@article{bb249800,
AUTHOR = "Li, Y.C. and Wang, X. and Xiao, J.B. and Ji, W. and Chua, T.S.",
TITLE = "Transformer-Empowered Invariant Grounding for Video Question
Answering",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "9510-9522",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT244690"}
@inproceedings{bb249801,
AUTHOR = "Li, Y.C. and Wang, X. and Xiao, J.B. and Ji, W. and Chua, T.S.",
TITLE = "Invariant Grounding for Video Question Answering",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "2918-2927",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT244691"}
@article{bb249802,
AUTHOR = "Zhu, L. and Pan, L.M. and Tan, S. and Zhang, C.Y. and Liu, D. and Wu, L.Y.B. and Boussaid, F. and Bennamoun, M.",
TITLE = "HAViG: Hierarchical adaptive visual grounding framework for video
question answering",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114178",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT244692"}
@inproceedings{bb249803,
AUTHOR = "Huang, J.Y. and Jia, B.X. and Wang, Y. and Zhu, Z.Y. and Linghu, X.K. and Li, Q. and Zhu, S.C. and Huang, S.Y.",
TITLE = "Unveiling the Mist over 3D Vision-Language Understanding:
Object-centric Evaluation with Chain-of-Analysis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24570-24581",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT244693"}
@inproceedings{bb249804,
AUTHOR = "Chen, K. and Wu, X.Q.",
TITLE = "VTQA: Visual Text Question Answering via Entity Alignment and
Cross-Media Reasoning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27208-27217",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT244694"}
@inproceedings{bb249805,
AUTHOR = "Di, S.Z. and Xie, W.",
TITLE = "Grounded Question-Answering in Long Egocentric Videos",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12934-12943",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgrqa3.html#TT244695"}
@inproceedings{bb249806,
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#TT244696"}
@inproceedings{bb249807,
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#TT244697"}
@inproceedings{bb249808,
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#TT244698"}
@inproceedings{bb249809,
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#TT244699"}
@inproceedings{bb249810,
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#TT244700"}
@inproceedings{bb249811,
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#TT244701"}
@inproceedings{bb249812,
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#TT244702"}
@inproceedings{bb249813,
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#TT244703"}
@inproceedings{bb249814,
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#TT244704"}
@inproceedings{bb249815,
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#TT244705"}
@inproceedings{bb249816,
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#TT244706"}
@article{bb249817,
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#TT244707"}
@article{bb249818,
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#TT244708"}
@article{bb249819,
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#TT244709"}
@article{bb249820,
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#TT244710"}
@article{bb249821,
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#TT244711"}
@inproceedings{bb249822,
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#TT244712"}
@article{bb249823,
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#TT244713"}
@article{bb249824,
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#TT244714"}
@article{bb249825,
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#TT244715"}
@article{bb249826,
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#TT244716"}
@article{bb249827,
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#TT244717"}
@article{bb249828,
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#TT244718"}
@article{bb249829,
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#TT244719"}
@article{bb249830,
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#TT244720"}
@inproceedings{bb249831,
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#TT244721"}
@article{bb249832,
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#TT244722"}
@inproceedings{bb249833,
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#TT244723"}
@article{bb249834,
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#TT244724"}
@article{bb249835,
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#TT244725"}
@article{bb249836,
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#TT244726"}
@article{bb249837,
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#TT244727"}
@article{bb249838,
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#TT244728"}
@article{bb249839,
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#TT244729"}
@article{bb249840,
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#TT244730"}
@article{bb249841,
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#TT244731"}
@article{bb249842,
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#TT244732"}
@article{bb249843,
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#TT244733"}
@article{bb249844,
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#TT244734"}
@article{bb249845,
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#TT244735"}
@article{bb249846,
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#TT244736"}
@article{bb249847,
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#TT244737"}
@article{bb249848,
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#TT244738"}
@article{bb249849,
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#TT244739"}
@article{bb249850,
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#TT244740"}
@article{bb249851,
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#TT244741"}
@article{bb249852,
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#TT244742"}
@article{bb249853,
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#TT244743"}
@article{bb249854,
AUTHOR = "Wu, J. and Ji, Z. and Wang, Y.D. and Pang, Y.W. and Han, J.G.",
TITLE = "Cyclic Pseudo-Label Generation and Refinement for Weakly Supervised
Referring Expression Grounding",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "5",
MONTH = "May",
PAGES = "5839-5851",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244744"}
@article{bb249855,
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#TT244745"}
@article{bb249856,
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#TT244746"}
@article{bb249857,
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#TT244747"}
@article{bb249858,
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 = "3597-3612",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244748"}
@article{bb249859,
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#TT244749"}
@article{bb249860,
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#TT244750"}
@article{bb249861,
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#TT244751"}
@article{bb249862,
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#TT244752"}
@article{bb249863,
AUTHOR = "Li, J. and Wen, Z. and Zhang, Y. and Wang, W.X. and Cai, Y.X. and Zhang, T.X. and He, X.J. and Liu, J.",
TITLE = "Generalized referring expression segmentation driven by
instance-oriented queries",
JOURNAL = PR,
VOLUME = "172",
YEAR = "2026",
PAGES = "112524",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244753"}
@article{bb249864,
AUTHOR = "Liu, X.Y. and Liu, T. and Huang, S. and Xin, Y. and Hu, Y. and Qin, L. and Wang, D.L. and Wu, Y.Y. and Chen, H.G.",
TITLE = "M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring
Expression Comprehension",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "1341-1354",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244754"}
@article{bb249865,
AUTHOR = "Li, R.F. and Lu, M.C. and Lin, P.Y. and Yu, Z.H. and Ma, Z.Y.",
TITLE = "Improving Scene Knowledge Referring Expression Comprehension With
Large Language Models",
JOURNAL = MultMedMag,
VOLUME = "33",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "72-80",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244755"}
@article{bb249866,
AUTHOR = "Zhang, Z. and Guan, Z. and Zhao, T.C. and Shen, H.Z. and Cai, Y.X. and Su, Z.G. and Shang, Y.H. and Liu, Z.J. and Yin, J.W. and Li, X.",
TITLE = "Geo-R1: Improving few-shot geospatial referring expression
understanding with reinforcement fine-tuning",
JOURNAL = PandRS,
VOLUME = "237",
YEAR = "2026",
PAGES = "113-129",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244756"}
@article{bb249867,
AUTHOR = "Cheng, W.X. and Dai, M. and Yang, W.K.",
TITLE = "PLRVG: Progressive layer-wise refinement for visual grounding via
deep-to-shallow decoding",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113555",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244757"}
@article{bb249868,
AUTHOR = "Yang, F. and Zhu, Y. and Zhan, Y.F. and Zhao, H.Y. and Li, X. and Wang, Y.W. and Tang, M. and Ning, X. and Wang, J.Q.",
TITLE = "Seg-LLaVA: Empowering pixel-level understanding with large vision
language model",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113560",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244758"}
@article{bb249869,
AUTHOR = "Wu, C.L. and Chen, Q. and Ji, J.Y. and Liu, Y.H. and Ma, Y.W. and Sun, X.S. and Cao, L.J.",
TITLE = "3D-STMN++: Leveraging semantic proxies to enhance superpoint-text
matching for 3D Referring Expression Segmentation",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113854",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244759"}
@article{bb249870,
AUTHOR = "Wang, K.Y. and Wu, G. and Fu, X. and Wang, X. and Liu, K. and Lu, X. and Ge, C.J. and Zhai, W. and Zha, Z.J.",
TITLE = "SkyFind: A Large-Scale Benchmark Unveiling Referring Expression
Comprehension for UAV",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "8",
MONTH = "August",
PAGES = "9859-9875",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244760"}
@article{bb249871,
AUTHOR = "Li, R. and Zhuo, W. and Zheng, S.Y. and Wu, Z.H. and Shen, L.L.",
TITLE = "Zero-shot referring expression comprehension via guidance of
Multimodal Large Language Models",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114223",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244761"}
@article{bb249872,
AUTHOR = "Song, C.W. and Koh, Y.J.",
TITLE = "OBB-PBD: Extending Parallel Box Decoding to Oriented Bounding Boxes
for Referring Expression Grounding in Aerial Imagery",
JOURNAL = RS,
VOLUME = "18",
YEAR = "2026",
NUMBER = "20",
PAGES = "3535",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244762"}
@article{bb249873,
AUTHOR = "Wu, Y. and Bolucu, N. and Wan, S. and Wang, D.D. and Xia, J.H. and Zhang, J.",
TITLE = "Interpretable Zero-Shot Referring Expression Comprehension With
Query-Driven Scene Graphs",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "10849-10860",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244763"}
@article{bb249874,
AUTHOR = "Wu, M.R. and Chen, H. and Ji, J.Y. and Sun, X.S. and Liu, Z.Y. and Cao, L.J. and Cheng, M.M. and Ji, R.R.",
TITLE = "Test-Time Computing for Referring Multimodal Large Language Models",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "11",
MONTH = "November",
PAGES = "484",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244764"}
@inproceedings{bb249875,
AUTHOR = "Chen, J. and Wei, F.Y. and Zhao, J.J. and Song, S. and Wu, B.H. and Peng, Z.X. and Chan, S.H.G. and Zhang, H.Y.",
TITLE = "Revisiting Referring Expression Comprehension Evaluation in the Era
of Large Multimodal Models",
BOOKTITLE = "AIBench25",
YEAR = "2025",
PAGES = "513-524",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803refex3.html#TT244765"}
@inproceedings{bb249876,
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#TT244766"}
@inproceedings{bb249877,
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#TT244767"}
@inproceedings{bb249878,
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#TT244768"}
@inproceedings{bb249879,
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#TT244769"}
@inproceedings{bb249880,
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#TT244770"}
@inproceedings{bb249881,
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#TT244771"}
@inproceedings{bb249882,
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#TT244772"}
@inproceedings{bb249883,
AUTHOR = "Han, Z. and Zhu, F.R. 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#TT244773"}
@inproceedings{bb249884,
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#TT244774"}
@inproceedings{bb249885,
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#TT244775"}
@inproceedings{bb249886,
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#TT244776"}
@inproceedings{bb249887,
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#TT244777"}
@inproceedings{bb249888,
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#TT244778"}
@inproceedings{bb249889,
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#TT244779"}
@inproceedings{bb249890,
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#TT244780"}
@inproceedings{bb249891,
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#TT244781"}
@inproceedings{bb249892,
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#TT244782"}
@inproceedings{bb249893,
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#TT244783"}
@inproceedings{bb249894,
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#TT244784"}
@inproceedings{bb249895,
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#TT244785"}
@inproceedings{bb249896,
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#TT244786"}
@inproceedings{bb249897,
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#TT244787"}
@inproceedings{bb249898,
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#TT244788"}
@inproceedings{bb249899,
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#TT244789"}
Last update:Nov 9, 2026 at 17:04:52