = "Flenner, A.",
TITLE = "Time dependent Markov matrices for automated image analysis",
BOOKTITLE = Southwest10,
YEAR = "2010",
PAGES = "193-196",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578m1.html#TT125646"}
@inproceedings{bb129503,
AUTHOR = "Okumura, T. and Takiguchi, T. and Ariki, Y.",
TITLE = "Generic Object Recognition by Tree Conditional Random Field Based on
Hierarchical Segmentation",
BOOKTITLE = ICPR10,
YEAR = "2010",
PAGES = "3025-3028",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578m1.html#TT125647"}
@inproceedings{bb129504,
AUTHOR = "Petersen, K. and Fehr, J. and Burkhardt, H.",
TITLE = "Fast Generalized Belief Propagation for MAP Estimation on 2D and 3D
Grid-Like Markov Random Fields",
BOOKTITLE = DAGM08,
YEAR = "2008",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578m1.html#TT125648"}
@inproceedings{bb129505,
AUTHOR = "Riviere, D. and Mangin, J.F. and Martinez, J.M. and Tupin, F. and Papadopoulos Orfanos, D. and Frouin, V.",
TITLE = "Relational graph labelling using learning techniques and markov random
fields",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "II: 172-175",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578m1.html#TT125649"}
@article{bb129506,
AUTHOR = "Barrow, H.G. and Popplestone, R.J.",
TITLE = "Relational Descriptions in Picture Processing",
JOURNAL = MI,
VOLUME = "VI",
YEAR = "1971",
PAGES = "377-396",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125650"}
@inproceedings{bb129507,
AUTHOR = "Barrow, H.G. and Ambler, A.P. and Burstall, R.M.",
TITLE = "Some Techniques for Recognizing Structures in Pictures",
BOOKTITLE = FPR72,
YEAR = "1972",
PAGES = "1-29",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125651"}
@inproceedings{bb129508,
AUTHOR = "Barrow, H.G. and Ambler, A.P. and Burstall, R.M.",
TITLE = "Some Techniques for Recognizing Structures in Pictures",
BOOKTITLE = "CMetImAly77",
YEAR = "1977",
PAGES = "397-425",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125651"}
@article{bb129509,
AUTHOR = "Ambler, A.P. and Popplestone, R.J.",
TITLE = "Inferring the Position of Bodies from Specified Spatial Relationships",
JOURNAL = AI,
VOLUME = "6",
YEAR = "1975",
NUMBER = "2",
MONTH = "June",
PAGES = "157-174",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125652"}
@article{bb129510,
AUTHOR = "Popplestone, R.J. and Ambler, A.P. and Bellos, I.M.",
TITLE = "An Interpreter for a Language for Describing Assemblies",
JOURNAL = AI,
VOLUME = "14",
YEAR = "1980",
NUMBER = "1",
MONTH = "August",
PAGES = "79-107",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125653"}
@article{bb129511,
AUTHOR = "Barrow, H.G. and Burstall, R.M.",
TITLE = "Subgraph Isomorphism, Matching Relational Structures and
Maximal Cliques",
JOURNAL = IPL,
VOLUME = "4",
YEAR = "1976",
PAGES = "83-84",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125654"}
@article{bb129512,
AUTHOR = "Harlow, C.A.",
TITLE = "Image Analysis and Graphs",
JOURNAL = CGIP,
VOLUME = "2",
YEAR = "1973",
NUMBER = "1",
MONTH = "August",
PAGES = "60-82",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125655"}
@article{bb129513,
AUTHOR = "Cheng, J.K. and Huang, T.S.",
TITLE = "Image Registration by Matching Relational Structures",
JOURNAL = PR,
VOLUME = "17",
YEAR = "1984",
NUMBER = "1",
PAGES = "149-159",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125656"}
@inproceedings{bb129514,
AUTHOR = "Huang, T.S. and Cheng, J.K.",
TITLE = "Image Registration by Matching Relational Structures",
BOOKTITLE = ICPR82,
YEAR = "1982",
PAGES = "354-356",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125656"}
@inproceedings{bb129515,
AUTHOR = "Huang, T.S. and Cheng, J.K.",
TITLE = "Image Registration by Matching Relational Structures",
BOOKTITLE = PRIP81,
YEAR = "1981",
PAGES = "542-547",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125656"}
@article{bb129516,
AUTHOR = "Cheng, J.K. and Huang, T.S.",
TITLE = "A Subgraph Isomorphism Algorithm Using Resolution",
JOURNAL = PR,
VOLUME = "13",
YEAR = "1981",
NUMBER = "5",
PAGES = "371-379",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125657"}
@inproceedings{bb129517,
AUTHOR = "Cheng, J.K. and Huang, T.S.",
TITLE = "Recognition of Curvilinear Objects by Matching
Relational Structures",
BOOKTITLE = PRIP82,
YEAR = "1982",
PAGES = "343-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125658"}
@article{bb129518,
AUTHOR = "Bolles, R.C. and Cain, R.A.",
TITLE = "Recognizing and Locating Partially Visible Objects:
The Local-Feature-Focus Method",
JOURNAL = IJRR,
VOLUME = "1",
YEAR = "1982",
NUMBER = "3",
PAGES = "57-82",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125659"}
@inproceedings{bb129519,
AUTHOR = "Bolles, R.C.",
TITLE = "Recognizing and Locating Partially Visible Objects:
The Local-Feature-Focus Method",
BOOKTITLE = AAAI-80,
YEAR = "1980",
PAGES = "41-43",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125659"}
@inproceedings{bb129520,
AUTHOR = "Bolles, R.C. and Cain, R.A.",
TITLE = "Recognizing and Locating Partially Visible Workpieces:
The Local-Feature-Focus Method",
BOOKTITLE = PRIP82,
YEAR = "1982",
PAGES = "498-503",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125660"}
@inproceedings{bb129521,
AUTHOR = "Bolles, R.C.",
TITLE = "Verification Vision for Programmable Assembly",
BOOKTITLE = IJCAI77,
YEAR = "1977",
PAGES = "569-575",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125661"}
@inproceedings{bb129522,
AUTHOR = "Bolles, R.C.",
TITLE = "Verification Vision within a Programmable Assembly System",
BOOKTITLE = "Stanford AI",
YEAR = "1975",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125662"}
@article{bb129523,
AUTHOR = "Kupeev, K.Y. and Wolfson, H.J.",
TITLE = "A New Method of Estimating Shape Similarity",
JOURNAL = PRL,
VOLUME = "17",
YEAR = "1996",
NUMBER = "8",
MONTH = "July",
PAGES = "873-887",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125663"}
@inproceedings{bb129524,
AUTHOR = "Kupeev, K.Y. and Wolfson, H.J.",
TITLE = "On Shape Similarity",
BOOKTITLE = ICPR94,
YEAR = "1994",
PAGES = "A:227-231",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125664"}
@article{bb129525,
AUTHOR = "Fitch, A.J. and Kadyrov, A. and Christmas, W.J. and Kittler, J.V.",
TITLE = "Fast robust correlation",
JOURNAL = IP,
VOLUME = "14",
YEAR = "2005",
NUMBER = "8",
MONTH = "August",
PAGES = "1063-1073",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125665"}
@inproceedings{bb129526,
AUTHOR = "Fitch, A.J. and Kadyrov, A. and Christmas, W.J. and Kittler, J.V.",
TITLE = "Fast exhaustive robust matching",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "III: 903-906",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125666"}
@article{bb129527,
AUTHOR = "Ommer, B. and Mader, T. and Buhmann, J.M.",
TITLE = "Seeing the Objects Behind the Dots: Recognition in Videos from a Moving
Camera",
JOURNAL = IJCV,
VOLUME = "83",
YEAR = "2009",
NUMBER = "1",
MONTH = "June",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125667"}
@article{bb129528,
AUTHOR = "Ommer, B. and Buhmann, J.M.",
TITLE = "Learning the Compositional Nature of Visual Object Categories for
Recognition",
JOURNAL = PAMI,
VOLUME = "32",
YEAR = "2010",
NUMBER = "3",
MONTH = "March",
PAGES = "501-516",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125668"}
@inproceedings{bb129529,
AUTHOR = "Ommer, B. and Buhmann, J.M.",
TITLE = "Learning the Compositional Nature of Visual Objects",
BOOKTITLE = CVPR07,
YEAR = "2007",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125669"}
@inproceedings{bb129530,
AUTHOR = "Ommer, B. and Buhmann, J.M.",
TITLE = "Compositional Object Recognition, Segmentation, and Tracking in Video",
BOOKTITLE = EMMCVPR07,
YEAR = "2007",
PAGES = "318-333",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125670"}
@inproceedings{bb129531,
AUTHOR = "Ommer, B. and Buhmann, J.M.",
TITLE = "Learning Compositional Categorization Models",
BOOKTITLE = ECCV06,
YEAR = "2006",
PAGES = "III: 316-329",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125671"}
@inproceedings{bb129532,
AUTHOR = "Ommer, B. and Buhmann, J.M.",
TITLE = "Object Categorization by Compositional Graphical Models",
BOOKTITLE = EMMCVPR05,
YEAR = "2005",
PAGES = "235-250",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125672"}
@inproceedings{bb129533,
AUTHOR = "Ommer, B. and Sauter, M. and Buhmann, J.M.",
TITLE = "Learning Top-Down Grouping of Compositional Hierarchies for Recognition",
BOOKTITLE = PercOrg06,
YEAR = "2006",
PAGES = "194",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125673"}
@inproceedings{bb129534,
AUTHOR = "Roth, V. and Ommer, B.",
TITLE = "Exploiting Low-Level Image Segmentation for Object Recognition",
BOOKTITLE = DAGM06,
YEAR = "2006",
PAGES = "11-20",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125674"}
@inproceedings{bb129535,
AUTHOR = "Zhou, M. and Bai, Y.L. and Zhang, W. and Zhao, T.J. and Mei, T.",
TITLE = "Look-Into-Object:
Self-Supervised Structure Modeling for Object Recognition",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "11771-11780",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125675"}
@inproceedings{bb129536,
AUTHOR = "Sadeghi, F. and Tappen, M.F.",
TITLE = "Latent Pyramidal Regions for Recognizing Scenes",
BOOKTITLE = ECCV12,
YEAR = "2012",
PAGES = "V: 228-241",
BIBSOURCE = "http://www.visionbib.com/bibliography/match578.html#TT125676"}
@inproceedings{bb129537,
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#TT125677"}
@inproceedings{bb129538,
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#TT125678"}
@inproceedings{bb129539,
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#TT125679"}
@inproceedings{bb129540,
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#TT125680"}
@inproceedings{bb129541,
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#TT125681"}
@inproceedings{bb129542,
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#TT125682"}
@inproceedings{bb129543,
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#TT125683"}
@inproceedings{bb129544,
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#TT125684"}
@article{bb129545,
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#TT125685"}
@article{bb129546,
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#TT125686"}
@article{bb129547,
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#TT125687"}
@inproceedings{bb129548,
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#TT125688"}
@article{bb129549,
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#TT125689"}
@article{bb129550,
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#TT125690"}
@article{bb129551,
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#TT125691"}
@article{bb129552,
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#TT125692"}
@article{bb129553,
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#TT125693"}
@article{bb129554,
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#TT125694"}
@article{bb129555,
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#TT125695"}
@article{bb129556,
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#TT125696"}
@article{bb129557,
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#TT125697"}
@article{bb129558,
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#TT125698"}
@article{bb129559,
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#TT125699"}
@article{bb129560,
AUTHOR = "Tian, Y. and Ling, X.Y. and Geng, C. and Hu, Q. and Lu, G. and Zhai, G.T.",
TITLE = "SMC++: Masked Learning of Unsupervised Video Semantic Compression",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "1992-2011",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125700"}
@inproceedings{bb129561,
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#TT125701"}
@inproceedings{bb129562,
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#TT125702"}
@article{bb129563,
AUTHOR = "Sun, Y.D. and Cheng, H.Z. and Lu, C.Y. and Li, Z.Q. and Wu, M.H. and Lu, H.M. and Zhu, J.",
TITLE = "HyperPoint: Multimodal 3D foundation model in hyperbolic space",
JOURNAL = PR,
VOLUME = "173",
YEAR = "2026",
PAGES = "112800",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125703"}
@article{bb129564,
AUTHOR = "Fan, Z.X. and Li, G. and Zhou, Z.K.",
TITLE = "R-FGDepth: Towards foundation models for recurrent depth learning
with frequency-Guided initialization and refinement",
JOURNAL = PR,
VOLUME = "173",
YEAR = "2026",
PAGES = "112843",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125704"}
@article{bb129565,
AUTHOR = "Wang, Z.Z. and Tian, Y.J. and Xie, L.X. and Wang, Y.W. and Ye, Q.X.",
TITLE = "EinsPT: Efficient Instance-Aware Pre-Training of Vision Foundation
Models",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "786-799",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125705"}
@inproceedings{bb129566,
AUTHOR = "Silva, H.P. and Becattini, F. and Seidenari, L.",
TITLE = "Attacking Attention of Foundation Models Disrupts Downstream Tasks",
BOOKTITLE = AML25,
YEAR = "2025",
PAGES = "3534-3543",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125706"}
@inproceedings{bb129567,
AUTHOR = "Durante, Z. and Gong, R. and Sarkar, B. and Wake, N. and Taori, R. and Tang, P. and Lakshmikanth, S.K. and Schulman, K. and Milstein, A. and Vo, H. and Adeli, E. and Terzopoulos, D. and Fei Fei, L. and Gao, J.F.",
TITLE = "An Interactive Agent Foundation Model",
BOOKTITLE = WhatNext25,
YEAR = "2025",
PAGES = "3652-3662",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125707"}
@inproceedings{bb129568,
AUTHOR = "Zuo, Y.M. and Kayan, K. and Wang, M. and Jeon, K. and Deng, J. and Griffiths, T.L.",
TITLE = "Towards Foundation Models for 3D Vision: How Close are We?",
BOOKTITLE = "3DV25",
YEAR = "2025",
PAGES = "1285-1296",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125708"}
@inproceedings{bb129569,
AUTHOR = "Lee, D. and Wu, Z. and Monno, Y. and Okutomi, M.",
TITLE = "FMDP: Leveraging a Foundation Model for Dual-Pixel Disparity
Estimation",
BOOKTITLE = MVA25,
YEAR = "2025",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125709"}
@inproceedings{bb129570,
AUTHOR = "Waldmann, L. and Shah, A. and Wang, Y. and Lehmann, N. and Stewart, A.J. and Xiong, Z. and Zhu, X.X. and Bauer, S. and Chuang, J.",
TITLE = "Panopticon: Advancing Any-Sensor Foundation Models for Earth
Observation",
BOOKTITLE = FGVC25,
YEAR = "2025",
PAGES = "2195-2205",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125710"}
@inproceedings{bb129571,
AUTHOR = "Englert, B.B. and Kerssies, T. and Dubbelman, G.",
TITLE = "What is the Added Value of UDA in the VFM Era?",
BOOKTITLE = WAD25,
YEAR = "2025",
PAGES = "2521-2531",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125711"}
@inproceedings{bb129572,
AUTHOR = "Pulfer, B. and Belousov, Y. and Kinakh, V. and Furon, T. and Voloshynovskiy, S.",
TITLE = "Task-Agnostic Attacks Against Vision Foundation Models",
BOOKTITLE = AML25,
YEAR = "2025",
PAGES = "3570-3581",
BIBSOURCE = "http://www.visionbib.com/bibliography/match579gfm4.html#TT125712"}
@inproceedings{bb129573,
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#TT125713"}
@inproceedings{bb129574,
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#TT125714"}
@inproceedings{bb129575,
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#TT125715"}
@inproceedings{bb129576,
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#TT125716"}
@inproceedings{bb129577,
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#TT125717"}
@inproceedings{bb129578,
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#TT125718"}
@inproceedings{bb129579,
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#TT125719"}
@inproceedings{bb129580,
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#TT125720"}
@inproceedings{bb129581,
AUTHOR = "Chen, R. and Liang, S.Y. and Li, J.Z. and Liu, S.M. and Li, M.S. 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#TT125721"}
@inproceedings{bb129582,
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#TT125722"}
@inproceedings{bb129583,
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#TT125723"}
@inproceedings{bb129584,
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#TT125724"}
@inproceedings{bb129585,
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#TT125725"}
@inproceedings{bb129586,
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#TT125726"}
@inproceedings{bb129587,
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#TT125727"}
@inproceedings{bb129588,
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#TT125728"}
@inproceedings{bb129589,
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#TT125729"}
@inproceedings{bb129590,
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#TT125730"}
@inproceedings{bb129591,
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#TT125731"}
@inproceedings{bb129592,
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#TT125732"}
@inproceedings{bb129593,
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#TT125733"}
@inproceedings{bb129594,
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#TT125734"}
@inproceedings{bb129595,
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#TT125735"}
@inproceedings{bb129596,
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#TT125736"}
@inproceedings{bb129597,
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#TT125737"}
@inproceedings{bb129598,
AUTHOR = "Guo, X. and Lao, J.W. and Dang, B. and Zhang, Y.Y. and Yu, L. and Ru, L.X. and Zhong, L.H. 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#TT125738"}
@inproceedings{bb129599,
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#TT125739"}
Last update:Feb 26, 2026 at 10:58:24