@inproceedings{bb214700,
        AUTHOR = "Sinha, A. and Akilesh, B. and Sarkar, M. and Krishnamurthy, B.",
        TITLE = "Attention Based Natural Language Grounding by Navigating Virtual
Environment",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "236-244",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209768"}

@inproceedings{bb214701,
        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/applicat803vgr2.html#TT209769"}

@inproceedings{bb214702,
        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/applicat803vgr2.html#TT209770"}

@inproceedings{bb214703,
        AUTHOR = "Shi, J. and Xu, J. and Gong, B.Q. and Xu, C.L.",
        TITLE = "Not All Frames Are Equal: Weakly-Supervised Video Grounding With
Contextual Similarity and Visual Clustering Losses",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10436-10444",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209771"}

@inproceedings{bb214704,
        AUTHOR = "Datta, S. and Sikka, K. and Roy, A. and Ahuja, K. and Parikh, D. and Divakaran, A.",
        TITLE = "Align2Ground: Weakly Supervised Phrase Grounding Guided by
Image-Caption Alignment",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2601-2610",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209772"}

@inproceedings{bb214705,
        AUTHOR = "Fang, Z.Y. and Kong, S. and Fowlkes, C.C. and Yang, Y.Z.",
        TITLE = "Modularized Textual Grounding for Counterfactual Resilience",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6371-6381",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209773"}

@inproceedings{bb214706,
        AUTHOR = "Zhuang, B. and Wu, Q. and Shen, C. and Reid, I.D. and van den Hengel, A.J.",
        TITLE = "Parallel Attention: A Unified Framework for Visual Object Discovery
Through Dialogs and Queries",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4252-4261",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209774"}

@inproceedings{bb214707,
        AUTHOR = "Yang, Z.Y. and Chen, T.L. and Wang, L.W. and Luo, J.B.",
        TITLE = "Improving One-Stage Visual Grounding by Recursive Sub-query
Construction",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIV:387-404",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209775"}

@inproceedings{bb214708,
        AUTHOR = "Liu, D.Q. and Zhang, H.W. and Zha, Z.J. and Wu, F.",
        TITLE = "Learning to Assemble Neural Module Tree Networks for Visual Grounding",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4672-4681",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209776"}

@inproceedings{bb214709,
        AUTHOR = "Sadhu, A. and Chen, K. and Nevatia, R.",
        TITLE = "Zero-Shot Grounding of Objects From Natural Language Queries",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4693-4702",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209777"}

@inproceedings{bb214710,
        AUTHOR = "Yang, Z.Y. and Gong, B.Q. and Wang, L.W. and Huang, W.B. and Yu, D. and Luo, J.B.",
        TITLE = "A Fast and Accurate One-Stage Approach to Visual Grounding",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4682-4692",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209778"}

@inproceedings{bb214711,
        AUTHOR = "Rohrbach, A. and Rohrbach, M. and Tang, S. and Oh, S.J. and Schiele, B.",
        TITLE = "Generating Descriptions with Grounded and Co-referenced People",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "4196-4206",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209779"}

@inproceedings{bb214712,
        AUTHOR = "Zhu, Y. and Kiros, R. and Zemel, R. and Salakhutdinov, R. and Urtasun, R. and Torralba, A.B. and Fidler, S.",
        TITLE = "Aligning Books and Movies: Towards Story-Like Visual Explanations by
Watching Movies and Reading Books",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "19-27",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT209780"}

@article{bb214713,
        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#TT209781"}

@article{bb214714,
        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#TT209782"}

@article{bb214715,
        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#TT209783"}

@article{bb214716,
        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#TT209784"}

@article{bb214717,
        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#TT209785"}

@inproceedings{bb214718,
        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#TT209786"}

@article{bb214719,
        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#TT209787"}

@article{bb214720,
        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",
        NUMBER = "2022",
        PAGES = "1922-1932",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT209788"}

@article{bb214721,
        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",
        NUMBER = "2022",
        PAGES = "2839-2849",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT209789"}

@article{bb214722,
        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#TT209790"}

@article{bb214723,
        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#TT209791"}

@article{bb214724,
        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#TT209792"}

@article{bb214725,
        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#TT209793"}

@article{bb214726,
        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#TT209794"}

@inproceedings{bb214727,
        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#TT209795"}

@article{bb214728,
        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#TT209796"}

@inproceedings{bb214729,
        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#TT209797"}

@article{bb214730,
        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#TT209798"}

@article{bb214731,
        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#TT209799"}

@article{bb214732,
        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#TT209800"}

@article{bb214733,
        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#TT209801"}

@article{bb214734,
        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#TT209802"}

@article{bb214735,
        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#TT209803"}

@article{bb214736,
        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#TT209804"}

@article{bb214737,
        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#TT209805"}

@article{bb214738,
        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#TT209806"}

@article{bb214739,
        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#TT209807"}

@article{bb214740,
        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#TT209808"}

@article{bb214741,
        AUTHOR = "Li, X.C. and Fan, B.Y. and Zhang, R. 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#TT209809"}

@article{bb214742,
        AUTHOR = "Luo, G. and Zhou, 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#TT209810"}

@article{bb214743,
        AUTHOR = "Miao, P. and Su, W. and Wang, G. and Li, X. 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#TT209811"}

@article{bb214744,
        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#TT209812"}

@inproceedings{bb214745,
        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#TT209813"}

@inproceedings{bb214746,
        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#TT209814"}

@inproceedings{bb214747,
        AUTHOR = "Qiao, Y. and Qi, Y. 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#TT209815"}

@inproceedings{bb214748,
        AUTHOR = "Chen, Y. and Du, R. and Liang, K. 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#TT209816"}

@inproceedings{bb214749,
        AUTHOR = "Sun, J. and Luo, G. and Zhou, Y. and Sun, X.S. and Jiang, G. and Wang, Z. 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#TT209817"}

@inproceedings{bb214750,
        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#TT209818"}

@inproceedings{bb214751,
        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#TT209819"}

@inproceedings{bb214752,
        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#TT209820"}

@inproceedings{bb214753,
        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#TT209821"}

@inproceedings{bb214754,
        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#TT209822"}

@inproceedings{bb214755,
        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#TT209823"}

@inproceedings{bb214756,
        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#TT209824"}

@inproceedings{bb214757,
        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#TT209825"}

@inproceedings{bb214758,
        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#TT209826"}

@inproceedings{bb214759,
        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#TT209827"}

@inproceedings{bb214760,
        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#TT209828"}

@article{bb214761,
        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#TT209829"}

@inproceedings{bb214762,
        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#TT209830"}

@article{bb214763,
        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#TT209831"}

@article{bb214764,
        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#TT209832"}

@article{bb214765,
        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#TT209833"}

@article{bb214766,
        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#TT209834"}

@inproceedings{bb214767,
        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#TT209835"}

@article{bb214768,
        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#TT209836"}

@article{bb214769,
        AUTHOR = "Peng, F. and Yang, X.S. and Xiao, L.H. and Wang, Y. 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#TT209837"}

@article{bb214770,
        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#TT209838"}

@article{bb214771,
        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#TT209839"}

@article{bb214772,
        AUTHOR = "Xiao, L.H. and Yang, X.S. and Peng, F. and Yan, M. and Wang, Y. 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#TT209840"}

@article{bb214773,
        AUTHOR = "Zhang, K. and Yang, Y. and Yu, J. and Jiang, H. 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#TT209841"}

@article{bb214774,
        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#TT209842"}

@inproceedings{bb214775,
        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#TT209843"}

@article{bb214776,
        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#TT209844"}

@inproceedings{bb214777,
        AUTHOR = "Shen, S. and Zhu, Z. and Fan, L.Q. and Zhang, H. and Wu, X.X.",
        TITLE = "DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D
Classification",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "3584-3593",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209845"}

@inproceedings{bb214778,
        AUTHOR = "Wan, B. and Tuytelaars, T.",
        TITLE = "Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge
Distillation at Multiple Levels",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "1794-1804",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209846"}

@inproceedings{bb214779,
        AUTHOR = "Mei, J. and Piergiovanni, A.J. and Hwang, J.N. and Li, W.",
        TITLE = "SLVP: Self-Supervised Language-Video Pre-Training for Referring Video
Object Segmentation",
        BOOKTITLE = Pretrain24,
        YEAR = "2024",
        PAGES = "507-517",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209847"}

@inproceedings{bb214780,
        AUTHOR = "Nicolas, J. and Chiaroni, F. and Ziko, I. and Ahmad, O. and Desrosiers, C. and Dolz, J.",
        TITLE = "MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain
Incremental Learning",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "1751-1761",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209848"}

@inproceedings{bb214781,
        AUTHOR = "Hess, G. and Tonderski, A. and Petersson, C. and Astrom, K. and Svensson, L.",
        TITLE = "LidarCLIP or: How I Learned to Talk to Point Clouds",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "7423-7432",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209849"}

@inproceedings{bb214782,
        AUTHOR = "Theisen, W. and Scheirer, W.",
        TITLE = "C-CLIP: Contrastive Image-Text Encoders to Close the
Descriptive-Commentative Gap",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "7226-7235",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209850"}

@inproceedings{bb214783,
        AUTHOR = "Gondal, M.W. and Gast, J. and Ruiz, I.A. and Droste, R. and Macri, T. and Kumar, S. and Staudigl, L.",
        TITLE = "Domain Aligned CLIP for Few-shot Classification",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "5709-5718",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209851"}

@inproceedings{bb214784,
        AUTHOR = "Phan, T. and Vo, K. and Le, D. and Doretto, G. and Adjeroh, D. and Le, N.",
        TITLE = "ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot
End-to-End Temporal Action Detection",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "7031-7040",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209852"}

@inproceedings{bb214785,
        AUTHOR = "Lai, Z.F. and Bai, H.P. and Zhang, H.T. and Du, X.Z. and Shan, J.L. and Yang, Y.F. and Chuah, C.N. and Cao, M.",
        TITLE = "Empowering Unsupervised Domain Adaptation with Large-scale
Pre-trained Vision-Language Models",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "2679-2689",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209853"}

@inproceedings{bb214786,
        AUTHOR = "Gupta, D. and Kharbanda, S. and Zhou, J.W. and Li, W. and Pfister, H. and Wei, D.L.",
        TITLE = "CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for
Multimodal Machine Translation",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "2863-2874",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209854"}

@inproceedings{bb214787,
        AUTHOR = "Fang, H. and Yang, Z.F. and Wei, Y.H. and Zang, X.H. and Ban, C. and Feng, Z. and He, Z.J. and Li, Y.X. and Sun, H.",
        TITLE = "Alignment and Generation Adapter for Efficient Video-Text
Understanding",
        BOOKTITLE = CLVL23,
        YEAR = "2023",
        PAGES = "2783-2789",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209855"}

@inproceedings{bb214788,
        AUTHOR = "Zhu, B. and Niu, Y. and Han, Y.C. and Wu, Y. and Zhang, H.W.",
        TITLE = "Prompt-aligned Gradient for Prompt Tuning",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "15613-15623",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209856"}

@inproceedings{bb214789,
        AUTHOR = "Yuan, H.J. and Zhang, S.W. and Wang, X. and Albanie, S. and Pan, Y. and Feng, T. and Jiang, J.W. and Ni, D. and Zhang, Y. and Zhao, D.L.",
        TITLE = "RLIPv2: Fast Scaling of Relational Language-Image Pre-training",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "21592-21604",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209857"}

@inproceedings{bb214790,
        AUTHOR = "Wang, Z. and Yu, X. and Rao, Y.M. and Zhou, J. and Lu, J.W.",
        TITLE = "Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "5617-5627",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209858"}

@inproceedings{bb214791,
        AUTHOR = "Li, M. and Wu, J. and Wang, X. and Chen, C. and Qin, J. and Xiao, X.F. and Wang, R. and Zheng, M. and Pan, X.",
        TITLE = "AlignDet: Aligning Pre-training and Fine-tuning in Object Detection",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "6843-6853",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209859"}

@inproceedings{bb214792,
        AUTHOR = "Lee, S. and Chung, H.J. and Park, M.Y. and Park, J. and Ryu, W.S. and Ye, J.C.",
        TITLE = "Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion
Models",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "10676-10686",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209860"}

@inproceedings{bb214793,
        AUTHOR = "Ye, Q.H. and Xu, G.H. and Yan, M. and Xu, H.Y. and Qian, Q. and Zhang, J. and Huang, F.",
        TITLE = "HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "15359-15370",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209861"}

@inproceedings{bb214794,
        AUTHOR = "Wu, C.Y. and Zhang, X.M. and Zhang, Y. and Wang, Y.F. and Xie, W.",
        TITLE = "MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training for
X-ray Diagnosis",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "21315-21326",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209862"}

@inproceedings{bb214795,
        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#TT209863"}

@inproceedings{bb214796,
        AUTHOR = "Ma, W.X. and Li, S. and Zhang, J. and Liu, C.H. and Kang, J.X. and Wang, Y.L. and Huang, G.",
        TITLE = "Borrowing Knowledge From Pre-trained Language Model:
A New Data-efficient Visual Learning Paradigm",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "18740-18751",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209864"}

@inproceedings{bb214797,
        AUTHOR = "Ganugula, P. and Kumar, Y.S.S.S.S. and Reddy, N.K.S. and Chellingi, P. and Thakur, A. and Kasera, N. and Anand, C.S.",
        TITLE = "MOSAIC: Multi-Object Segmented Arbitrary Stylization Using CLIP",
        BOOKTITLE = NIVT23,
        YEAR = "2023",
        PAGES = "892-903",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209865"}

@inproceedings{bb214798,
        AUTHOR = "Luo, Z.Y. and Zhao, P. and Xu, C. and Geng, X. and Shen, T. and Tao, C.Y. and Ma, J. and Lin, Q.W. and Jiang, D.X.",
        TITLE = "LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for
Large-Scale Image-Text Sparse Retrieval",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "11172-11183",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209866"}

@inproceedings{bb214799,
        AUTHOR = "Zhai, X.H. and Mustafa, B. and Kolesnikov, A. and Beyer, L.",
        TITLE = "Sigmoid Loss for Language Image Pre-Training",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "11941-11952",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT209867"}