@article{bb248800,
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#TT243692"}
@article{bb248801,
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#TT243693"}
@inproceedings{bb248802,
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#TT243694"}
@inproceedings{bb248803,
AUTHOR = "Dahal, A. and Murad, S.A. and Rahimi, N.",
TITLE = "Embedding Shift Dissection on CLIP: Effects of Augmentations on VLM's
Representation Learning",
BOOKTITLE = InterpVis25,
YEAR = "2025",
PAGES = "4814-4818",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243695"}
@article{bb248804,
AUTHOR = "Song, T.C. and Liu, Q. and Qin, A. and Liu, Y.",
TITLE = "RotCLIP: Tuning CLIP with Visual Adapter and Textual Prompts for
Rotation Robust Remote Sensing Image Classification",
JOURNAL = SP:IC,
VOLUME = "140",
YEAR = "2026",
PAGES = "117407",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243696"}
@article{bb248805,
AUTHOR = "Gao, X. and Chang, Z.B. and Kong, D. and Zhou, H.Y. and Lu, Y.G.",
TITLE = "MIP-CLIP: Multimodal Independent Prompt CLIP for Action Recognition",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "9918-9930",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243697"}
@article{bb248806,
AUTHOR = "Yang, Q. and Ye, M. and Tao, D.C.",
TITLE = "Synergy of Sight and Semantics: Holistic Visual Understanding With
CLIP",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "3119-3136",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243698"}
@inproceedings{bb248807,
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#TT243699"}
@article{bb248808,
AUTHOR = "Li, M.W. and Wang, Z. and Zhang, Y.X.",
TITLE = "Improving Zero-Shot Generalization for CLIP With Prompt Ensemble
Self-Distillation",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "2304-2317",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243700"}
@article{bb248809,
AUTHOR = "Peng, Z.Q. and Qi, Z.Y. and Cao, Y. and Kang, Y. and Lv, W.J.",
TITLE = "Modeling Cross-Modal Semantic Transformations From Coarse to Fine in
CLIP",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "2164-2176",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243701"}
@article{bb248810,
AUTHOR = "Li, Y. and Guo, W.W. and Yang, X. and Liao, N. and Zhang, S.F. and Yu, Y. and Yu, W.X. and Yan, J.C.",
TITLE = "Exploiting Unlabeled Data with Multiple Expert Teachers for Open
Vocabulary Aerial Object Detection and Its Orientation Adaptation",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "4",
MONTH = "April",
PAGES = "156",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243702"}
@inproceedings{bb248811,
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#TT243703"}
@article{bb248812,
AUTHOR = "Park, J.Y. and Ko, J. and Lee, S. and Choi, J. and Kim, H.W.J.",
TITLE = "Parameter-Efficient Fine-Tuning via Meta-Regularizer",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "4",
MONTH = "April",
PAGES = "148",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243704"}
@article{bb248813,
AUTHOR = "Liang, C. and Wang, S.G. and Zhang, B.B.",
TITLE = "M2-CLIP++: Dual-branch high-order vision-language adaptation with
dynamic semantic prompting for efficient video recognition",
JOURNAL = CVIU,
VOLUME = "267",
YEAR = "2026",
PAGES = "104708",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243705"}
@article{bb248814,
AUTHOR = "Wu, J.Y. and Han, X.H. and Cao, L. and Tian, Y. and Yuan, D. and Cheng, L.L.",
TITLE = "DualAdapt: A simple parallel framework makes CLIP-based Few-shot
Learning classifier see better",
JOURNAL = JVCIR,
VOLUME = "117",
YEAR = "2026",
PAGES = "104782",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243706"}
@article{bb248815,
AUTHOR = "Choi, H. and Jang, Y.K. and Eom, C.",
TITLE = "FAST-GOAL: Fast and Efficient Global-Local Object Alignment Learning",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "5181-5195",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243707"}
@inproceedings{bb248816,
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#TT243708"}
@article{bb248817,
AUTHOR = "Li, Z.X. and Wang, W.X. and Liu, C. and He, J. and Zhao, Y. and Zhai, Y. and Tang, R.",
TITLE = "Symptom-Aware Adaptation of CLIP for Few-Shot Medical Image
Classification",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "1701-1705",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243709"}
@article{bb248818,
AUTHOR = "Xu, L.L. and Xie, H.R. and Qin, S.J. and Tao, X.H. and Wang, F.L.",
TITLE = "Parameter-Efficient Fine-Tuning Methods for Pretrained Language
Models: A Critical Review and Assessment",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "6",
MONTH = "June",
PAGES = "6107-6126",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243710"}
@article{bb248819,
AUTHOR = "Yu, L. and Zhang, H.Y. and Xu, C.S.",
TITLE = "Complementary Text-Guided Attention for Zero-Shot Adversarial
Robustness",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "7",
MONTH = "July",
PAGES = "8185-8198",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243711"}
@article{bb248820,
AUTHOR = "Zhang, H.Q. and Li, Z.Q. and Tang, H. and Li, Z.C.",
TITLE = "Trajectory-enhanced transferable attacks for vision-language
pre-trained models",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113571",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243712"}
@article{bb248821,
AUTHOR = "Huang, H. and Huo, Y.Q. and Zhao, Z. and Lu, H.Y. and Wu, S. and Wang, B. and Liu, Q. and Chen, W.P. and Wang, L.",
TITLE = "AITQE: An Adaptive Image-Text Quality Enhancer for Scalable MLLM
Pretraining",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "6",
MONTH = "June",
PAGES = "7833-7845",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243713"}
@article{bb248822,
AUTHOR = "Ren, K. and Du, Y.T. and Xu, L. and Yao, Y.X. and Han, W. and Jin, L. and Wang, L.",
TITLE = "CE-CLIP: Cloud-edge collaborative fine-tuning for multimodal
adaptation",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113846",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243714"}
@article{bb248823,
AUTHOR = "Pan, J.Y. and Wan, C. and Chen, W. and Huang, L.F.",
TITLE = "Semantic Region-Guided Transferable Attacks on Vision-Language
Pretraining Models",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2380-2384",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243715"}
@article{bb248824,
AUTHOR = "Yang, W.Y. and Sun, Y.C. and Chen, C.Z. and Chu, Z.X. and Zhang, J.H. and Li, Y.M. and Tao, D.C.",
TITLE = "SWAP: Towards Copyright Auditing of Soft Prompts via Sequential
Watermarking",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "7",
MONTH = "July",
PAGES = "319",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243716"}
@article{bb248825,
AUTHOR = "Ding, Y. and Jiang, B. and Zheng, A. and Xu, Q. and Liang, J.",
TITLE = "Ranking Vision-Language Models in Fully Unlabeled Tasks",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "4562-4571",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243717"}
@article{bb248826,
AUTHOR = "Yang, Q.S. and Li, W.Y. and Peng, Z. and Cheng, F.X. and Yuan, Y.X.",
TITLE = "MRM++: Enhanced Masked Relation Modeling for Multi-Modal Medical
Pre-training",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "8",
MONTH = "August",
PAGES = "355",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243718"}
@inproceedings{bb248827,
AUTHOR = "Yang, Q.S. and Li, W.Y. and Li, B. and Yuan, Y.X.",
TITLE = "MRM: Masked Relation Modeling for Medical Image Pre-Training with
Genetics",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "21395-21405",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243719"}
@article{bb248828,
AUTHOR = "Lin, Z.X. and Zhou, G.X. and Huang, H.N. and Huang, Z.H. and Zhao, Q. and Xie, S.L.",
TITLE = "Redundancy-Aware External Signal Learning for Image Clustering",
JOURNAL = SMCS,
VOLUME = "56",
YEAR = "2026",
NUMBER = "9",
MONTH = "September",
PAGES = "4984-4997",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243720"}
@article{bb248829,
AUTHOR = "Lu, H.Y. and Zhang, M.M. and Liu, Z. and Jing, H.Y.",
TITLE = "CLIP Distillation for Cross-Domain Traffic Scene Adaptation",
JOURNAL = ITS,
VOLUME = "27",
YEAR = "2026",
NUMBER = "9",
MONTH = "September",
PAGES = "11165-11176",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243721"}
@article{bb248830,
AUTHOR = "Ge, H.L. and Zhao, Y.X. and Lv, Z.W. and Yang, X.",
TITLE = "DCAF: Decoupled Cache Adaptation and Auxiliary Logit Fusion for
few-shot CLIP",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114382",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243722"}
@article{bb248831,
AUTHOR = "Wang, C. and Liu, F. and Liu, Y. and Chen, Y.H. and Tian, Y. and Fang, L.Y.",
TITLE = "MedCure: Medical Data Curation for Efficient Vision-Language
Pretraining",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "9744-9756",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243723"}
@inproceedings{bb248832,
AUTHOR = "Jeong, S. and Chen, H. and Yun, S.G. and Cho, S. and Huang, W.J. and Liu, X.J. and Imani, M.",
TITLE = "Cross-Modal Event Encoder: Bridging Image-Text Knowledge to Event
Streams",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "3213-3222",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243724"}
@inproceedings{bb248833,
AUTHOR = "Eyiokur, F.I. and Yaman, D. and Ekenel, H.K. and Waibel, A.",
TITLE = "CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues
for Embodied Reference Understanding",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "3939-3950",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243725"}
@inproceedings{bb248834,
AUTHOR = "Vu, J. and Sheshappanavar, S.",
TITLE = "Improving Negation Understanding in Medical Vision-Language Models
via Contrastive Fine-Tuning",
BOOKTITLE = CVClinical26,
YEAR = "2026",
PAGES = "395-404",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243726"}
@inproceedings{bb248835,
AUTHOR = "Fahes, M. and Vu, T.H. and Bursuc, A. and Perez, P. and de Charette, R.",
TITLE = "CLIP's Visual Embedding Projector is a Few-shot Cornucopia",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "3254-3264",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243727"}
@inproceedings{bb248836,
AUTHOR = "Quetin, S. and Ghosh, T. and Maleki, F.",
TITLE = "Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training
Improves Dense Prediction",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "1000-1010",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243728"}
@inproceedings{bb248837,
AUTHOR = "Liang, M.L. and Larson, M.",
TITLE = "Frequency Is What You Need: Considering Word Frequency When Text
Masking Benefits Vision-Language Model Pre-training",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "3771-3780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243729"}
@inproceedings{bb248838,
AUTHOR = "Pham, P. and Pham, N. and Ly, N.Q.",
TITLE = "Boosting Medical Vision-Language Pretraining via Momentum
Self-Distillation under Limited Computing Resources",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "860-868",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243730"}
@inproceedings{bb248839,
AUTHOR = "Zohra, F. and Zhao, C. and Liu, S.M. and Ghanem, B.",
TITLE = "Effectiveness of Max-Pooling for Fine-Tuning CLIP on Videos",
BOOKTITLE = LargeVM25,
YEAR = "2025",
PAGES = "3282-3291",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243731"}
@inproceedings{bb248840,
AUTHOR = "Patel, C. and Niebles, J.C. and Adeli, E.",
TITLE = "AdaVid: Adaptive Video-Language Pretraining",
BOOKTITLE = EDGE25,
YEAR = "2025",
PAGES = "6379-6388",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243732"}
@inproceedings{bb248841,
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#TT243733"}
@inproceedings{bb248842,
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#TT243734"}
@inproceedings{bb248843,
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#TT243735"}
@inproceedings{bb248844,
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#TT243736"}
@inproceedings{bb248845,
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#TT243737"}
@inproceedings{bb248846,
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#TT243738"}
@inproceedings{bb248847,
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#TT243739"}
@inproceedings{bb248848,
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#TT243740"}
@inproceedings{bb248849,
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#TT243741"}
@inproceedings{bb248850,
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#TT243742"}
@inproceedings{bb248851,
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#TT243743"}
@inproceedings{bb248852,
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#TT243744"}
@inproceedings{bb248853,
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#TT243745"}
@inproceedings{bb248854,
AUTHOR = "Xie, S. and Kong, L.J. 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#TT243746"}
@inproceedings{bb248855,
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#TT243747"}
@inproceedings{bb248856,
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#TT243748"}
@inproceedings{bb248857,
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#TT243749"}
@inproceedings{bb248858,
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#TT243750"}
@inproceedings{bb248859,
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#TT243751"}
@inproceedings{bb248860,
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#TT243752"}
@inproceedings{bb248861,
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#TT243753"}
@inproceedings{bb248862,
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#TT243754"}
@inproceedings{bb248863,
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#TT243755"}
@inproceedings{bb248864,
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#TT243756"}
@inproceedings{bb248865,
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#TT243757"}
@inproceedings{bb248866,
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#TT243758"}
@inproceedings{bb248867,
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#TT243759"}
@inproceedings{bb248868,
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#TT243760"}
@inproceedings{bb248869,
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#TT243761"}
@inproceedings{bb248870,
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#TT243762"}
@inproceedings{bb248871,
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#TT243763"}
@inproceedings{bb248872,
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#TT243764"}
@inproceedings{bb248873,
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#TT243765"}
@inproceedings{bb248874,
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#TT243766"}
@inproceedings{bb248875,
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#TT243767"}
@inproceedings{bb248876,
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#TT243768"}
@inproceedings{bb248877,
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#TT243769"}
@inproceedings{bb248878,
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#TT243770"}
@inproceedings{bb248879,
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#TT243771"}
@inproceedings{bb248880,
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#TT243772"}
@inproceedings{bb248881,
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#TT243773"}
@inproceedings{bb248882,
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#TT243774"}
@inproceedings{bb248883,
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#TT243775"}
@inproceedings{bb248884,
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#TT243776"}
@inproceedings{bb248885,
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#TT243777"}
@inproceedings{bb248886,
AUTHOR = "Du, Y. and Zhai, Q. and Dai, W.H. and Li, X.M.",
TITLE = "Teach CLIP to Develop a Number Sense for Ordinal Regression",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXV: 1-17",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243778"}
@inproceedings{bb248887,
AUTHOR = "Jo, S. and Ryu, S. and Kim, S. and Yang, E. and Kim, K.",
TITLE = "TTD: Text-tag Self-distillation Enhancing Image-text Alignment in CLIP
to Alleviate Single Tag Bias",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXI: 341-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243779"}
@inproceedings{bb248888,
AUTHOR = "Lu, S. and Jiao, J. and Wang, L.X. and Qiu, H.Q. and Lin, X.T. and Mei, H. and Li, H.L.",
TITLE = "Video Class-Incremental Learning with CLIP Based Transformer",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "500-506",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243780"}
@inproceedings{bb248889,
AUTHOR = "Chen, Y.C. and Li, W.H. and Chen, C.S.",
TITLE = "Open-Vocabulary Panoptic Segmentation Using Bert Pre-Training of
Vision-Language Multiway Transformer Model",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "2494-2500",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243781"}
@inproceedings{bb248890,
AUTHOR = "Yi, C. and Ren, L. and Zhan, D.C. and Ye, H.J.",
TITLE = "Leveraging Cross-Modal Neighbor Representation for Improved CLIP
Classification",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27392-27401",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243782"}
@inproceedings{bb248891,
AUTHOR = "Byun, J. and Kim, D. and Moon, T.",
TITLE = "MAFA: Managing False Negatives for Vision-Language Pre-Training",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27304-27314",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243783"}
@inproceedings{bb248892,
AUTHOR = "Wei, Z. and Pan, Z.X. and Owens, A.",
TITLE = "Efficient Vision-Language Pre-Training by Cluster Masking",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26805-26815",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243784"}
@inproceedings{bb248893,
AUTHOR = "Wang, S. and Zhang, J. and Yuan, Z. and Shan, S.G.",
TITLE = "Pre-Trained Model Guided Fine-Tuning for Zero-Shot Adversarial
Robustness",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24502-24511",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243785"}
@inproceedings{bb248894,
AUTHOR = "Lee, J.H. and Kang, J.W.",
TITLE = "SRTube: Video-Language Pre-Training with Action-Centric Video Tube
Features and Semantic Role Labeling",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13689-13699",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243786"}
@inproceedings{bb248895,
AUTHOR = "Gao, Y. and Shi, K.Y. and Zhu, P.K. and Belval, E. and Nuriel, O. and Appalaraju, S. and Ghadar, S. and Tu, Z.W. and Mahadevan, V. and Soatto, S.",
TITLE = "Enhancing Vision-Language Pre-Training with Rich Supervisions",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13480-13491",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243787"}
@inproceedings{bb248896,
AUTHOR = "Bulat, A. and Ouali, Y. and Tzimiropoulos, G.",
TITLE = "FFF: Fixing Flawed Foundations in contrastive pre-training results in
very strong Vision-Language models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14172-14182",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243788"}
@inproceedings{bb248897,
AUTHOR = "Shao, S. and Bai, Y. and Wang, Y. and Liu, B. and Zhou, Y.C.",
TITLE = "DeIL: Direct-and-Inverse CLIP for Open-World Few-Shot Learning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28505-28514",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243789"}
@inproceedings{bb248898,
AUTHOR = "Martin, S. and Huang, Y. and Shakeri, F. and Pesquet, J.C. and Ayed, I.B.",
TITLE = "Transductive Zero-Shot and Few-Shot CLIP",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28816-28826",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243790"}
@inproceedings{bb248899,
AUTHOR = "Xing, X. and Xiong, Z. and Stylianou, A. and Sastry, S. and Gong, L. and Jacobs, N.",
TITLE = "Vision-Language Pseudo-Labels for Single-Positive Multi-Label
Learning",
BOOKTITLE = ZeroShot24,
YEAR = "2024",
PAGES = "7799-7808",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT243791"}
Last update:Oct 8, 2026 at 11:03:09