@article{bb237800,
AUTHOR = "Zhang, K. and Yang, Y. and Yu, J. and Jiang, H.L. and Fan, J.P. and Huang, Q.M. and Han, W.D.",
TITLE = "Multi-Task Paired Masking With Alignment Modeling for Medical
Vision-Language Pre-Training",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "4706-4721",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232766"}
@article{bb237801,
AUTHOR = "Zara, G. and Turrisi da Costa, V.G. and Roy, S. and Rota, P. and Ricci, E.",
TITLE = "Simplifying open-set video domain adaptation with contrastive
learning",
JOURNAL = CVIU,
VOLUME = "241",
YEAR = "2024",
PAGES = "103953",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232767"}
@inproceedings{bb237802,
AUTHOR = "Zara, G. and Roy, S. and Rota, P. and Ricci, E.",
TITLE = "AutoLabel: CLIP-based framework for Open-Set Video Domain Adaptation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11504-11513",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232768"}
@article{bb237803,
AUTHOR = "Wang, X.H. and Wang, W.G. and Shao, J.Y. and Yang, Y.",
TITLE = "Learning to Follow and Generate Instructions for Language-Capable
Navigation",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "3334-3350",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232769"}
@article{bb237804,
AUTHOR = "Zhang, W.B. and Zhang, Y.F. and Deng, Y.Y. and Zhang, W.L. and Lin, J.F. and Huang, B.Q. and Zhang, J. and Yu, W.H.",
TITLE = "Ta-Adapter: Enhancing few-shot CLIP with task-aware encoders",
JOURNAL = PR,
VOLUME = "153",
YEAR = "2024",
PAGES = "110559",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232770"}
@article{bb237805,
AUTHOR = "Wu, Z.X. and Weng, Z. and Peng, W. and Yang, X.T. and Li, A. and Davis, L.S. and Jiang, Y.G.",
TITLE = "Building an Open-Vocabulary Video CLIP Model With Better
Architectures, Optimization and Data",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "7",
MONTH = "July",
PAGES = "4747-4762",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232771"}
@article{bb237806,
AUTHOR = "Yu, W.W. and Liu, Y.L. and Zhu, X.K. and Cao, H.Y. and Sun, X. and Bai, X.",
TITLE = "Turning a CLIP Model Into a Scene Text Spotter",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "9",
MONTH = "September",
PAGES = "6040-6054",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232772"}
@inproceedings{bb237807,
AUTHOR = "Yu, W.W. and Liu, Y.L. and Hua, W. and Jiang, D.Q. and Ren, B. and Bai, X.",
TITLE = "Turning a CLIP Model into a Scene Text Detector",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6978-6988",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232773"}
@article{bb237808,
AUTHOR = "Cheng, H. and Ye, H.H. and Zhou, X.F. and Liu, X.M. and Chen, F. and Wang, M.Q.",
TITLE = "Vision-language pre-training via modal interaction",
JOURNAL = PR,
VOLUME = "156",
YEAR = "2024",
PAGES = "110809",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232774"}
@article{bb237809,
AUTHOR = "Kong, J. and Wang, J. and Yu, L.C. and Zhang, X.J.",
TITLE = "Multimodality Self-distillation for Fast Inference of Vision and
Language Pretrained Models",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "8928-8940",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232775"}
@article{bb237810,
AUTHOR = "Yang, Z.Q. and An, G. and Zheng, Z.X. and Cao, S. and Ruan, Q.Q.",
TITLE = "GBC: Guided Alignment and Adaptive Boosting CLIP Bridging Vision and
Language for Robust Action Recognition",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "9",
MONTH = "September",
PAGES = "8172-8187",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232776"}
@article{bb237811,
AUTHOR = "Lin, X. and Zhu, M.H. and Dang, R.H. and Zhou, G.L. and Shu, S.L. and Lin, F. and Liu, C.J. and Chen, Q.J.",
TITLE = "CLIPose: Category-Level Object Pose Estimation With Pre-Trained
Vision-Language Knowledge",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "10",
MONTH = "October",
PAGES = "9125-9138",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232777"}
@article{bb237812,
AUTHOR = "Huang, Z.Y. and Yang, M. and Xiao, X.Y. and Hu, P. and Peng, X.",
TITLE = "Noise-Robust Vision-Language Pre-Training With Positive-Negative
Learning",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "338-350",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232778"}
@article{bb237813,
AUTHOR = "Yao, D.S. and Zhu, M.Q. and Zhu, H. and Cai, W.Q. and Zhou, L.",
TITLE = "Integrating synthetic datasets with CLIP semantic insights for single
image localization advancements",
JOURNAL = PandRS,
VOLUME = "218",
YEAR = "2024",
PAGES = "198-213",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232779"}
@article{bb237814,
AUTHOR = "Jha, A. and Singha, M. and Bhattacharya, A. and Banerjee, B.",
TITLE = "RS3Lip: Consistency for remote sensing image classification on part
embeddings using self-supervised learning and CLIP",
JOURNAL = CVIU,
VOLUME = "251",
YEAR = "2025",
PAGES = "104254",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232780"}
@article{bb237815,
AUTHOR = "Wang, X. and Jin, J.D. and Li, C.L. and Tang, J. and Zhang, C. and Wang, W.",
TITLE = "Pedestrian Attribute Recognition via CLIP-Based Prompt
Vision-Language Fusion",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "148-161",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232781"}
@inproceedings{bb237816,
AUTHOR = "Zhu, J. and Jin, J.D. and Yang, Z.H. and Wu, X.H. and Wang, X.",
TITLE = "Learning CLIP Guided Visual-Text Fusion Transformer for Video-based
Pedestrian Attribute Recognition",
BOOKTITLE = NFVLR23,
YEAR = "2023",
PAGES = "2626-2629",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232782"}
@article{bb237817,
AUTHOR = "Jin, W.Q. and Qu, M.X. and Shi, C. and Zhao, Y. and Wei, Y.C.",
TITLE = "RelFormer: Advancing contextual relations for transformer-based dense
captioning",
JOURNAL = CVIU,
VOLUME = "252",
YEAR = "2025",
PAGES = "104300",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232783"}
@article{bb237818,
AUTHOR = "Wu, Y.J. and Zhou, Y. and Saiyin, J. and Wei, B.Z. and Lai, M. and Shou, J.Z. and Xu, Y.",
TITLE = "AttriPrompter: Auto-Prompting With Attribute Semantics for Zero-Shot
Nuclei Detection via Visual-Language Pre-Trained Models",
JOURNAL = MedImg,
VOLUME = "44",
YEAR = "2025",
NUMBER = "2",
MONTH = "February",
PAGES = "982-993",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232784"}
@article{bb237819,
AUTHOR = "Ma, Q.J. and Yang, S.Q. and Zhang, L.J. and Lan, Q. and Yang, D.D. and Chen, H. and Tan, Y.",
TITLE = "APOVIS: Automated pixel-level open-vocabulary instance segmentation
through integration of pre-trained vision-language models and
foundational segmentation models",
JOURNAL = IVC,
VOLUME = "154",
YEAR = "2025",
PAGES = "105384",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232785"}
@article{bb237820,
AUTHOR = "Zhang, W.Y. and Shen, L. and Foo, C.S.",
TITLE = "Source-Free Domain Adaptation Guided by Vision and Vision-Language
Pre-training",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "2",
MONTH = "February",
PAGES = "844-866",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232786"}
@article{bb237821,
AUTHOR = "Zhang, Y.W. and Wang, J. and Tang, H.Y. and Qin, R.H.",
TITLE = "DALSCLIP: Domain aggregation via learning stronger domain-invariant
features for CLIP",
JOURNAL = IVC,
VOLUME = "154",
YEAR = "2025",
PAGES = "105359",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232787"}
@article{bb237822,
AUTHOR = "Liu, Y. and Wang, X.L. and Zhu, M.Z. and Cao, Y. and Huang, T.J. and Shen, C.H.",
TITLE = "Masked Channel Modeling for Bootstrapping Visual Pre-training",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "2",
MONTH = "February",
PAGES = "760-780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232788"}
@article{bb237823,
AUTHOR = "Li, Y. and Wang, H.L. and Duan, Y.Q. and Zhang, J.H. and Li, X.M.",
TITLE = "A closer look at the explainability of Contrastive language-image
pre-training",
JOURNAL = PR,
VOLUME = "162",
YEAR = "2025",
PAGES = "111409",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232789"}
@article{bb237824,
AUTHOR = "Zhang, Z.K. and Gao, B. and Ye, J.R. and Jin, H. and Jiang, L.H. and Yang, W.M.",
TITLE = "CLIP prior-guided 3D open-vocabulary occupancy prediction",
JOURNAL = PR,
VOLUME = "162",
YEAR = "2025",
PAGES = "111347",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232790"}
@article{bb237825,
AUTHOR = "Cai, S.Q. and Liu, X. and Yuan, J.L. and Zhou, Q.H.",
TITLE = "Prompt-Ladder: Memory-efficient prompt tuning for vision-language
models on edge devices",
JOURNAL = PR,
VOLUME = "163",
YEAR = "2025",
PAGES = "111460",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232791"}
@article{bb237826,
AUTHOR = "Ren, H.R. and Tang, F. and Zheng, H.J. and Zhao, H. and Guo, D.D. and Chang, Y.",
TITLE = "Modality-Consistent Prompt Tuning With Optimal Transport",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "3",
MONTH = "March",
PAGES = "2499-2512",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232792"}
@article{bb237827,
AUTHOR = "Cao, Y.K. and Xu, X.H. and Cheng, Y.Q. and Sun, C. and Du, Z.W. and Gao, L. and Shen, W.M.",
TITLE = "Personalizing Vision-Language Models With Hybrid Prompts for
Zero-Shot Anomaly Detection",
JOURNAL = Cyber,
VOLUME = "55",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "1917-1929",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232793"}
@inproceedings{bb237828,
AUTHOR = "Cao, Y.K. and Zhang, J.N. and Frittoli, L. and Cheng, Y.Q. and Shen, W.M. and Boracchi, G.",
TITLE = "AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-shot
Anomaly Detection",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXV: 55-72",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232794"}
@article{bb237829,
AUTHOR = "Zhang, Z.Q. and Jiang, Y. and Wang, Y. and Xie, B. and Zhang, W. and Li, Y.H. and Chen, Z. and Jin, X. and Zeng, W.J.",
TITLE = "Exploring Contrastive Pre-Training for Domain Connections in Medical
Image Segmentation",
JOURNAL = MedImg,
VOLUME = "44",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "1686-1698",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232795"}
@article{bb237830,
AUTHOR = "Zhang, W.B. and Zhang, Y.F. and Lin, J.F. and Huang, B.Q. and Zhang, J. and Yu, W.H.",
TITLE = "DC-CLIP: Multilingual CLIP Compression via vision-language
distillation and vision-language alignment",
JOURNAL = PR,
VOLUME = "164",
YEAR = "2025",
PAGES = "111547",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232796"}
@article{bb237831,
AUTHOR = "Wang, Y.F. and Kang, G.L.",
TITLE = "Attention head purification: A new perspective to harness CLIP for
domain generalization",
JOURNAL = IVC,
VOLUME = "157",
YEAR = "2025",
PAGES = "105511",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232797"}
@article{bb237832,
AUTHOR = "He, X.J. and Chen, S. and Ma, F. and Huang, Z.C. and Jin, X.J. and Liu, Z. and Fu, D.M. and Yang, Y. and Liu, J. and Feng, J.S.",
TITLE = "VLAB: Enhancing Video Language Pretraining by Feature Adapting and
Blending",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "2168-2180",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232798"}
@article{bb237833,
AUTHOR = "Fu, T.C. and Zhang, J.H. and Li, F.X. and Wei, P. and Zeng, X.L. and Zhou, W.",
TITLE = "Multimodal alignment augmentation transferable attack on
vision-language pre-training models",
JOURNAL = PRL,
VOLUME = "191",
YEAR = "2025",
PAGES = "131-137",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232799"}
@article{bb237834,
AUTHOR = "Chen, J. and Yuan, H. and Xie, B.",
TITLE = "MIF: Multi-source information fusion for few-shot classification with
CLIP",
JOURNAL = PRL,
VOLUME = "192",
YEAR = "2025",
PAGES = "113-121",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232800"}
@article{bb237835,
AUTHOR = "Luo, G. and Zhou, Y.Y. and Huang, M.L. and Ren, T. and Sun, X.S. and Ji, R.R.",
TITLE = "MoIL: Momentum Imitation Learning for Efficient Vision-Language
Adaptation",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "5192-5204",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232801"}
@article{bb237836,
AUTHOR = "Lu, Z.Q. and Liu, M. and Yu, Y.L. and Wang, Z. and Li, X. and Han, J.G.",
TITLE = "Variational Adapter: Improving CLIP in Data-Imbalanced Scenarios",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "6",
MONTH = "June",
PAGES = "5251-5264",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232802"}
@article{bb237837,
AUTHOR = "Tu, W.J. and Deng, W.J. and Gedeon, T.",
TITLE = "Toward a Holistic Evaluation of Robustness in CLIP Models",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "9",
MONTH = "September",
PAGES = "8280-8296",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232803"}
@article{bb237838,
AUTHOR = "Cao, M.X. and Xie, W.Y. and Zhang, X. and Zhang, J.Q. and Jiang, K. and Lei, J. and Li, Y.S.",
TITLE = "M³amba: CLIP-Driven Mamba Model for Multi-Modal Remote Sensing
Classification",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "7605-7617",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232804"}
@article{bb237839,
AUTHOR = "Wei, X.Y. and Kurtz, C. and Cloppet, F.",
TITLE = "Enhancing vision-language contrastive representation learning using
domain knowledge",
JOURNAL = CVIU,
VOLUME = "259",
YEAR = "2025",
PAGES = "104403",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232805"}
@inproceedings{bb237840,
AUTHOR = "Wei, X.Y. and Kurtz, C. and Cloppet, F.",
TITLE = "Relaxing Binary Constraints in Contrastive Vision-Language Medical
Representation Learning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4462-4471",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232806"}
@article{bb237841,
AUTHOR = "Jia, X.J. and Gao, S.S. and Guo, Q. and Qin, S. and Ma, K. and Huang, Y.H. and Liu, Y. and Tsang, I.W. and Cao, X.C.",
TITLE = "Semantic-Aligned Adversarial Evolution Triangle for
High-Transferability Vision-Language Attack",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "10",
MONTH = "October",
PAGES = "8489-8505",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232807"}
@article{bb237842,
AUTHOR = "You, S. and Li, J. and Bao, B.K.",
TITLE = "Pro-MA: Progressively Margin-Based Attribution in Pretrained
Vision-Language Models",
JOURNAL = MultMedMag,
VOLUME = "32",
YEAR = "2025",
NUMBER = "2",
MONTH = "April",
PAGES = "53-64",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232808"}
@article{bb237843,
AUTHOR = "Wang, Y.Z. and Hu, W.B. and Dong, Y.P. and Zhang, H.W. and Su, H. and Hong, R.C.",
TITLE = "Exploring Transferability of Multimodal Adversarial Samples for
Vision-Language Pre-Training Models with Contrastive Learning",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "6410-6421",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232809"}
@article{bb237844,
AUTHOR = "Lai, X. and Ke, X. and Xu, H.B. and Wu, S.H. and Guo, W.Z.",
TITLE = "MSP: Multimodal Self-Attention Prompt Learning",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "5978-5988",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232810"}
@article{bb237845,
AUTHOR = "Guo, Z.X. and Wang, T.J.J. and Pehlivan, S. and Radman, A. and Cao, M. and Laaksonen, J.",
TITLE = "Prompt-based Weakly-supervised Vision-language Pre-training",
JOURNAL = PRL,
VOLUME = "197",
YEAR = "2025",
PAGES = "8-15",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232811"}
@article{bb237846,
AUTHOR = "Ding, M. and Ma, Y. and Qin, P. and Wu, J.L. and Li, Y.H. and Nie, L.Q.",
TITLE = "RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping
Language-Image Pre-Training",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "7522-7532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232812"}
@article{bb237847,
AUTHOR = "Ye, Z.P. and Jiang, F. and Wang, Q. and Huang, K. and Huang, J.Q.",
TITLE = "IDEA: Image description enhanced CLIP-adapter for image
classification",
JOURNAL = PR,
VOLUME = "171",
YEAR = "2026",
PAGES = "112224",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232813"}
@article{bb237848,
AUTHOR = "Lai, H. and Wei, X. and Sun, R. and Zhang, T.Z.",
TITLE = "Agent-Based Control Prompt Tuning for Video-Text Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "11613-11626",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232814"}
@article{bb237849,
AUTHOR = "Tu, R.C. and Ji, Y. and Jiang, J. and Kong, W.J. and Cai, C.F. and Zhao, W.Z. and Wang, H.F. and Yang, Y. and Liu, W.",
TITLE = "Global and Local Semantic Completion Learning for Vision-Language
Pre-Training",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "12",
MONTH = "December",
PAGES = "11065-11079",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232815"}
@inproceedings{bb237850,
AUTHOR = "Ji, Y. and Tu, R.C. and Jiang, J. and Kong, W.J. and Cai, C.F. and Zhao, W.Z. and Wang, H.F. and Yang, Y. and Liu, W.",
TITLE = "Seeing What You Miss:
Vision-Language Pre-training with Semantic Completion Learning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6789-6798",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232816"}
@inproceedings{bb237851,
AUTHOR = "Abbasi, R. and Nazari, A. and Sefid, A. and Banayeeanzade, M. and Rohban, M.H. and Baghshah, M.S.",
TITLE = "CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object
Representation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "9308-9317",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232817"}
@inproceedings{bb237852,
AUTHOR = "Choi, H. and Jang, Y.K. and Eom, C.",
TITLE = "GOAL: Global-local Object Alignment Learning",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4070-4079",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232818"}
@inproceedings{bb237853,
AUTHOR = "Li, S. and Liu, F. and Hao, Z. and Wang, X. and Li, L.L. and Liu, X. and Chen, P. and Ma, W.P.",
TITLE = "Logits DeConfusion with CLIP for Few-Shot Learning",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25411-25421",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232819"}
@inproceedings{bb237854,
AUTHOR = "Zhang, Z.Y. and Yu, Y. and Chen, Y.C. and Yang, X. and Yeo, S.Y.",
TITLE = "MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data
with Vision Generation Task using Discrete Visual Representations",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29744-29755",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232820"}
@inproceedings{bb237855,
AUTHOR = "Chen, Z.L. and Huang, X. and Fan, X.X. and Wang, K. and Zhou, Y. and Guan, Q.L. and Lin, L.",
TITLE = "Reproducible Vision-Language Models Meet Concepts Out of Pre-Training",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14701-14711",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232821"}
@inproceedings{bb237856,
AUTHOR = "Wu, S. and Zhang, J. and Zeng, P.P. and Gao, L. and Song, J.K. and Shen, H.T.",
TITLE = "Skip Tuning: Pre-trained Vision-Language Models are Effective and
Efficient Adapters Themselves",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14723-14732",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232822"}
@inproceedings{bb237857,
AUTHOR = "Rui, S.H. and Chen, L.Z. and Tang, Z.Y. and Wang, L.L. and Liu, M. and Zhang, S.T. and Wang, X.S.",
TITLE = "Multi-modal Vision Pre-training for Medical Image Analysis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "5164-5174",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232823"}
@inproceedings{bb237858,
AUTHOR = "Wang, H.C. and Ju, C. and Lin, W.X. and Xiao, S. and Chen, M.T. and Huang, Y.X. and Liu, C. and Yao, M. and Lan, J.S. and Chen, Y. and Liu, Q.W. and Wang, Y.F.",
TITLE = "Advancing Myopia To Holism:
Fully Contrastive Language-Image Pre-training",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29791-29802",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232824"}
@inproceedings{bb237859,
AUTHOR = "Wang, Z. and Lee, G.H.",
TITLE = "g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14191-14202",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232825"}
@inproceedings{bb237860,
AUTHOR = "Kim, S. and Xiao, R. and Georgescu, M.I. and Alaniz, S. and Akata, Z.",
TITLE = "COSMOS: Cross-Modality Self-Distillation for Vision Language
Pre-training",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14690-14700",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232826"}
@inproceedings{bb237861,
AUTHOR = "Gallagher Syed, A. and Senior, H. and Alwazzan, O. and Pontarini, E. and Bombardieri, M. and Pitzalis, C. and Lewis, M.J. and Barnes, M.R. and Rossi, L. and Slabaugh, G.",
TITLE = "BioX-CPath: Biologically-driven Explainable Diagnostics for
Multistain IHC Computational Pathology",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "10372-10383",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232827"}
@inproceedings{bb237862,
AUTHOR = "Wen, C.S. and Peng, Z.L. and Huang, Y. and Yang, X.K. and Shen, W.",
TITLE = "Domain Generalization in CLIP via Learning with Diverse Text Prompts",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "9559-9569",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232828"}
@inproceedings{bb237863,
AUTHOR = "Xing, S. and Zhao, Z.Y. and Sebe, N.",
TITLE = "CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards
Zero-shot Adversarial Robustness of CLIP",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "15172-15182",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232829"}
@inproceedings{bb237864,
AUTHOR = "Asokan, M. and Wu, K. and Albreiki, F.",
TITLE = "FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with
Longer Text Inputs",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14495-14504",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232830"}
@inproceedings{bb237865,
AUTHOR = "Yang, Y.H. and Deng, J.H. and Li, W. and Duan, L.X.",
TITLE = "ResCLIP: Residual Attention for Training-free Dense Vision-language
Inference",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29968-29978",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232831"}
@inproceedings{bb237866,
AUTHOR = "Xie, S. and Kong, L. and Zheng, Y.J. and Yao, Y. and Tang, Z. and Xing, E.P. and Chen, G.Y. and Zhang, K.",
TITLE = "SmartCLIP: Modular Vision-language Alignment with Identification
Guarantees",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29780-29780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232832"}
@inproceedings{bb237867,
AUTHOR = "Wang, Z. and Zhou, S. and He, S.X. and Huang, H.F. and Yang, L. and Zhang, Z. and Cheng, X.Z. and Ji, S.P. and Jin, T. and Zhao, H.S. and Zhao, Z.",
TITLE = "SpatialCLIP: Learning 3D-aware Image Representations from Spatially
Discriminative Language",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29656-29666",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232833"}
@inproceedings{bb237868,
AUTHOR = "Chen, S.X. and Sra, M. and Sen, P.",
TITLE = "Instruct-CLIP: Improving Instruction-Guided Image Editing with
Automated Data Refinement Using Contrastive Learning",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28513-28522",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232834"}
@inproceedings{bb237869,
AUTHOR = "Feng, Y.H. and Wen, C.S. and Peng, Z.L. and Jiaye, L. and Zhu, S.",
TITLE = "Retaining Knowledge and Enhancing Long-Text Representations in CLIP
through Dual-Teacher Distillation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24895-24904",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232835"}
@inproceedings{bb237870,
AUTHOR = "Pei, G. and Chen, T. and Wang, Y.J. and Cai, X.H. and Shu, X.B. and Zhou, T.F. and Yao, Y.Z.",
TITLE = "Seeing What Matters: Empowering CLIP with Patch
Generation-to-Selection",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24862-24872",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232836"}
@inproceedings{bb237871,
AUTHOR = "Wang, E. and Peng, Z. and Xie, Z.Y. and Yang, F. and Liu, X.L. and Cheng, M.M.",
TITLE = "GET: Unlocking the Multi-modal Potential of CLIP for Generalized
Category Discovery",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "20296-20306",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232837"}
@inproceedings{bb237872,
AUTHOR = "Wu, C.E. and Lin, J.H. and Hu, Y.H. and Morgado, P.",
TITLE = "Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5842-5851",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232838"}
@inproceedings{bb237873,
AUTHOR = "Kravets, A. and Namboodiri, V.P.",
TITLE = "Zero-Shot Class Unlearning in CLIP with Synthetic Samples",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6456-6464",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232839"}
@inproceedings{bb237874,
AUTHOR = "Hakim, G.A.V. and Osowiechi, D. and Noori, M. and Cheraghalikhani, M. and Bahri, A. and Yazdanpanah, M. and Ben Ayed, I. and Desrosiers, C.",
TITLE = "CLIPArTT: Adaptation of CLIP to New Domains at Test Time",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "7092-7101",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232840"}
@inproceedings{bb237875,
AUTHOR = "Cao, A.Q. and Jaritz, M. and Guillaumin, M. and de Charette, R. and Bazzani, L.",
TITLE = "LATTECLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5030-5040",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232841"}
@inproceedings{bb237876,
AUTHOR = "Song, Y. and Cho, S.",
TITLE = "Leveraging CLIP Encoder for Multimodal Emotion Recognition",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6115-6124",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232842"}
@inproceedings{bb237877,
AUTHOR = "Jiang, H.Y. and Cheng, Z.Q. and Moreira, G. and Zhu, J. and Sun, J.D. and Ren, B. and He, J.Y. and Dai, Q. and Hua, X.S.",
TITLE = "UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language
Models for Universal Cross-Domain Retrieval",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5429-5438",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232843"}
@inproceedings{bb237878,
AUTHOR = "Kim, D. and Jo, Y.J. and Lee, M. and Kim, T.",
TITLE = "Retaining and Enhancing Pre-trained Knowledge in Vision-Language
Models with Prompt Ensembling",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5550-5559",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232844"}
@inproceedings{bb237879,
AUTHOR = "Ruan, S. and Dong, Y.P. and Liu, H.Q. and Huang, Y. and Su, H. and Wei, X.X.",
TITLE = "Omniview-tuning: Boosting Viewpoint Invariance of Vision-language
Pre-training Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXVI: 309-327",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232845"}
@inproceedings{bb237880,
AUTHOR = "Bhalgat, Y. and Laina, I. and Henriques, J.F. and Zisserman, A. and Vedaldi, A.",
TITLE = "N2F2: Hierarchical Scene Understanding with Nested Neural Feature
Fields",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LIX: 197-214",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232846"}
@inproceedings{bb237881,
AUTHOR = "An, X. and Yang, K.C. and Dai, X.Z. and Feng, Z. and Deng, J.K.",
TITLE = "Multi-label Cluster Discrimination for Visual Representation Learning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXVII: 428-444",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232847"}
@inproceedings{bb237882,
AUTHOR = "Chen, W. and Shi, C.Y. and Ma, C.X. and Li, W.H. and Dong, S.",
TITLE = "DepthBLIP-2: Leveraging Language to Guide BLIP-2 in Understanding Depth
Information",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "VII: 287-302",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232848"}
@inproceedings{bb237883,
AUTHOR = "Zhou, Y. and Wu, Y.J. and Saiyin, J. and Wei, B.Z. and Lai, M. and Chang, E. and Xu, Y.",
TITLE = "SDPT: Synchronous Dual Prompt Tuning for Fusion-based Visual-language
Pre-trained Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIX: 340-356",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232849"}
@inproceedings{bb237884,
AUTHOR = "Naeem, M.F. and Xian, Y.Q. and Zhai, X.H. and Hoyer, L. and Van Gool, L.J. and Tombari, F.",
TITLE = "Silc: Improving Vision Language Pretraining with Self-distillation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXI: 38-55",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232850"}
@inproceedings{bb237885,
AUTHOR = "Chen, Q. and Hong, Y.",
TITLE = "Medblip: Bootstrapping Language-image Pretraining from 3d Medical
Images and Texts",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 98-113",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232851"}
@inproceedings{bb237886,
AUTHOR = "Zheng, K. and Zhang, Y.F. and Wu, W. and Lu, F. and Ma, S. and Jin, X. and Chen, W. and Shen, Y.J.",
TITLE = "Dreamlip: Language-image Pre-training with Long Captions",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVIII: 73-90",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232852"}
@inproceedings{bb237887,
AUTHOR = "Zhuang, J. and Hu, J.Q. and Mu, L. and Hu, R. and Liang, X.Y. and Ye, J. and Hu, H.J.",
TITLE = "FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-shot
Performance",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "X: 236-253",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232853"}
@inproceedings{bb237888,
AUTHOR = "Yang, Q. and Ye, M. and Tao, D.C.",
TITLE = "Synergy of Sight and Semantics: Visual Intention Understanding with
CLIP",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XI: 144-160",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232854"}
@inproceedings{bb237889,
AUTHOR = "Lu, Z.Q. and Shen, F.L. and Liu, M. and Yu, Y.L. and Li, X.",
TITLE = "Improving Zero-shot Generalization for CLIP with Variational Adapter",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XX: 328-344",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232855"}
@inproceedings{bb237890,
AUTHOR = "Wang, F. and Mei, J. and Yuille, A.L.",
TITLE = "SCLIP: Rethinking Self-attention for Dense Vision-language Inference",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXI: 315-332",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232856"}
@inproceedings{bb237891,
AUTHOR = "Lan, M.C. and Chen, C.F. and Ke, Y.P. and Wang, X.J. and Feng, L. and Zhang, W.",
TITLE = "ClearCLIP: Decomposing CLIP Representations for Dense Vision-language
Inference",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLVII: 143-160",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232857"}
@inproceedings{bb237892,
AUTHOR = "Zhang, B.C. and Zhang, P. and Dong, X.Y. and Zang, Y.H. and Wang, J.Q.",
TITLE = "Long-CLIP: Unlocking the Long-text Capability of CLIP",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LI: 310-325",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232858"}
@inproceedings{bb237893,
AUTHOR = "Poppi, S. and Poppi, T. and Cocchi, F. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
TITLE = "Safe-CLIP: Removing NSFW Concepts from Vision-and-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LIII: 340-356",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232859"}
@inproceedings{bb237894,
AUTHOR = "Huang, L. and Cao, X. and Lu, H. and Liu, X.L.",
TITLE = "Class-incremental Learning with CLIP: Adaptive Representation
Adjustment and Parameter Fusion",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LIV: 214-231",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232860"}
@inproceedings{bb237895,
AUTHOR = "Lai, Z.F. and Zhang, H.T. and Zhang, B. and Wu, W.T. and Bai, H. and Timofeev, A. and Du, X.Z. and Gan, Z. and Shan, J. and Chuah, C.N. and Yang, Y.F. and Cao, M.",
TITLE = "VECLIP: Improving CLIP Training via Visual-enriched Captions",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLII: 111-127",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232861"}
@inproceedings{bb237896,
AUTHOR = "Qian, Q. and Hu, J.",
TITLE = "Online Zero-shot Classification with CLIP",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXVII: 462-477",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232862"}
@inproceedings{bb237897,
AUTHOR = "Balauca, A.A. and Paudel, D.P. and Toutanova, K. and Van Gool, L.J.",
TITLE = "Taming CLIP for Fine-grained and Structured Visual Understanding of
Museum Exhibits",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXVI: 377-394",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232863"}
@inproceedings{bb237898,
AUTHOR = "Abbasi, R. and Rohban, M.H. and Baghshah, M.S.",
TITLE = "Deciphering the Role of Representation Disentanglement:
Investigating Compositional Generalization in CLIP Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXIX: 35-50",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232864"}
@inproceedings{bb237899,
AUTHOR = "Li, Y. and Guo, W.W. and Yang, X. and Liao, N. and He, D. and Zhou, J.Q. and Yu, W.X.",
TITLE = "Toward Open Vocabulary Aerial Object Detection with CLIP-activated
Student-teacher Learning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXVI: 431-448",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT232865"}
Last update:Nov 26, 2025 at 20:24:09