@inproceedings{bb237700,
        AUTHOR = "Chen, C.Y. and Anjum, S. and Gurari, D.",
        TITLE = "VQA Therapy: Exploring Answer Differences by Visually Grounding
Answers",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "15269-15279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232666"}

@inproceedings{bb237701,
        AUTHOR = "Le, T.M. and Le, V. and Gupta, S.I. and Venkatesh, S. and Tran, T.",
        TITLE = "Guiding Visual Question Answering with Attention Priors",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "4370-4379",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232667"}

@inproceedings{bb237702,
        AUTHOR = "Khan, A.U. and Kuehne, H. and Gan, C. and da Vitoria Lobo, N. and Shah, M.",
        TITLE = "Weakly Supervised Grounding for VQA in Vision-Language Transformers",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXV:652-670",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232668"}

@inproceedings{bb237703,
        AUTHOR = "Gupta, K. and Gautam, D. and Mamidi, R.",
        TITLE = "cViL: Cross-Lingual Training of Vision-Language Models using
Knowledge Distillation",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "1734-1741",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232669"}

@inproceedings{bb237704,
        AUTHOR = "Lu, X.P. and Fan, Z. and Wang, Y. and Oh, J. and Rose, C.P.",
        TITLE = "Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling",
        BOOKTITLE = XSAnim21,
        YEAR = "2021",
        PAGES = "2631-2639",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232670"}

@inproceedings{bb237705,
        AUTHOR = "Khan, A.U. and Kuehne, H. and Duarte, K. and Gan, C. and Lobo, N. and Shah, M.",
        TITLE = "Found a Reason for me? Weakly-supervised Grounded Visual Question
Answering using Capsules",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "8461-8470",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232671"}

@inproceedings{bb237706,
        AUTHOR = "Selvaraju, R.R. and Tendulkar, P. and Parikh, D. and Horvitz, E. and Tulio Ribeiro, M. and Nushi, B. and Kamar, E.",
        TITLE = "SQuINTing at VQA Models: Introspecting VQA Models With Sub-Questions",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10000-10008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232672"}

@inproceedings{bb237707,
        AUTHOR = "Gouthaman, K.V. and Mittal, A.",
        TITLE = "Reducing Language Biases in Visual Question Answering with
Visually-grounded Question Encoder",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIII:18-34",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232673"}

@inproceedings{bb237708,
        AUTHOR = "Tan, H.L. and Leong, M.C. and Xu, Q. and Li, L. and Fang, F. and Cheng, Y. and Gauthier, N. and Sun, Y. and Lim, J.H.",
        TITLE = "Task-Oriented Multi-Modal Question Answering For Collaborative
Applications",
        BOOKTITLE = ICIP20,
        YEAR = "2020",
        PAGES = "1426-1430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232674"}

@inproceedings{bb237709,
        AUTHOR = "Selvaraju, R.R. and Lee, S. and Shen, Y. and Jin, H. and Ghosh, S. and Heck, L. and Batra, D. and Parikh, D.",
        TITLE = "Taking a HINT: Leveraging Explanations to Make Vision and Language
Models More Grounded",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2591-2600",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232675"}

@inproceedings{bb237710,
        AUTHOR = "Zhang, Y. and Niebles, J.C. and Soto, A.",
        TITLE = "Interpretable Visual Question Answering by Visual Grounding From
Attention Supervision Mining",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "349-357",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT232676"}

@article{bb237711,
        AUTHOR = "Li, X. and Jiang, S.",
        TITLE = "Bundled Object Context for Referring Expressions",
        JOURNAL = MultMed,
        VOLUME = "20",
        YEAR = "2018",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2749-2760",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232677"}

@article{bb237712,
        AUTHOR = "Wang, J.M. and Cui, E. and Liu, K.L. and Sun, Y.K. and Liang, J.Y. and Yuan, C.M. and Duan, X.J. and Jin, G.H. and Chung, T.S.",
        TITLE = "Referring expression comprehension model with matching detection and
linguistic feedback",
        JOURNAL = IET-CV,
        VOLUME = "14",
        YEAR = "2020",
        NUMBER = "8",
        MONTH = "December",
        PAGES = "625-633",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232678"}

@article{bb237713,
        AUTHOR = "Qiao, Y.Y. and Deng, C.R. and Wu, Q.",
        TITLE = "Referring Expression Comprehension: A Survey of Methods and Datasets",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "4426-4440",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232679"}

@article{bb237714,
        AUTHOR = "Niu, Y.L. and Zhang, H.W. and Lu, Z.W. and Chang, S.F.",
        TITLE = "Variational Context: Exploiting Visual and Textual Context for
Grounding Referring Expressions",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "347-359",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232680"}

@article{bb237715,
        AUTHOR = "Yang, S. and Li, G.B. and Yu, Y.Z.",
        TITLE = "Relationship-Embedded Representation Learning for Grounding Referring
Expressions",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "2765-2779",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232681"}

@inproceedings{bb237716,
        AUTHOR = "Yang, S. and Li, G.B. and Yu, Y.Z.",
        TITLE = "Cross-Modal Relationship Inference for Grounding Referring Expressions",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "4140-4149",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232682"}

@article{bb237717,
        AUTHOR = "Sun, M.J. and Xiao, J. and Lim, E.G. and Liu, S. and Goulermas, J.Y.",
        TITLE = "Discriminative Triad Matching and Reconstruction for Weakly Referring
Expression Grounding",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "4189-4195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232683"}

@article{bb237718,
        AUTHOR = "Lin, L. and Yan, P.X. and Xu, X.Q. and Yang, S. and Zeng, K. and Li, G.B.",
        TITLE = "Structured Attention Network for Referring Image Segmentation",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        PAGES = "1922-1932",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232684"}

@article{bb237719,
        AUTHOR = "Yang, X. and Wang, H. and Xie, D. and Deng, C. and Tao, D.C.",
        TITLE = "Object-Agnostic Transformers for Video Referring Segmentation",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "2839-2849",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232685"}

@article{bb237720,
        AUTHOR = "Wang, X. and Xie, D. and Zheng, Y.S.",
        TITLE = "Referring expression grounding by multi-context reasoning",
        JOURNAL = PRL,
        VOLUME = "160",
        YEAR = "2022",
        PAGES = "66-72",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232686"}

@article{bb237721,
        AUTHOR = "Shen, H.T. and Chen, C. and Wang, P. and Gao, L.L. and Wang, M. and Song, J.K.",
        TITLE = "Continual Referring Expression Comprehension via Dual Modular
Memorization",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "6694-6706",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232687"}

@article{bb237722,
        AUTHOR = "Chen, Y.W. and Tsai, Y.H. and Yang, M.H.",
        TITLE = "Understanding Synonymous Referring Expressions via Contrastive Features",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2501-2516",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232688"}

@article{bb237723,
        AUTHOR = "Suo, W. and Sun, M.Y. and Wang, P. and Zhang, Y.N. and Wu, Q.",
        TITLE = "Rethinking and Improving Feature Pyramids for One-Stage Referring
Expression Comprehension",
        JOURNAL = IP,
        VOLUME = "32",
        YEAR = "2023",
        PAGES = "854-864",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232689"}

@article{bb237724,
        AUTHOR = "Liu, X.J. and Li, L. and Wang, S.H. and Zha, Z.J. and Li, Z.C. and Tian, Q. and Huang, Q.M.",
        TITLE = "Entity-Enhanced Adaptive Reconstruction Network for Weakly Supervised
Referring Expression Grounding",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "3003-3018",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232690"}

@inproceedings{bb237725,
        AUTHOR = "Liu, X.J. and Li, L. and Wang, S.H. and Zha, Z.J. and Meng, D.C. and Huang, Q.M.",
        TITLE = "Adaptive Reconstruction Network for Weakly Supervised Referring
Expression Grounding",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2611-2620",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232691"}

@article{bb237726,
        AUTHOR = "Feng, G. and Zhang, L. and Sun, J.Y. 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#TT232692"}

@inproceedings{bb237727,
        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#TT232693"}

@article{bb237728,
        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#TT232694"}

@article{bb237729,
        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#TT232695"}

@article{bb237730,
        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#TT232696"}

@article{bb237731,
        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#TT232697"}

@article{bb237732,
        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#TT232698"}

@article{bb237733,
        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#TT232699"}

@article{bb237734,
        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#TT232700"}

@article{bb237735,
        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#TT232701"}

@article{bb237736,
        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#TT232702"}

@article{bb237737,
        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#TT232703"}

@article{bb237738,
        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#TT232704"}

@article{bb237739,
        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#TT232705"}

@article{bb237740,
        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#TT232706"}

@article{bb237741,
        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#TT232707"}

@article{bb237742,
        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#TT232708"}

@article{bb237743,
        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#TT232709"}

@article{bb237744,
        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#TT232710"}

@article{bb237745,
        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#TT232711"}

@article{bb237746,
        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#TT232712"}

@article{bb237747,
        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#TT232713"}

@article{bb237748,
        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#TT232714"}

@article{bb237749,
        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#TT232715"}

@article{bb237750,
        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#TT232716"}

@article{bb237751,
        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#TT232717"}

@article{bb237752,
        AUTHOR = "Ke, X. and Xu, P.R. 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#TT232718"}

@article{bb237753,
        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#TT232719"}

@article{bb237754,
        AUTHOR = "Guo, H. and Fan, W. and Wei, B. and Zhu, J.F. and Tian, J. and Yi, C.Z. and Jiang, F.",
        TITLE = "AD-DINO: Attention-Dynamic DINO for Distance-Aware Embodied Reference
Understanding",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "10238-10249",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232720"}

@article{bb237755,
        AUTHOR = "Ke, J.C. and Wen, J. and Wang, H.T. and Cheng, W.H. and Wang, J.",
        TITLE = "Multi-Perspective Cross-Modal Object Encoding for Referring
Expression Comprehension",
        JOURNAL = IP,
        VOLUME = "34",
        YEAR = "2025",
        PAGES = "6911-6924",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT232721"}

@inproceedings{bb237756,
        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#TT232722"}

@inproceedings{bb237757,
        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#TT232723"}

@inproceedings{bb237758,
        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#TT232724"}

@inproceedings{bb237759,
        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#TT232725"}

@inproceedings{bb237760,
        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#TT232726"}

@inproceedings{bb237761,
        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#TT232727"}

@inproceedings{bb237762,
        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#TT232728"}

@inproceedings{bb237763,
        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#TT232729"}

@inproceedings{bb237764,
        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#TT232730"}

@inproceedings{bb237765,
        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#TT232731"}

@inproceedings{bb237766,
        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#TT232732"}

@inproceedings{bb237767,
        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#TT232733"}

@inproceedings{bb237768,
        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#TT232734"}

@inproceedings{bb237769,
        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#TT232735"}

@inproceedings{bb237770,
        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#TT232736"}

@inproceedings{bb237771,
        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#TT232737"}

@inproceedings{bb237772,
        AUTHOR = "Qiao, Y.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#TT232738"}

@inproceedings{bb237773,
        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#TT232739"}

@inproceedings{bb237774,
        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#TT232740"}

@inproceedings{bb237775,
        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#TT232741"}

@inproceedings{bb237776,
        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#TT232742"}

@inproceedings{bb237777,
        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#TT232743"}

@inproceedings{bb237778,
        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#TT232744"}

@inproceedings{bb237779,
        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#TT232745"}

@inproceedings{bb237780,
        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#TT232746"}

@inproceedings{bb237781,
        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#TT232747"}

@inproceedings{bb237782,
        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#TT232748"}

@inproceedings{bb237783,
        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#TT232749"}

@inproceedings{bb237784,
        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#TT232750"}

@inproceedings{bb237785,
        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#TT232751"}

@inproceedings{bb237786,
        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#TT232752"}

@inproceedings{bb237787,
        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#TT232753"}

@article{bb237788,
        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#TT232754"}

@inproceedings{bb237789,
        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#TT232755"}

@article{bb237790,
        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#TT232756"}

@article{bb237791,
        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#TT232757"}

@article{bb237792,
        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#TT232758"}

@article{bb237793,
        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#TT232759"}

@inproceedings{bb237794,
        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#TT232760"}

@article{bb237795,
        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#TT232761"}

@article{bb237796,
        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#TT232762"}

@article{bb237797,
        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#TT232763"}

@article{bb237798,
        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#TT232764"}

@article{bb237799,
        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#TT232765"}

Last update:Nov 26, 2025 at 20:24:09