@inproceedings{bb247500,
AUTHOR = "Guo, Y.Y. and Wang, G.Z. and Kankanhalli, M.",
TITLE = "PELA: Learning Parameter-Efficient Models with Low-Rank Approximation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15699-15709",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242392"}
@inproceedings{bb247501,
AUTHOR = "Farina, M. and Mancini, M. and Cunegatti, E. and Cunegatti, E. and Iacca, G. and Ricci, E.",
TITLE = "MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16185-16195",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242393"}
@inproceedings{bb247502,
AUTHOR = "Mu, F.Z. and Mo, S.C. and Li, Y.",
TITLE = "SnAG: Scalable and Accurate Video Grounding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18930-18940",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242394"}
@inproceedings{bb247503,
AUTHOR = "Cao, Y.H. and Ji, K.X. and Huang, Z.Y. and Zheng, C.Y. and Liu, J.J. and Wang, J. and Chen, J.D. and Yang, M.",
TITLE = "Towards Better Vision-Inspired Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13537-13547",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242395"}
@inproceedings{bb247504,
AUTHOR = "Shi, K.Y. and Dong, Q. and Goncalves, L. and Tu, Z.W. and Soatto, S.",
TITLE = "Non-autoregressive Sequence-to-Sequence Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13603-13612",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242396"}
@inproceedings{bb247505,
AUTHOR = "Man, Y.Z. and Gui, L.Y. and Wang, Y.X.",
TITLE = "Situational Awareness Matters in 3D Vision Language Reasoning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13678-13688",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242397"}
@inproceedings{bb247506,
AUTHOR = "Zheng, C.H. and Zhang, J. and Kembhavi, A. and Krishna, R.",
TITLE = "Iterated Learning Improves Compositionality in Large Vision-Language
Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13785-13795",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242398"}
@inproceedings{bb247507,
AUTHOR = "Song, C.H. and Hwang, T. and Yoon, J.Y. and Choi, S. and Gu, Y.H.",
TITLE = "SyncMask: Synchronized Attentional Masking for Fashion-centric
Vision-Language Pretraining",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13948-13957",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242399"}
@inproceedings{bb247508,
AUTHOR = "Pramanick, S. and Han, G.X. and Hou, R. and Nag, S. and Lim, S.N. and Ballas, N. and Wang, Q.F. and Chellappa, R. and Almahairi, A.",
TITLE = "Jack of All Tasks, Master of Many: Designing General-purpose
Coarse-to-Fine Vision-Language Model",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14076-14088",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242400"}
@inproceedings{bb247509,
AUTHOR = "Zeng, Y. and Huang, Y. and Zhang, J.J. and Jie, Z.Q. and Chai, Z.H. and Wang, L.",
TITLE = "Investigating Compositional Challenges in Vision-Language Models for
Visual Grounding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14141-14151",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242401"}
@inproceedings{bb247510,
AUTHOR = "Sameni, S. and Kafle, K. and Tan, H. and Jenni, S.",
TITLE = "Building Vision-Language Models on Solid Foundations with Masked
Distillation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14216-14226",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242402"}
@inproceedings{bb247511,
AUTHOR = "Peng, W. and Xie, S.C. and You, Z. and Lan, S.Y. and Wu, Z.X.",
TITLE = "Synthesize, Diagnose, and Optimize: Towards Fine-Grained
Vision-Language Understanding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13279-13288",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242403"}
@inproceedings{bb247512,
AUTHOR = "Chen, J.N. and Yu, Q.H. and Shen, X.H. and Yuille, A.L. and Chen, L.C.",
TITLE = "ViTamin: Designing Scalable Vision Models in the Vision-Language Era",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12954-12966",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242404"}
@inproceedings{bb247513,
AUTHOR = "Liu, S.H. and Yu, S. and Lin, Z.Q. and Pathak, D. and Ramanan, D.",
TITLE = "Language Models as Black-Box Optimizers for Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12687-12697",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242405"}
@inproceedings{bb247514,
AUTHOR = "Howard, P. and Madasu, A. and Le, T. and Moreno, G.L. and Bhiwandiwalla, A. and Lal, V.",
TITLE = "SocialCounterfactuals: Probing and Mitigating Intersectional Social
Biases in Vision-Language Models with Counterfactual Examples",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "11975-11985",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242406"}
@inproceedings{bb247515,
AUTHOR = "Jiang, Y.K. and Huang, Z.Z. and Zhang, R.Z. and Zhang, X.F. and Zhang, S.T.",
TITLE = "ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and
Self-Prompting",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "11386-11397",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242407"}
@inproceedings{bb247516,
AUTHOR = "Kim, Y. and Mo, S. and Kim, M. and Lee, K. and Lee, J. and Shin, J.",
TITLE = "Discovering and Mitigating Visual Biases Through Keyword Explanation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "11082-11092",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242408"}
@inproceedings{bb247517,
AUTHOR = "Li, R. and Fischer, T. and Segu, M. and Pollefeys, M. and Van Gool, L.J. and Tombari, F.",
TITLE = "Know Your Neighbors: Improving Single-View Reconstruction via Spatial
Vision-Language Reasoning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9848-9858",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242409"}
@inproceedings{bb247518,
AUTHOR = "Zeng, Z. and Wang, D. and Yang, F.Y. and Park, H. and Soatto, S. and Lao, D. and Wong, A.",
TITLE = "WorDepth: Variational Language Prior for Monocular Depth Estimation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9708-9719",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242410"}
@inproceedings{bb247519,
AUTHOR = "Yang, C. and Xu, R. and Guo, Y. and Huang, P.X. and Chen, Y. and Ding, W. and Wang, Z.Y. and Zhou, H.",
TITLE = "Improving Vision-and-Language Reasoning via Spatial Relations
Modeling",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "758-767",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242411"}
@inproceedings{bb247520,
AUTHOR = "Zhang, G.Y. and Zhang, Y.R. and Zhang, K. and Tresp, V.",
TITLE = "Can Vision-Language Models be a Good Guesser? Exploring VLMs for
Times and Location Reasoning",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "625-634",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242412"}
@inproceedings{bb247521,
AUTHOR = "Ganz, R. and Nuriel, O. and Aberdam, A. and Kittenplon, Y. and Mazor, S. and Litman, R.",
TITLE = "Towards Models that Can See and Read",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "21661-21671",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242413"}
@inproceedings{bb247522,
AUTHOR = "Zhang, H. and Liu, D. and Lv, Z. and Su, B. and Tao, D.C.",
TITLE = "Exploring Temporal Concurrency for Video-Language Representation
Learning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15522-15532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242414"}
@inproceedings{bb247523,
AUTHOR = "Shukor, M. and Dancette, C. and Cord, M.",
TITLE = "eP-ALM: Efficient Perceptual Augmentation of Language Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "21999-22012",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242415"}
@inproceedings{bb247524,
AUTHOR = "Schulter, S. and Kumar, B.G.V. and Suh, Y.M. and Dafnis, K.M. and Zhang, Z.X. and Zhao, S.Y. and Metaxas, D.N.",
TITLE = "OmniLabel: A Challenging Benchmark for Language-Based Object
Detection",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "11919-11928",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242416"}
@inproceedings{bb247525,
AUTHOR = "Chen, Z.L. and Huang, X. and Guan, Q.L. and Lin, L. and Luo, W.Q.",
TITLE = "A Retrospect to Multi-prompt Learning across Vision and Language",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22133-22144",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242417"}
@inproceedings{bb247526,
AUTHOR = "Derakhshani, M.M. and Sanchez, E. and Bulat, A. and da Costa, V.G.T. and Snoek, C.G.M. and Tzimiropoulos, G. and Martinez, B.",
TITLE = "Bayesian Prompt Learning for Image-Language Model Generalization",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15191-15200",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242418"}
@inproceedings{bb247527,
AUTHOR = "Cascante Bonilla, P. and Shehada, K. and Smith, J.S. and Doveh, S. and Kim, D.H. and Panda, R. and Varol, G. and Oliva, A. and Ordonez, V. and Feris, R.S. and Karlinsky, L.",
TITLE = "Going Beyond Nouns With Vision & Language Models Using Synthetic
Data",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20098-20108",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242419"}
@inproceedings{bb247528,
AUTHOR = "Bitton Guetta, N. and Bitton, Y. and Hessel, J. and Schmidt, L. and Elovici, Y. and Stanovsky, G. and Schwartz, R.",
TITLE = "Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of
Synthetic and Compositional Images",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2616-2627",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242420"}
@inproceedings{bb247529,
AUTHOR = "Slyman, E. and Kahng, M. and Lee, S.",
TITLE = "VLSlice: Interactive Vision-and-Language Slice Discovery",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15245-15255",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242421"}
@inproceedings{bb247530,
AUTHOR = "Najibi, M. and Ji, J.W. and Zhou, Y. and Qi, C.R. and Yan, X.C. and Ettinger, S. and Anguelov, D.",
TITLE = "Unsupervised 3D Perception with 2D Vision-Language Distillation for
Autonomous Driving",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "8568-8578",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242422"}
@inproceedings{bb247531,
AUTHOR = "Xu, H. and Xie, S. and Huang, P.Y. and Yu, L.C. and Howes, R. and Ghosh, G. and Zettlemoyer, L. and Feichtenhofer, C.",
TITLE = "CiT: Curation in Training for Effective Vision-Language Data",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15134-15143",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242423"}
@inproceedings{bb247532,
AUTHOR = "Trager, M. and Perera, P. and Zancato, L. and Achille, A. and Bhatia, P. and Soatto, S.",
TITLE = "Linear Spaces of Meanings: Compositional Structures in
Vision-Language Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15349-15358",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242424"}
@inproceedings{bb247533,
AUTHOR = "Chen, Y.S. and Song, Y.Z. and Yeo, C.Y. and Liu, B. and Fu, J.L. and Shuai, H.H.",
TITLE = "SINC: Self-Supervised In-Context Learning for Vision-Language Tasks",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15384-15396",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242425"}
@inproceedings{bb247534,
AUTHOR = "Zhai, J.T. and Zhang, Q. and Wu, T. and Chen, X.Y. and Liu, J.J. and Cheng, M.M.",
TITLE = "SLAN: Self-Locator Aided Network for Vision-Language Understanding",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "21892-21901",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242426"}
@inproceedings{bb247535,
AUTHOR = "Long, S. and Zhao, Z. and Yuan, J. and Tan, Z.C. and Liu, J.J. and Zhou, L.P. and Wang, S.S. and Wang, J.D.",
TITLE = "Task-Oriented Multi-Modal Mutual Learning for Vision-Language Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "21902-21912",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242427"}
@inproceedings{bb247536,
AUTHOR = "Zhu, H.G. and Wei, Y.C. and Liang, X.D. and Zhang, C.J. and Zhao, Y.",
TITLE = "CTP: Towards Vision-Language Continual Pretraining via Compatible
Momentum Contrast and Topology Preservation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22200-22210",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242428"}
@inproceedings{bb247537,
AUTHOR = "Hall, M. and Gustafson, L. and Adcock, A. and Misra, I. and Ross, C.",
TITLE = "Vision-Language Models Performing Zero-Shot Tasks Exhibit Disparities
Between Gender Groups",
BOOKTITLE = CLVL23,
YEAR = "2023",
PAGES = "2770-2777",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242429"}
@inproceedings{bb247538,
AUTHOR = "Agnolucci, L. and Baldrati, A. and Todino, F. and Becattini, F. and Bertini, M. and del Bimbo, A.",
TITLE = "ECO: Ensembling Context Optimization for Vision-Language Models",
BOOKTITLE = CLVL23,
YEAR = "2023",
PAGES = "2803-2807",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242430"}
@inproceedings{bb247539,
AUTHOR = "Palit, V. and Pandey, R. and Arora, A. and Liang, P.P.",
TITLE = "Towards Vision-Language Mechanistic Interpretability: A Causal
Tracing Tool for BLIP",
BOOKTITLE = CLVL23,
YEAR = "2023",
PAGES = "2848-2853",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242431"}
@inproceedings{bb247540,
AUTHOR = "Sammani, F. and Deligiannis, N.",
TITLE = "Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language
Tasks",
BOOKTITLE = VLAR23,
YEAR = "2023",
PAGES = "4636-4641",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242432"}
@inproceedings{bb247541,
AUTHOR = "Lee, D.J. and Song, S. and Suh, J. and Choi, J. and Lee, S. and Kim, H.W.J.",
TITLE = "Read-only Prompt Optimization for Vision-Language Few-shot Learning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "1401-1411",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242433"}
@inproceedings{bb247542,
AUTHOR = "Li, X. and Fang, Y.H. and Liu, M.H. and Ling, Z. and Tu, Z.W. and Su, H.",
TITLE = "Distilling Large Vision-Language Model with Out-of-Distribution
Generalizability",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2492-2503",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242434"}
@inproceedings{bb247543,
AUTHOR = "Bi, J.Y. and Cheng, D. and Yao, P. and Pang, B. and Zhan, Y.F. and Yang, C.G. and Wang, Y.J. and Sun, H. and Deng, W.W. and Zhang, Q.",
TITLE = "VL-Match: Enhancing Vision-Language Pretraining with Token-Level and
Instance-Level Matching",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2584-2593",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242435"}
@inproceedings{bb247544,
AUTHOR = "Udandarao, V. and Gupta, A. and Albanie, S.",
TITLE = "SuS-X: Training-Free Name-Only Transfer of Vision-Language Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2725-2736",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242436"}
@inproceedings{bb247545,
AUTHOR = "Jiang, C.Y. and Xu, H.Y. and Ye, W. and Ye, Q.H. and Li, C.L. and Yan, M. and Bi, B. and Zhang, S.K. and Huang, F. and Huang, S.F.",
TITLE = "BUS: Efficient and Effective Vision-language Pre-training with
Bottom-Up Patch Summarization",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2888-2898",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242437"}
@inproceedings{bb247546,
AUTHOR = "Shi, C. and Yang, S.",
TITLE = "LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for
Vision-Language Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2920-2929",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242438"}
@inproceedings{bb247547,
AUTHOR = "Wang, A.J.P. and Lin, K.Q.H. and Zhang, D.J.H. and Lei, S.W.X. and Shou, M.Z.",
TITLE = "Too Large; Data Reduction for Vision-Language Pre-Training",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "3124-3134",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242439"}
@inproceedings{bb247548,
AUTHOR = "Wang, W.H. and Yang, Z. and Xu, B. and Li, J.Z. and Sun, Y.K.",
TITLE = "ViLTA: Enhancing Vision-Language Pre-training through Textual
Augmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "3135-3146",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242440"}
@inproceedings{bb247549,
AUTHOR = "Boecking, B. and Usuyama, N. and Bannur, S. and Castro, D.C. and Schwaighofer, A. and Hyland, S. and Wetscherek, M. and Naumann, T. and Nori, A. and Alvarez Valle, J. and Poon, H. and Oktay, O.",
TITLE = "Making the Most of Text Semantics to Improve Biomedical Vision-Language
Processing",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:1-21",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242441"}
@inproceedings{bb247550,
AUTHOR = "Cui, Q. and Zhou, B. and Guo, Y. and Yin, W.D. and Wu, H. and Yoshie, O. and Chen, Y.",
TITLE = "Contrastive Vision-Language Pre-training with Limited Resources",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:236-253",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242442"}
@inproceedings{bb247551,
AUTHOR = "Hu, X.W. and Gan, Z. and Wang, J.F. and Yang, Z.Y. and Liu, Z.C. and Lu, Y. and Wang, L.J.",
TITLE = "Scaling Up Vision-Language Pretraining for Image Captioning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17959-17968",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242443"}
@inproceedings{bb247552,
AUTHOR = "Zhang, P.C. and Li, X.J. and Hu, X.W. and Yang, J.W. and Zhang, L. and Wang, L.J. and Choi, Y.J. and Gao, J.F.",
TITLE = "VinVL: Revisiting Visual Representations in Vision-Language Models",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "5575-5584",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242444"}
@inproceedings{bb247553,
AUTHOR = "Li, Z.W. and Stengel Eskin, E. and Zhang, Y.X. and Xie, C. and Tran, Q. and van Durme, B. and Yuille, A.L.",
TITLE = "Calibrating Concepts and Operations:
Towards Symbolic Reasoning on Real Images",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "14890-14899",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242445"}
@inproceedings{bb247554,
AUTHOR = "Yang, X. and Zhang, H.W. and Qi, G.J. and Cai, J.F.",
TITLE = "Causal Attention for Vision-Language Tasks",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "9842-9852",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242446"}
@inproceedings{bb247555,
AUTHOR = "Zheng, W.B. and Yan, L. and Gou, C. and Wang, F.Y.",
TITLE = "Webly Supervised Knowledge Embedding Model for Visual Reasoning",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "12442-12451",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242447"}
@inproceedings{bb247556,
AUTHOR = "Nguyen, D.K. and Okatani, T.",
TITLE = "Multi-Task Learning of Hierarchical Vision-Language Representation",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "10484-10493",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242448"}
@inproceedings{bb247557,
AUTHOR = "Gupta, T. and Shih, K.J. and Singh, S. and Hoiem, D.",
TITLE = "Aligned Image-Word Representations Improve Inductive Transfer Across
Vision-Language Tasks",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "4223-4232",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242449"}
@article{bb247558,
AUTHOR = "Ming, Y.F. and Li, Y.X.",
TITLE = "How Does Fine-Tuning Impact Out-of-Distribution Detection for
Vision-Language Models?",
JOURNAL = IJCV,
VOLUME = "132",
YEAR = "2024",
NUMBER = "2",
MONTH = "February",
PAGES = "596-609",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242450"}
@article{bb247559,
AUTHOR = "Zhao, C.R. and Wang, Y. and Jiang, X.Y. and Shen, Y.F. and Song, K. and Li, D.S. and Miao, D.Q.",
TITLE = "Learning Domain Invariant Prompt for Vision-Language Models",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "1348-1360",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242451"}
@article{bb247560,
AUTHOR = "Zhan, C.L. and Zhang, Y.F. and Lin, Y. and Wang, G.A. and Wang, H.W.",
TITLE = "UniDCP: Unifying Multiple Medical Vision-Language Tasks via Dynamic
Cross-Modal Learnable Prompts",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "9736-9748",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242452"}
@article{bb247561,
AUTHOR = "Dong, M.P. and Li, F. and Li, Z.B. and Liu, X.",
TITLE = "Cluster prototype earth mover's distance adapters and
alignment-guided prompt learning for vision-language models",
JOURNAL = PR,
VOLUME = "156",
YEAR = "2024",
PAGES = "110861",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242453"}
@article{bb247562,
AUTHOR = "Xuan, S.Y. and Yang, M. and Zhang, S.L.",
TITLE = "Adapting Vision-Language Models via Learning to Inject Knowledge",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "5798-5809",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242454"}
@article{bb247563,
AUTHOR = "Zhou, W. and Zhou, Z.H.",
TITLE = "Unsupervised Domain Adaption Harnessing Vision-Language Pre-Training",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "9",
MONTH = "September",
PAGES = "8201-8214",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242455"}
@article{bb247564,
AUTHOR = "Guo, M.H. and Zhang, Y. and Mu, T.J. and Huang, S.X. and Hu, S.M.",
TITLE = "Tuning Vision-Language Models With Multiple Prototypes Clustering",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "11186-11199",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242456"}
@article{bb247565,
AUTHOR = "Jiang, H.J. and Zhang, J.K. and Huang, R. and Ge, C.J. and Ni, Z. and Song, S. and Huang, G.",
TITLE = "Cross-modal adapter for vision-language retrieval",
JOURNAL = PR,
VOLUME = "159",
YEAR = "2025",
PAGES = "111144",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242457"}
@article{bb247566,
AUTHOR = "Yang, L.F. and Li, X. and Wang, Y.Z. and Wang, X.L. and Yang, J.",
TITLE = "Fine-Grained Visual Text Prompting",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "3",
MONTH = "March",
PAGES = "1594-1609",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242458"}
@article{bb247567,
AUTHOR = "Wang, F. and Han, Z.Y. and Liu, X. and Yin, Y.L. and Gao, X.",
TITLE = "CTPT: Continual Test-time Prompt Tuning for vision-language models",
JOURNAL = PR,
VOLUME = "161",
YEAR = "2025",
PAGES = "111300",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242459"}
@article{bb247568,
AUTHOR = "Liang, N. and Liu, Y.",
TITLE = "DPO: Discrete Prompt Optimization for Vision-Language Models",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "671-675",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242460"}
@article{bb247569,
AUTHOR = "Xu, C. and Zhu, Y.H. and Shen, H.C. and Chen, B.H. and Liao, Y.X. and Chen, X.X. and Wang, L.M.",
TITLE = "Progressive Visual Prompt Learning with Contrastive Feature
Re-formation",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "2",
MONTH = "February",
PAGES = "511-526",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242461"}
@article{bb247570,
AUTHOR = "Yin, J.H. and Zhang, X.Y. and Wu, L. and Wang, X.J.",
TITLE = "Context-aware prompt learning for test-time vision recognition with
frozen vision-language model",
JOURNAL = PR,
VOLUME = "162",
YEAR = "2025",
PAGES = "111359",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242462"}
@article{bb247571,
AUTHOR = "Lu, Z. and Bai, J. and Li, X. and Xiao, Z. and Wang, X.C.",
TITLE = "Task-to-Instance Prompt Learning for Vision-Language Models at Test
Time",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "1908-1920",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242463"}
@article{bb247572,
AUTHOR = "Yao, H.T. and Zhang, R. and Lyu, H.H. and Zhang, Y.D. and Xu, C.S.",
TITLE = "Bi-Modality Individual-Aware Prompt Tuning for Visual-Language Model",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "6352-6368",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242464"}
@inproceedings{bb247573,
AUTHOR = "Yao, H.T. and Zhang, R. and Xu, C.S.",
TITLE = "TCP: Textual-Based Class-Aware Prompt Tuning for Visual-Language
Model",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23438-23448",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242465"}
@article{bb247574,
AUTHOR = "Hao, Z.W. and Guo, J.Y. and Shen, L. and Luo, Y. and Hu, H. and Wen, Y.G.",
TITLE = "ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language
Tuning",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "5527-5543",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242466"}
@article{bb247575,
AUTHOR = "Gao, Y.S. and Zhu, Z.X. and Wang, S.S.",
TITLE = "Mixture of coarse and fine-grained prompt tuning for vision-language
model",
JOURNAL = PR,
VOLUME = "170",
YEAR = "2026",
PAGES = "112074",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242467"}
@article{bb247576,
AUTHOR = "Hao, F.S. and Liu, L. and Wu, F.X. and Zhang, Q.S. and Cheng, J.",
TITLE = "Textual Embeddings are Good Class-Aware Visual Prompts for Adapting
Vision-Language Models",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2992-2996",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242468"}
@article{bb247577,
AUTHOR = "Liu, J. and Lu, Z.Q. and Luo, H. and Lu, Z.M. and Zheng, Y.M.",
TITLE = "Progressive Multi-Prompt Learning for Vision-Language Models",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "10",
MONTH = "October",
PAGES = "9562-9574",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242469"}
@article{bb247578,
AUTHOR = "Zhang, E. and Zhu, B. and Chen, Y.Y. and Miao, Q.H. and Tang, M. and Wang, J.Q.",
TITLE = "Optimization of Prompt Learning via Multi-Knowledge Representation
for Vision-Language Models",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "7557-7569",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242470"}
@article{bb247579,
AUTHOR = "Li, J.C. and Gao, M. and Tang, S.L. and Wei, L.H. and Xiao, J. and Wu, F. and Hong, R.C. and Wang, M. and Tian, Q.",
TITLE = "Structure-Induced Gradient Regulation for Generalizable
Vision-Language Models",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "219-235",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242471"}
@inproceedings{bb247580,
AUTHOR = "Li, J.C. and Gao, M. and Wei, L.H. and Tang, S.L. and Zhang, W.Q. and Li, M.Z. and Ji, W. and Tian, Q. and Chua, T.S. and Zhuang, Y.T.",
TITLE = "Gradient-Regulated Meta-Prompt Learning for Generalizable
Vision-Language Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2551-2562",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242472"}
@article{bb247581,
AUTHOR = "Su, Y.L. and Liu, X.L. and Huang, Z. and Zhao, Y.W. and Hong, R.C. and Wang, M.",
TITLE = "AttriPrompt: Class Attribute-Aware Prompt Tuning for Vision-Language
Model",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "1395-1407",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242473"}
@article{bb247582,
AUTHOR = "Chen, Y. and Fu, S. and Zhang, Y.",
TITLE = "MoPD: Mixture-of-Prompts Distillation for Vision-Language Models",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "1943-1954",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242474"}
@article{bb247583,
AUTHOR = "Liu, X. and Lan, N. and Wei, M.J. and Xie, X.M. and Shi, G.M.",
TITLE = "SceneReasoner: Sufficient Embodied Scene Understanding From Limited
Perception by Explicit Functional Association",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "5",
MONTH = "May",
PAGES = "6456-6471",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242475"}
@article{bb247584,
AUTHOR = "Zhao, X.Y. and Li, X.T. and Duan, H.D. and Huang, H. and Li, Y. and Chen, K. and Yang, H.",
TITLE = "MG-LLaVA: Toward Multi-Granularity Visual Instruction Tuning",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "4",
MONTH = "April",
PAGES = "4464-4478",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242476"}
@article{bb247585,
AUTHOR = "Zhang, J.M. and Wang, X. and Ma, X.J. and Qiu, L.Y. and Jiang, Y.G. and Sang, J.",
TITLE = "NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust
Vision-Language Models",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "6",
MONTH = "June",
PAGES = "6615-6627",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242477"}
@inproceedings{bb247586,
AUTHOR = "Wang, X. and Chen, K. and Zhang, J.M. and Chen, J.J. and Ma, X.J.",
TITLE = "TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19910-19920",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242478"}
@article{bb247587,
AUTHOR = "Wang, G.Q. and Zhao, P. and Wang, X. and Guo, H.R. and Qi, N. and Yang, S. and Guo, Q.H.",
TITLE = "DHPT: Dual-Modality Heterogeneous Prompt Tuning for Online Test-Time
Adaption in Vision-Language Models",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "6",
MONTH = "June",
PAGES = "8590-8601",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242479"}
@article{bb247588,
AUTHOR = "Wang, X.X. and Liu, M. and Jiang, B. and Tang, J. and Luo, B.",
TITLE = "BHGraphAdapter: Parameter-Efficient VLMs Tuning Meets Hyper-Graph
Learning",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "6",
MONTH = "June",
PAGES = "9057-9071",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242480"}
@article{bb247589,
AUTHOR = "Chung, S.Y. and Yu, Y.J. and Kim, S. and Chee, Y. and Ro, Y.M.",
TITLE = "Enhanced Vision-Language Models for Diverse Sensor Understanding:
Cost-Efficient Optimization and Benchmarking",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "7444-7459",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242481"}
@article{bb247590,
AUTHOR = "Zhao, R.F. and Zhou, L. and Shang, Z. and Liu, Y.W. and Zhang, Y. and Li, S. and Ning, J. and Ning, X.",
TITLE = "ProMML for robust few-shot adaptation of vision-language models",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114160",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242482"}
@article{bb247591,
AUTHOR = "Dong, C. and Zhang, T. and Zhang, F. and Hua, Q. and Zhu, J. and Zhang, Y.",
TITLE = "Hierarchical intra-inter modal adaptation for vision-language models",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114200",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242483"}
@article{bb247592,
AUTHOR = "Dong, H. and Sheng, L.J. and Liang, J. and He, R. and Chatzi, E. and Fink, O.",
TITLE = "Adapting Vision-Language Models Without Labels: A Comprehensive Survey",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "8",
MONTH = "August",
PAGES = "389",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242484"}
@article{bb247593,
AUTHOR = "Chen, Z. and Wang, W.Y. and Zhu, J.G. and Wang, W.H. and Liu, Y.Z. and Liu, Z.Y. and Luo, G. and Sun, P. and Su, W.J. and Tian, H. and Lu, L.W. and Zhu, X. and Lu, T. and Lin, D. and Qiao, Y. and Dai, J.F.",
TITLE = "Revisiting InternVL: A Systematic Technical Framework for Building
Powerful Open-Source Vision-Language Models",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "10",
MONTH = "October",
PAGES = "12582-12600",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242485"}
@article{bb247594,
AUTHOR = "Jiao, J. and Zhou, Y.Z. and Wu, L. and Song, Z.P. and Kong, X.Y. and Cao, Y. and Qi, H.",
TITLE = "LightRA: Lightweight Residual Attention for Adaptation of
Vision-Language Models",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "7912-7923",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242486"}
@inproceedings{bb247595,
AUTHOR = "Ali, E. and Silva, S. and Arora, C. and Khan, M.H.",
TITLE = "Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment
Score",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "5875-5885",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242487"}
@inproceedings{bb247596,
AUTHOR = "Mishra, U. and Shukla, V. and Hambarde, P. and Shukla, A.",
TITLE = "Improvise, Adapt, Overcome: Telescopic Adapters for Efficient
Fine-tuning of Vision Language Models in Medical Imaging",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "7605-7615",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242488"}
@inproceedings{bb247597,
AUTHOR = "Lin, X. and Li, W.X. and Guo, S. and Wang, L.H. and Huang, D.",
TITLE = "GIP: Gated Interaction Prompt for Parameter Efficient Vision-Language
Fine-Tuning",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "617-622",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242489"}
@inproceedings{bb247598,
AUTHOR = "Valois, P.H.V. and Satav, D. and de Campos, R.A.P. and Pratamasunu, G.Q.O. and Fukui, K.",
TITLE = "Vision Language Model Interpretability with Concept Guided Decoding",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "397-402",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242490"}
@inproceedings{bb247599,
AUTHOR = "Hao, F.S. and He, F.X. and Wu, F. and Wang, T. and Song, C.Q. and Cheng, J.",
TITLE = "Task-Aware Clustering for Prompting Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14745-14755",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803tunvlm5.html#TT242491"}
Last update:Oct 8, 2026 at 11:03:09