@article{bb236200,
        AUTHOR = "Feng, G. and Zhang, L. and Sun, J. and Hu, Z.W. and Lu, H.C.",
        TITLE = "Referring Segmentation via Encoder-Fused Cross-Modal Attention
Network",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "7654-7667",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231175"}

@inproceedings{bb236201,
        AUTHOR = "Feng, G. and Hu, Z.W. and Zhang, L. and Lu, H.C.",
        TITLE = "Encoder Fusion Network with Co-Attention Embedding for Referring
Image Segmentation",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "15501-15510",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231176"}

@article{bb236202,
        AUTHOR = "Liu, D.Z. and Zhou, P. and Xu, Z. and Wang, H.Z. and Li, R.X.",
        TITLE = "Few-Shot Temporal Sentence Grounding via Memory-Guided Semantic
Learning",
        JOURNAL = CirSysVideo,
        VOLUME = "33",
        YEAR = "2023",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "2491-2505",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231177"}

@article{bb236203,
        AUTHOR = "Sun, M.J. and Xiao, J. and Lim, E.G. and Zhao, Y.",
        TITLE = "Cycle-Free Weakly Referring Expression Grounding With Self-Paced
Learning",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "1611-1621",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231178"}

@article{bb236204,
        AUTHOR = "Sun, M.Y. and Suo, W. and Wang, P. and Zhang, Y.N. and Wu, Q.",
        TITLE = "A Proposal-Free One-Stage Framework for Referring Expression
Comprehension and Generation via Dense Cross-Attention",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "2446-2458",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231179"}

@article{bb236205,
        AUTHOR = "Sun, Y.F. and Zhang, Y. and Jiang, H. and Hu, Y.L. and Yin, B.C.",
        TITLE = "Multi-level attention for referring expression comprehension",
        JOURNAL = PRL,
        VOLUME = "172",
        YEAR = "2023",
        PAGES = "252-258",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231180"}

@article{bb236206,
        AUTHOR = "Wang, R. and Tang, Z. and Zhou, Q.L. and Liu, X.Q. and Hui, T.R. and Tan, Q. and Liu, S.",
        TITLE = "Unified Transformer with Isomorphic Branches for Natural Language
Tracking",
        JOURNAL = CirSysVideo,
        VOLUME = "33",
        YEAR = "2023",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "4529-4541",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231181"}

@article{bb236207,
        AUTHOR = "Li, H. and Sun, M.J. and Xiao, J. and Lim, E.G. and Zhao, Y.",
        TITLE = "Fully and Weakly Supervised Referring Expression Segmentation With
End-to-End Learning",
        JOURNAL = CirSysVideo,
        VOLUME = "33",
        YEAR = "2023",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "5999-6012",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231182"}

@article{bb236208,
        AUTHOR = "Liu, C. and Jiang, X.D. and Ding, H.H.",
        TITLE = "Instance-Specific Feature Propagation for Referring Segmentation",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "3657-3667",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231183"}

@article{bb236209,
        AUTHOR = "Song, Y.Z. and Chen, Y.S. and Shuai, H.H.",
        TITLE = "Decoupling-Cooperative Framework for Referring Expression
Comprehension",
        JOURNAL = SPLetters,
        VOLUME = "30",
        YEAR = "2023",
        PAGES = "1542-1546",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231184"}

@article{bb236210,
        AUTHOR = "Hua, G.G. and Liao, M. and Tian, S. and Zhang, Y.H. and Zou, W.B.",
        TITLE = "Multiple Relational Learning Network for Joint Referring Expression
Comprehension and Segmentation",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "8805-8816",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231185"}

@article{bb236211,
        AUTHOR = "Wang, W.B. and Pagnucco, M. and Xu, C.P. and Song, Y.",
        TITLE = "InterREC: An Interpretable Method for Referring Expression
Comprehension",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "9330-9342",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231186"}

@article{bb236212,
        AUTHOR = "Ke, J.C. and Wang, J. and Chen, J.C. and Jhuo, I.H. and Lin, C.W. and Lin, Y.Y.",
        TITLE = "CLIPREC: Graph-Based Domain Adaptive Network for Zero-Shot Referring
Expression Comprehension",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "2480-2492",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231187"}

@article{bb236213,
        AUTHOR = "Ke, J.C. and Wang, J. and Wong, W.K. and Toomey, A. and Wen, J.",
        TITLE = "Graph-Based Group Division Network for Referring Expression
Comprehension",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "6170-6183",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231188"}

@article{bb236214,
        AUTHOR = "Li, X.C. and Fan, B.Y. and Zhang, R.Z. and Zhao, K. and Guo, Z.H. and Zhao, Y.Q. and Li, R.",
        TITLE = "Inexactly Matched Referring Expression Comprehension With Rationale",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "3937-3950",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231189"}

@article{bb236215,
        AUTHOR = "Luo, G. and Zhou, Y.Y. and Sun, J. and Sun, X.S. and Ji, R.R.",
        TITLE = "A Survivor in the Era of Large-Scale Pretraining: An Empirical Study
of One-Stage Referring Expression Comprehension",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "3689-3700",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231190"}

@article{bb236216,
        AUTHOR = "Miao, P.H. and Su, W. and Wang, G.A. and Li, X.W. and Xi, L.",
        TITLE = "Self-Paced Multi-Grained Cross-Modal Interaction Modeling for
Referring Expression Comprehension",
        JOURNAL = IP,
        VOLUME = "33",
        YEAR = "2024",
        PAGES = "1497-1507",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231191"}

@article{bb236217,
        AUTHOR = "Liu, Z.T. and Xu, T.Y. and Song, X.N. and Wu, X.J.",
        TITLE = "Unified Referring Expression Generation for Bounding Boxes and
Segmentations",
        JOURNAL = SPLetters,
        VOLUME = "31",
        YEAR = "2024",
        PAGES = "636-640",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231192"}

@article{bb236218,
        AUTHOR = "Zhang, Y.J. and Li, Q.Z. and Pan, Y. and Zhao, X.G. and Tan, M.",
        TITLE = "Multi-Stage Image-Language Cross-Generative Fusion Network for
Video-Based Referring Expression Comprehension",
        JOURNAL = IP,
        VOLUME = "33",
        YEAR = "2024",
        PAGES = "3256-3270",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231193"}

@article{bb236219,
        AUTHOR = "Lu, M.C. and Li, R.F. and Feng, F.X. and Ma, Z.Y. and Wang, X.J.",
        TITLE = "LGR-NET: Language Guided Reasoning Network for Referring Expression
Comprehension",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "7771-7784",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231194"}

@article{bb236220,
        AUTHOR = "Yao, H.B. and Wang, L.P. and Cai, C.T. and Wang, W. and Zhang, Z. and Shang, X.B.",
        TITLE = "Language conditioned multi-scale visual attention networks for visual
grounding",
        JOURNAL = IVC,
        VOLUME = "150",
        YEAR = "2024",
        PAGES = "105242",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231195"}

@article{bb236221,
        AUTHOR = "Ji, Z. and Wu, J. and Wang, Y.D. and Yang, A.P. and Han, J.G.",
        TITLE = "Progressive Semantic Reconstruction Network for Weakly Supervised
Referring Expression Grounding",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "13058-13070",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231196"}

@article{bb236222,
        AUTHOR = "Qiu, H.Q. and Wang, L.X. and Zhao, T. and Meng, F.M. and Wu, Q.B. and Li, H.L.",
        TITLE = "MCCE-REC: MLLM-Driven Cross-Modal Contrastive Entropy Model for
Zero-Shot Referring Expression Comprehension",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "754-768",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231197"}

@article{bb236223,
        AUTHOR = "Ke, J.C. and Zhang, Q. and Wang, J. and Ding, H.Q. and Zhang, P.F. and Wen, J.",
        TITLE = "Graph-based referring expression comprehension with expression-guided
selective filtering and noun-oriented reasoning",
        JOURNAL = PR,
        VOLUME = "161",
        YEAR = "2025",
        PAGES = "111222",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231198"}

@article{bb236224,
        AUTHOR = "Ke, J.C. and Wang, D. and Chen, J.C. and Jhuo, I.H. and Lin, C.W. and Lin, Y.Y.",
        TITLE = "Make Graph-Based Referring Expression Comprehension Great Again
Through Expression-Guided Dynamic Gating and Regression",
        JOURNAL = MultMed,
        VOLUME = "27",
        YEAR = "2025",
        PAGES = "1950-1961",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231199"}

@article{bb236225,
        AUTHOR = "Huang, S.J. and Li, F. and Zhang, H. and Liu, S.L. and Zhang, L. and Wang, L.W.",
        TITLE = "A Mutual Supervision Framework for Referring Expression Segmentation
and Generation",
        JOURNAL = IJCV,
        VOLUME = "133",
        YEAR = "2025",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "Psges 3597-3612",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231200"}

@article{bb236226,
        AUTHOR = "Ke, X. and Xu, P. and Guo, W.Z.",
        TITLE = "Language-Image Consistency Augmentation and Distillation Network for
visual grounding",
        JOURNAL = PR,
        VOLUME = "166",
        YEAR = "2025",
        PAGES = "111663",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231201"}

@article{bb236227,
        AUTHOR = "Yang, X.Z. and Liu, J.Z. and Wang, P. and Wang, G.Q. and Yang, Y. and Shen, H.T.",
        TITLE = "New Dataset and Methods for Fine-Grained Compositional Referring
Expression Comprehension via Specialist-MLLM Collaboration",
        JOURNAL = PAMI,
        VOLUME = "47",
        YEAR = "2025",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "8598-8612",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231202"}

@inproceedings{bb236228,
        AUTHOR = "Wang, Z.C. and Pan, Z.Y. and Peng, Z. and Cheng, J. and Xiao, L.W. and Jiang, W. and Cao, Z.G.",
        TITLE = "Exploring Contextual Attribute Density in Referring Expression
Counting",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "19587-19596",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231203"}

@inproceedings{bb236229,
        AUTHOR = "Chen, X. and Luo, Y.X. and Luo, G. and Ji, J.Y. and Ding, H.H. and Zhou, Y.",
        TITLE = "DViN: Dynamic Visual Routing Network for Weakly Supervised Referring
Expression Comprehension",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "14347-14357",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231204"}

@inproceedings{bb236230,
        AUTHOR = "Wang, S.J. and Kim, D. and Taalimi, A. and Sun, C. and Kuo, W.C.",
        TITLE = "Learning Visual Grounding from Generative Vision and Language Model",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "8057-8067",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231205"}

@inproceedings{bb236231,
        AUTHOR = "Wu, T.Y. and Huang, S.Y. and Wang, Y.C.A.F.",
        TITLE = "Data-Efficient 3D Visual Grounding via Order-Aware Referring",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "3107-3117",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231206"}

@inproceedings{bb236232,
        AUTHOR = "Chu, T.Y. and Lin, Y.X. and Huang, C.C. and Hua, K.L.",
        TITLE = "Enhancing Anchor-based Weakly Supervised Referring Expression
Comprehension with Cross-modality Attention",
        BOOKTITLE = ACCV24,
        YEAR = "2024",
        PAGES = "III: 131-147",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231207"}

@inproceedings{bb236233,
        AUTHOR = "Nag, S. and Goswami, K. and Karanam, S.",
        TITLE = "Safari: Adaptive Sequence Transformer for Weakly Supervised Referring
Expression Segmentation",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XLIV: 485-503",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231208"}

@inproceedings{bb236234,
        AUTHOR = "Dai, S.Y. and Liu, J. and Cheung, N.M.",
        TITLE = "Referring Expression Counting",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "16985-16995",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231209"}

@inproceedings{bb236235,
        AUTHOR = "Han, Z. and Zhu, F. and Lao, Q. and Jiang, H.",
        TITLE = "Zero-Shot Referring Expression Comprehension via Structural
Similarity Between Images and Captions",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "14364-14375",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231210"}

@inproceedings{bb236236,
        AUTHOR = "Su, W. and Miao, P.H. and Dou, H.Z. and Li, X.",
        TITLE = "ScanFormer: Referring Expression Comprehension by Iteratively
Scanning",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "13449-13458",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231211"}

@inproceedings{bb236237,
        AUTHOR = "Yu, Z.H. and Li, R.",
        TITLE = "Revisiting Counterfactual Problems in Referring Expression
Comprehension",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "13438-13448",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231212"}

@inproceedings{bb236238,
        AUTHOR = "Li, X. and Qiu, K. and Wang, J.L. and Xu, X.H. and Singh, R. and Yamazaki, K. and Chen, H. and Huang, X.N. and Raj, B.",
        TITLE = "R^2-Bench: Benchmarking the Robustness of Referring Perception Models
Under Perturbations",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "IX: 211-230",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231213"}

@inproceedings{bb236239,
        AUTHOR = "Chng, Y.X. and Zheng, H. and Han, Y.Z. and Qiu, X. and Huang, G.",
        TITLE = "Mask Grounding for Referring Image Segmentation",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "26563-26573",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231214"}

@inproceedings{bb236240,
        AUTHOR = "Shah, N.A. and VS, V. and Patel, V.M.",
        TITLE = "LQMFormer: Language-Aware Query Mask Transformer for Referring Image
Segmentation",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "12903-12913",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231215"}

@inproceedings{bb236241,
        AUTHOR = "Wang, W.X. and Yue, T.T. and Zhang, Y. and Guo, L.T. and He, X.J. and Wang, X.L. and Liu, J.",
        TITLE = "Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring
Expression Segmentation",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "12998-13008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231216"}

@inproceedings{bb236242,
        AUTHOR = "Wu, Y.X. and Zhang, Z. and Xie, C. and Zhu, F. and Zhao, R.",
        TITLE = "Advancing Referring Expression Segmentation Beyond Single Image",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "2628-2638",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231217"}

@inproceedings{bb236243,
        AUTHOR = "Kurita, S. and Katsura, N. and Onami, E.",
        TITLE = "RefEgo: Referring Expression Comprehension Dataset from First-Person
Perception of Ego4D",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "15168-15178",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231218"}

@inproceedings{bb236244,
        AUTHOR = "Qiao, Y. and Qi, Y.K. and Yu, Z. and Liu, J. and Wu, Q.",
        TITLE = "March in Chat: Interactive Prompting for Remote Embodied Referring
Expression",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "15712-15721",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231219"}

@inproceedings{bb236245,
        AUTHOR = "Chen, Y. and Du, R. and Liang, K.M. and Ma, Z.Y.",
        TITLE = "Self-Enhanced Training Framework for Referring Expression Grounding",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "3060-3064",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231220"}

@inproceedings{bb236246,
        AUTHOR = "Sun, J. and Luo, G. and Zhou, Y.Y. and Sun, X.S. and Jiang, G.N. and Wang, Z.Y. and Ji, R.R.",
        TITLE = "RefTeacher: A Strong Baseline for Semi-Supervised Referring
Expression Comprehension",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "19144-19154",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231221"}

@inproceedings{bb236247,
        AUTHOR = "Tang, J.J. and Zheng, G. and Shi, C. and Yang, S.",
        TITLE = "Contrastive Grouping with Transformer for Referring Image
Segmentation",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "23570-23580",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231222"}

@inproceedings{bb236248,
        AUTHOR = "Liu, J. and Ding, H. and Cai, Z.W. and Zhang, Y.T. and Satzoda, R.K. and Mahadevan, V. and Manmatha, R.",
        TITLE = "PolyFormer: Referring Image Segmentation as Sequential Polygon
Generation",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "18653-18663",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231223"}

@inproceedings{bb236249,
        AUTHOR = "Xu, L. and Huang, M.H. and Shang, X. and Yuan, Z.H. and Sun, Y. and Liu, J.",
        TITLE = "Meta Compositional Referring Expression Segmentation",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "19478-19487",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231224"}

@inproceedings{bb236250,
        AUTHOR = "Liu, C. and Ding, H.H. and Jiang, X.D.",
        TITLE = "GRES: Generalized Referring Expression Segmentation",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "23592-23601",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231225"}

@inproceedings{bb236251,
        AUTHOR = "Song, S. and Lin, X.D. and Liu, J.Y. and Guo, Z.M. and Chang, S.F.",
        TITLE = "Co-Grounding Networks with Semantic Attention for Referring
Expression Comprehension in Videos",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "1346-1355",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231226"}

@inproceedings{bb236252,
        AUTHOR = "Sun, M.J. and Xiao, J. and Lim, E.G.",
        TITLE = "Iterative Shrinking for Referring Expression Grounding Using Deep
Reinforcement Learning",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "14055-14064",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231227"}

@inproceedings{bb236253,
        AUTHOR = "Zhu, H.D. and Sadhu, A. and Zheng, Z.H. and Nevatia, R.",
        TITLE = "Utilizing Every Image Object for Semi-supervised Phrase Grounding",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "2209-2218",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231228"}

@inproceedings{bb236254,
        AUTHOR = "Wang, P. and Wu, Q. and Cao, J.W. and Shen, C.H. and Gao, L.L. and van den Hengel, A.J.",
        TITLE = "Neighbourhood Watch: Referring Expression Comprehension via
Language-Guided Graph Attention Networks",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1960-1968",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231229"}

@inproceedings{bb236255,
        AUTHOR = "Tanaka, M. and Itamochi, T. and Narioka, K. and Sato, I. and Ushiku, Y. and Harada, T.",
        TITLE = "Generating Easy-to-Understand Referring Expressions for Target
Identifications",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "5793-5802",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231230"}

@inproceedings{bb236256,
        AUTHOR = "Yang, S.B. and Li, G.B. and Yu, Y.Z.",
        TITLE = "Dynamic Graph Attention for Referring Expression Comprehension",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4643-4652",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231231"}

@inproceedings{bb236257,
        AUTHOR = "Zhang, H.W. and Niu, Y.L. and Chang, S.F.",
        TITLE = "Grounding Referring Expressions in Images by Variational Context",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4158-4166",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231232"}

@inproceedings{bb236258,
        AUTHOR = "Yu, L.C. and Lin, Z. and Shen, X.H. and Yang, J.M. and Lu, X. and Bansal, M. and Berg, T.L.",
        TITLE = "MAttNet: Modular Attention Network for Referring Expression
Comprehension",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "1307-1315",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231233"}

@inproceedings{bb236259,
        AUTHOR = "Luo, R. and Shakhnarovich, G.",
        TITLE = "Comprehension-Guided Referring Expressions",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3125-3134",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT231234"}

@article{bb236260,
        AUTHOR = "Tung, F. and Mori, G.",
        TITLE = "Deep Neural Network Compression by In-Parallel Pruning-Quantization",
        JOURNAL = PAMI,
        VOLUME = "42",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "568-579",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231235"}

@inproceedings{bb236261,
        AUTHOR = "Tung, F. and Mori, G.",
        TITLE = "CLIP-Q: Deep Network Compression Learning by In-parallel
Pruning-Quantization",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7873-7882",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231236"}

@article{bb236262,
        AUTHOR = "Kwon, G. and Ye, J.C.",
        TITLE = "One-Shot Adaptation of GAN in Just One CLIP",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "12179-12191",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231237"}

@article{bb236263,
        AUTHOR = "Han, B.H. and Jiang, X.Y. and Fang, Z.J. and Fujita, H. and Gao, Y.B.",
        TITLE = "F-SCP: An automatic prompt generation method for specific classes
based on visual language pre-training models",
        JOURNAL = PR,
        VOLUME = "147",
        YEAR = "2024",
        PAGES = "110096",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231238"}

@article{bb236264,
        AUTHOR = "Liu, B. and Lu, D.H. and Wei, D. and Wu, X. and Wang, Y. and Zhang, Y. and Zheng, Y.F.",
        TITLE = "Improving Medical Vision-Language Contrastive Pretraining with
Semantics-Aware Triage",
        JOURNAL = MedImg,
        VOLUME = "42",
        YEAR = "2023",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "3579-3589",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231239"}

@article{bb236265,
        AUTHOR = "Gao, P. and Geng, S.J. and Zhang, R.R. and Ma, T. and Fang, R.Y. and Zhang, Y.F. and Li, H.S. and Qiao, Y.",
        TITLE = "CLIP-Adapter: Better Vision-Language Models with Feature Adapters",
        JOURNAL = IJCV,
        VOLUME = "132",
        YEAR = "2024",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "581-595",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231240"}

@inproceedings{bb236266,
        AUTHOR = "Liu, Y.H. and He, J.W. and Gu, J.J. and Kong, X.T. and Qiao, Y. and Dong, C.",
        TITLE = "DegAE: A New Pretraining Paradigm for Low-Level Vision",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "23292-23303",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231241"}

@article{bb236267,
        AUTHOR = "Dong, S. and Wang, L. and Du, B. and Meng, X.L.",
        TITLE = "ChangeCLIP: Remote sensing change detection with multimodal
vision-language representation learning",
        JOURNAL = PandRS,
        VOLUME = "208",
        YEAR = "2024",
        PAGES = "53-69",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231242"}

@article{bb236268,
        AUTHOR = "Peng, F. and Yang, X.S. and Xiao, L.H. and Wang, Y.W. and Xu, C.S.",
        TITLE = "SgVA-CLIP: Semantic-Guided Visual Adapting of Vision-Language Models
for Few-Shot Image Classification",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "3469-3480",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231243"}

@article{bb236269,
        AUTHOR = "Guo, Y.F. and Chen, Y.P. and Ma, Z.",
        TITLE = "NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNN",
        JOURNAL = SPLetters,
        VOLUME = "31",
        YEAR = "2024",
        PAGES = "246-250",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231244"}

@article{bb236270,
        AUTHOR = "Xing, Y.H. and Wu, Q. and Cheng, D. and Zhang, S.Z. and Liang, G.Q. and Wang, P. and Zhang, Y.N.",
        TITLE = "Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "2056-2068",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231245"}

@article{bb236271,
        AUTHOR = "Xiao, L.H. and Yang, X.S. and Peng, F. and Yan, M. and Wang, Y.W. and Xu, C.S.",
        TITLE = "CLIP-VG: Self-Paced Curriculum Adapting of CLIP for Visual Grounding",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "4334-4347",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT231246"}

@article{bb236272,
        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#TT231247"}

@article{bb236273,
        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#TT231248"}

@inproceedings{bb236274,
        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#TT231249"}

@article{bb236275,
        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#TT231250"}

@article{bb236276,
        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#TT231251"}

@article{bb236277,
        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#TT231252"}

@article{bb236278,
        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#TT231253"}

@inproceedings{bb236279,
        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#TT231254"}

@article{bb236280,
        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#TT231255"}

@article{bb236281,
        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#TT231256"}

@article{bb236282,
        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#TT231257"}

@article{bb236283,
        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#TT231258"}

@article{bb236284,
        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#TT231259"}

@article{bb236285,
        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#TT231260"}

@article{bb236286,
        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#TT231261"}

@article{bb236287,
        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#TT231262"}

@inproceedings{bb236288,
        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#TT231263"}

@article{bb236289,
        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#TT231264"}

@article{bb236290,
        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#TT231265"}

@article{bb236291,
        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#TT231266"}

@article{bb236292,
        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#TT231267"}

@article{bb236293,
        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#TT231268"}

@article{bb236294,
        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#TT231269"}

@article{bb236295,
        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#TT231270"}

@article{bb236296,
        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#TT231271"}

@article{bb236297,
        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#TT231272"}

@article{bb236298,
        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#TT231273"}

@article{bb236299,
        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#TT231274"}