@inproceedings{bb242500,
AUTHOR = "Hua, H. and Shi, J. and Kafle, K. and Jenni, S. and Zhang, D. and Collomosse, J. and Cohen, S. and Luo, J.B.",
TITLE = "Finematch: Aspect-based Fine-grained Image and Text Mismatch Detection
and Correction",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "IX: 474-491",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237415"}
@inproceedings{bb242501,
AUTHOR = "Li, Y.H. and Liu, H.T. and Cai, M. and Li, Y.J. and Shechtman, E. and Lin, Z. and Lee, Y.J. and Singh, K.K.",
TITLE = "Removing Distributional Discrepancies in Captions Improves Image-Text
Alignment",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXI: 405-422",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237416"}
@inproceedings{bb242502,
AUTHOR = "Ma, W. and Li, K. and Jiang, Z. and Meshry, M. and Liu, Q.H. and Wang, H.Y. and Hane, C. and Yuille, A.L.",
TITLE = "Rethinking Video-text Understanding: Retrieval from Counterfactually
Augmented Data",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIII: 254-269",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237417"}
@inproceedings{bb242503,
AUTHOR = "Zhang, W. and Xu, X.W. and Tao, Y. and Wang, X.D. and Wang, C.L. and Wei, Z.M.",
TITLE = "Bi-Directional Image-Text Retrieval With Position Attention and
Similarity Filtering",
BOOKTITLE = ICIVC22,
YEAR = "2022",
PAGES = "635-640",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237418"}
@inproceedings{bb242504,
AUTHOR = "Li, Z. and Nian, X.H. and Pan, C. and Yang, D. and Xiong, H.Y. and Wang, H.B.",
TITLE = "Relation Graph Reasoning for Image-Text Matching",
BOOKTITLE = ICIVC22,
YEAR = "2022",
PAGES = "319-324",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237419"}
@inproceedings{bb242505,
AUTHOR = "Zhang, K. and Mao, Z.D. and Wang, Q. and Zhang, Y.D.",
TITLE = "Negative-Aware Attention Framework for Image-Text Matching",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15640-15649",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237420"}
@inproceedings{bb242506,
AUTHOR = "Long, S. and Han, S.C. and Wan, X.J. and Poon, J.",
TITLE = "GraDual: Graph-based Dual-modal Representation for Image-Text
Matching",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "2463-2472",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237421"}
@inproceedings{bb242507,
AUTHOR = "Biten, A.F. and Mafla, A. and Gomez, L. and Karatzas, D.",
TITLE = "Is An Image Worth Five Sentences? A New Look into Semantics for
Image-Text Matching",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "2483-2492",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237422"}
@inproceedings{bb242508,
AUTHOR = "Mithun, N.C. and Pasricha, R. and Papalexakis, E. and Roy Chowdhury, A.K.",
TITLE = "Webly Supervised Image-Text Embedding with Noisy Tag Refinement",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "7454-7461",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237423"}
@inproceedings{bb242509,
AUTHOR = "Chen, J.A. and Zhang, L. and Wang, Q. and Bai, C. and Kpalma, K.",
TITLE = "Intra-Modal Constraint Loss for Image-Text Retrieval",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "4023-4027",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237424"}
@inproceedings{bb242510,
AUTHOR = "Liu, Y. and Wang, H.Q. and Meng, F.Y. and Liu, M.Y. and Liu, H.",
TITLE = "Attend, Correct and Focus: A Bidirectional Correct Attention Network
for Image-Text Matching",
BOOKTITLE = ICIP21,
YEAR = "2021",
PAGES = "2673-2677",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237425"}
@inproceedings{bb242511,
AUTHOR = "Yang, S.T. and Huang, K.H. and Howe, B.",
TITLE = "JECL: Joint Embedding and Cluster Learning for Image-Text Pairs",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "8344-8351",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237426"}
@inproceedings{bb242512,
AUTHOR = "Mikriukov, G. and Ravanbakhsh, M. and Demir, B.",
TITLE = "An Unsupervised Cross-Modal Hashing Method Robust to Noisy Training
Image-Text Correspondences in Remote Sensing",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2556-2560",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237427"}
@inproceedings{bb242513,
AUTHOR = "Anwaar, M.U. and Labintcev, E. and Kleinsteuber, M.",
TITLE = "Compositional Learning of Image-Text Query for Image Retrieval",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "1139-1148",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237428"}
@inproceedings{bb242514,
AUTHOR = "Messina, N. and Falchi, F. and Esuli, A. and Amato, G.",
TITLE = "Transformer Reasoning Network for Image-Text Matching and Retrieval",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "5222-5229",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237429"}
@inproceedings{bb242515,
AUTHOR = "Zhang, Q. and Lei, Z. and Zhang, Z.X. and Li, S.Z.",
TITLE = "Context-Aware Attention Network for Image-Text Retrieval",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "3533-3542",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237430"}
@inproceedings{bb242516,
AUTHOR = "Chen, Y.C. and Li, L.J. and Yu, L.C. and El Kholy, A. and Ahmed, F. and Gan, Z. and Cheng, Y. and Liu, J.J.",
TITLE = "Uniter: Universal Image-Text Representation Learning",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XXX: 104-120",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237431"}
@inproceedings{bb242517,
AUTHOR = "Wang, H.R. and Zhang, Y. and Ji, Z. and Pang, Y.W. and Ma, L.",
TITLE = "Consensus-aware Visual-semantic Embedding for Image-Text Matching",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XXIV:18-34",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237432"}
@inproceedings{bb242518,
AUTHOR = "Chen, T.L. and Deng, J.J. and Luo, J.B.",
TITLE = "Adaptive Offline Quintuplet Loss for Image-text Matching",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XIII:549-565",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237433"}
@inproceedings{bb242519,
AUTHOR = "Lee, K.H. and Chen, X. and Hua, G. and Hu, H.D. and He, X.D.",
TITLE = "Stacked Cross Attention for Image-Text Matching",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "II: 212-228",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237434"}
@inproceedings{bb242520,
AUTHOR = "Plummer, B.A. and Kordas, P. and Kiapour, M.H. and Zheng, S. and Piramuthu, R. and Lazebnik, S.",
TITLE = "Conditional Image-Text Embedding Networks",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XII: 258-274",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT237435"}
@article{bb242521,
AUTHOR = "Yang, Z.Y. and Kumar, T. and Chen, T.L. and Su, J.S. and Luo, J.B.",
TITLE = "Grounding-Tracking-Integration",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "9",
MONTH = "September",
PAGES = "3433-3443",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237436"}
@article{bb242522,
AUTHOR = "Zhai, S.L. and Guo, G.B. and Yuan, F.J. and Liu, Y. and Wang, X.W.",
TITLE = "VSE-fs: Fast Full-Sample Visual Semantic Embedding",
JOURNAL = IEEE_Int_Sys,
VOLUME = "36",
YEAR = "2021",
NUMBER = "4",
MONTH = "July",
PAGES = "3-12",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237437"}
@article{bb242523,
AUTHOR = "Bargal, S.A. and Zunino, A. and Petsiuk, V. and Zhang, J.M. and Saenko, K. and Murino, V. and Sclaroff, S.",
TITLE = "Guided Zoom: Zooming into Network Evidence to Refine Fine-Grained
Model Decisions",
JOURNAL = PAMI,
VOLUME = "43",
YEAR = "2021",
NUMBER = "11",
MONTH = "November",
PAGES = "4196-4202",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237438"}
@article{bb242524,
AUTHOR = "Hong, R.C. and Liu, D. and Mo, X.Y. and He, X.N. and Zhang, H.W.",
TITLE = "Learning to Compose and Reason with Language Tree Structures for
Visual Grounding",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "2",
MONTH = "February",
PAGES = "684-696",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237439"}
@inproceedings{bb242525,
AUTHOR = "Tang, K.H. and Zhang, H.W. and Wu, B.Y. and Luo, W.H. and Liu, W.",
TITLE = "Learning to Compose Dynamic Tree Structures for Visual Contexts",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6612-6621",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237440"}
@article{bb242526,
AUTHOR = "Bin, Y. and Ding, Y.J. and Peng, B. and Peng, L. and Yang, Y. and Chua, T.S.",
TITLE = "Entity Slot Filling for Visual Captioning",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "1",
MONTH = "January",
PAGES = "52-62",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237441"}
@article{bb242527,
AUTHOR = "Chu, C. and Oliveira, V. and Virgo, F.G. and Otani, M. and Garcia, N. and Nakashima, Y.",
TITLE = "The semantic typology of visually grounded paraphrases",
JOURNAL = CVIU,
VOLUME = "215",
YEAR = "2022",
PAGES = "103333",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237442"}
@article{bb242528,
AUTHOR = "Deng, C.R. and Wu, Q. and Wu, Q.Y. and Hu, F.Y. and Lyu, F. and Tan, M.K.",
TITLE = "Visual Grounding Via Accumulated Attention",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "3",
MONTH = "March",
PAGES = "1670-1684",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237443"}
@inproceedings{bb242529,
AUTHOR = "Tan, M.K. and Lyu, F. and Hu, F.Y. and Wu, Q.Y. and Wu, Q. and Deng, C.R.",
TITLE = "Visual Grounding Via Accumulated Attention",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7746-7755",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237443"}
@article{bb242530,
AUTHOR = "Yu, X.T. and Zhang, H.M. and Hong, R.X. and Song, Y.Q. and Zhang, C.S.",
TITLE = "VD-PCR: Improving visual dialog with pronoun coreference resolution",
JOURNAL = PR,
VOLUME = "125",
YEAR = "2022",
PAGES = "108540",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237444"}
@article{bb242531,
AUTHOR = "Yuan, Y.T. and Ma, L. and Wang, J.W. and Liu, W. and Zhu, W.W.",
TITLE = "Semantic Conditioned Dynamic Modulation for Temporal Sentence
Grounding in Videos",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "5",
MONTH = "May",
PAGES = "2725-2741",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237445"}
@article{bb242532,
AUTHOR = "He, S. and Yang, X.F. and Lin, G.S.",
TITLE = "Learning language to symbol and language to vision mapping for visual
grounding",
JOURNAL = IVC,
VOLUME = "122",
YEAR = "2022",
PAGES = "104451",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237446"}
@article{bb242533,
AUTHOR = "Jiang, W.H. and Zhu, M. and Fang, Y.M. and Shi, G.M. and Zhao, X.W. and Liu, Y.",
TITLE = "Visual Cluster Grounding for Image Captioning",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "3920-3934",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237447"}
@article{bb242534,
AUTHOR = "Liao, Y. and Zhang, A. and Chen, Z.Y. and Hui, T.R. and Liu, S.",
TITLE = "Progressive Language-Customized Visual Feature Learning for One-Stage
Visual Grounding",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "4266-4277",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237448"}
@article{bb242535,
AUTHOR = "Nayyeri, M. and Xu, C.J. and Alam, M.M. and Lehmann, J. and Yazdi, H.S.",
TITLE = "LogicENN: A Neural Based Knowledge Graphs Embedding Model With
Logical Rules",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "7050-7062",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237449"}
@article{bb242536,
AUTHOR = "Chen, T.B. and Wang, W. and Han, K. and Xu, H.J.",
TITLE = "SaGCN: Semantic-Aware Graph Calibration Network for Temporal Sentence
Grounding",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "3003-3016",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237450"}
@article{bb242537,
AUTHOR = "Zhang, H. and Sun, A. and Jing, W. and Zhou, J.T.Y.",
TITLE = "Temporal Sentence Grounding in Videos: A Survey and Future Directions",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "8",
MONTH = "August",
PAGES = "10443-10465",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237451"}
@article{bb242538,
AUTHOR = "Deng, J.J. and Yang, Z.Y. and Liu, D. and Chen, T.L. and Zhou, W.G. and Zhang, Y. and Li, H.Q. and Ouyang, W.L.",
TITLE = "TransVG++: End-to-End Visual Grounding With Language Conditioned
Vision Transformer",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "11",
MONTH = "November",
PAGES = "13636-13652",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237452"}
@inproceedings{bb242539,
AUTHOR = "Deng, J.J. and Yang, Z.Y. and Chen, T.L. and Zhou, W.G. and Li, H.Q.",
TITLE = "TransVG: End-to-End Visual Grounding with Transformers",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1749-1759",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237453"}
@article{bb242540,
AUTHOR = "Li, J.C. and Tang, S.L. and Zhu, L.C. and Zhang, W.Q. and Yang, Y. and Chua, T.S. and Wu, F. and Zhuang, Y.T.",
TITLE = "Variational Cross-Graph Reasoning and Adaptive Structured Semantics
Learning for Compositional Temporal Grounding",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "12601-12617",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237454"}
@inproceedings{bb242541,
AUTHOR = "Li, J.C. and Xie, J.L. and Qian, L. and Zhu, L.C. and Tang, S.L. and Wu, F. and Yang, Y. and Zhuang, Y.T. and Wang, X.E.",
TITLE = "Compositional Temporal Grounding with Structured Variational
Cross-Graph Correspondence Learning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3022-3031",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237455"}
@article{bb242542,
AUTHOR = "Gonzalez, C. and Ayobi, N. and Hernandez, I. and Pont Tuset, J. and Arbelaez, P.",
TITLE = "PiGLET:
Pixel-Level Grounding of Language Expressions With Transformers",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "12206-12221",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237456"}
@article{bb242543,
AUTHOR = "Zhang, R.S. and Wang, C. and Liu, C.L.",
TITLE = "Cycle-Consistent Weakly Supervised Visual Grounding With Individual
and Contextual Representations",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "5167-5180",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237457"}
@article{bb242544,
AUTHOR = "Wang, Y. and Su, Y.T. and Li, W.H. and Xiao, J. and Li, X.Y. and Liu, A.A.",
TITLE = "Dual-Path Rare Content Enhancement Network for Image and Text
Matching",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "6144-6158",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237458"}
@article{bb242545,
AUTHOR = "Luo, F. and Chen, S.X. and Chen, J.J. and Wu, Z.X. and Jiang, Y.G.",
TITLE = "Self-Supervised Learning for Semi-Supervised Temporal Language
Grounding",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "7747-7757",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237459"}
@article{bb242546,
AUTHOR = "Liu, D.Z. and Fang, X. and Hu, W. and Zhou, P.",
TITLE = "Exploring Optical-Flow-Guided Motion and Detection-Based Appearance
for Temporal Sentence Grounding",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "8539-8553",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237460"}
@article{bb242547,
AUTHOR = "Yang, X.F. and Liu, F. and Lin, G.S.",
TITLE = "Effective End-to-End Vision Language Pretraining With Semantic Visual
Loss",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "8408-8417",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237461"}
@article{bb242548,
AUTHOR = "Ma, G.Q. and Bai, Y. and Zhang, W. and Yao, T. and Shihada, B. and Mei, T.",
TITLE = "Boosting Generic Visual-Linguistic Representation With Dynamic
Contexts",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "8445-8457",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237462"}
@article{bb242549,
AUTHOR = "Su, C. and Li, Z. and Lei, T.Y. and Peng, D.Z. and Wang, X.",
TITLE = "MetaVG: A Meta-Learning Framework for Visual Grounding",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "236-240",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237463"}
@article{bb242550,
AUTHOR = "Fang, X. and Liu, D. and Zhou, P. and Xu, Z.C. and Li, R.X.",
TITLE = "Hierarchical Local-Global Transformer for Temporal Sentence Grounding",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "3263-3277",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237464"}
@article{bb242551,
AUTHOR = "Wang, Z.Y. and Yang, C. and Jiang, B. and Yuan, J.S.",
TITLE = "A Dual Reinforcement Learning Framework for Weakly Supervised Phrase
Grounding",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "394-405",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237465"}
@article{bb242552,
AUTHOR = "Wang, W.K. and Su, Y.T. and Liu, J. and Jing, P.G.",
TITLE = "Adaptive proposal network based on generative adversarial learning
for weakly supervised temporal sentence grounding",
JOURNAL = PRL,
VOLUME = "179",
YEAR = "2024",
PAGES = "9-16",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237466"}
@article{bb242553,
AUTHOR = "Liu, M. and Zhou, D. and Guo, J. and Luo, X. and Gao, Z. and Nie, L.Q.",
TITLE = "Semantic-Aware Contrastive Learning With Proposal Suppression for
Video Semantic Role Grounding",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "4",
MONTH = "April",
PAGES = "3003-3016",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237467"}
@article{bb242554,
AUTHOR = "Tang, W. and Li, L. and Liu, X.J. and Jin, L. and Tang, J.H. and Li, Z.C.",
TITLE = "Context Disentangling and Prototype Inheriting for Robust Visual
Grounding",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "3213-3229",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237468"}
@article{bb242555,
AUTHOR = "Shao, R. and Wu, T.X. and Wu, J.L. and Nie, L.Q. and Liu, Z.W.",
TITLE = "Detecting and Grounding Multi-Modal Media Manipulation and Beyond",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "8",
MONTH = "August",
PAGES = "5556-5574",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237469"}
@inproceedings{bb242556,
AUTHOR = "Shao, R. and Wu, T.X. and Liu, Z.W.",
TITLE = "Detecting and Grounding Multi-Modal Media Manipulation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6904-6913",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237470"}
@article{bb242557,
AUTHOR = "Chen, L. and Deng, Z. and Liu, L.B. and Yin, S.",
TITLE = "Multilevel Semantic Interaction Alignment for Video-Text Cross-Modal
Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "7",
MONTH = "July",
PAGES = "6559-6575",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237471"}
@article{bb242558,
AUTHOR = "Wu, W. and Cao, M. and Hu, Y. and Peng, Y. and Qin, L. and Yin, Q.",
TITLE = "Visual Grounding With Dual Knowledge Distillation",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "10",
MONTH = "October",
PAGES = "10399-10410",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237472"}
@article{bb242559,
AUTHOR = "Li, S.T. and Li, B. and Sun, B. and Weng, Y.X.",
TITLE = "Towards Visual-Prompt Temporal Answer Grounding in Instructional
Video",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "8836-8853",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237473"}
@article{bb242560,
AUTHOR = "Qi, Z.B. and Yuan, Y. and Ruan, X.W. and Wang, S.H. and Zhang, W.G. and Huang, Q.M.",
TITLE = "Collaborative Debias Strategy for Temporal Sentence Grounding in
Video",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "11",
MONTH = "November",
PAGES = "10972-10986",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237474"}
@article{bb242561,
AUTHOR = "Wang, C.L. and Feng, W.Q. and Lyu, S.C. and Cheng, G.L. and Li, X.T. and Liu, B.H. and Zhao, Q.",
TITLE = "A Masked Reference Token Supervision-Based Iterative Visual-Language
Framework for Robust Visual Grounding",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "75-90",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237475"}
@inproceedings{bb242562,
AUTHOR = "Li, M.H. and Wang, C.L. and Feng, W.Q. and Lyu, S.C. and Cheng, G.L. and Li, X.T. and Liu, B.H. and Zhao, Q.",
TITLE = "Iterative Robust Visual Grounding with Masked Reference based
Centerpoint Supervision",
BOOKTITLE = VLAR23,
YEAR = "2023",
PAGES = "4653-4658",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237476"}
@article{bb242563,
AUTHOR = "Liu, H. and Tan, Z.C. and Chen, Q. and Wei, Y.C. and Zhao, Y. and Wang, J.D.",
TITLE = "Unified Frequency-Assisted Transformer Framework for Detecting and
Grounding Multi-modal Manipulation",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "3",
MONTH = "March",
PAGES = "1392-1409",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237477"}
@article{bb242564,
AUTHOR = "Ding, Y. and Wang, D. and Li, K. and Zhao, X.H. and Wang, Y.F.",
TITLE = "Visual grounding of remote sensing images with multi-dimensional
semantic-guidance",
JOURNAL = PRL,
VOLUME = "189",
YEAR = "2025",
PAGES = "85-91",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237478"}
@article{bb242565,
AUTHOR = "Li, T.Y. and Wang, C. and Tian, S. and Zhang, B. and Wu, F. and Tang, Y.X. and Zhang, H.",
TITLE = "TACMT: Text-aware cross-modal transformer for visual grounding on
high-resolution SAR images",
JOURNAL = PandRS,
VOLUME = "222",
YEAR = "2025",
PAGES = "152-166",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237479"}
@article{bb242566,
AUTHOR = "Han, T.T. and Wang, K. and Yu, J. and Zhao, S.C. and Fan, J.P.",
TITLE = "Adversarial temporal sentence grounding by learning from external
data",
JOURNAL = PR,
VOLUME = "165",
YEAR = "2025",
PAGES = "111621",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237480"}
@article{bb242567,
AUTHOR = "Guan, R.W. and Jia, L. and Yao, S. and Yang, F.Y.F. and Xu, S. and Purwanto, E. and Zhu, X.H. and Man, K.L. and Lim, E.G. and Smith, J. and Hu, X.M. and Yue, Y.T.",
TITLE = "WaterVG: Waterway Visual Grounding Based on Text-Guided Vision and
mmWave Radar",
JOURNAL = ITS,
VOLUME = "26",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "7275-7291",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237481"}
@article{bb242568,
AUTHOR = "Choudhury, S. and Kurkure, P. and Banerjee, B.",
TITLE = "Improving visual grounding in remote sensing images with adaptive
modality guidance",
JOURNAL = PandRS,
VOLUME = "224",
YEAR = "2025",
PAGES = "42-58",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237482"}
@article{bb242569,
AUTHOR = "Li, Y.X. and Wang, Z. and Liang, W.",
TITLE = "R2G: Reasoning to ground in 3D scenes",
JOURNAL = PR,
VOLUME = "168",
YEAR = "2025",
PAGES = "111728",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237483"}
@article{bb242570,
AUTHOR = "Xie, M.H. and Wang, M.Z. and Li, H.F. and Zhang, Y.F. and Tao, D.P. and Yu, Z.T.",
TITLE = "Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive
Position Correction for Visual Grounding",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "3979-3991",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237484"}
@article{bb242571,
AUTHOR = "Geng, L. and Yin, J.Q. and Chen, G. and Jia, Q.X.",
TITLE = "Pseudo-EV: Enhancing 3D Visual Grounding With Pseudo Embodied
Viewpoint",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "8031-8044",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237485"}
@article{bb242572,
AUTHOR = "Zhu, H. and Gao, T.Q. and Li, Z.X. and Chen, Z.P. and Li, Q. and Miao, K. and Hou, B. and Jiao, L.C.",
TITLE = "Cascaded Hierarchical Attention with Adaptive Fusion for Visual
Grounding in Remote Sensing",
JOURNAL = RS,
VOLUME = "17",
YEAR = "2025",
NUMBER = "17",
PAGES = "2930",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237486"}
@article{bb242573,
AUTHOR = "Chi, H. and Qin, W.W. and Chen, X.Y. and Guo, W.X. and An, B.",
TITLE = "TVI-MFAN: A Text-Visual Interaction Multilevel Feature Alignment
Network for Visual Grounding in Remote Sensing",
JOURNAL = RS,
VOLUME = "17",
YEAR = "2025",
NUMBER = "17",
PAGES = "2993",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237487"}
@article{bb242574,
AUTHOR = "Liu, D. and Hu, W.",
TITLE = "Imperceptible Backdoor Attacks on Text-Guided 3D Scene Grounding",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "5466-5479",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237488"}
@article{bb242575,
AUTHOR = "Bu, Y.Q. and Wu, X. and Cai, Y. and Liu, Q. and Wang, T. and Huang, Q.",
TITLE = "Error-Aware Generative Reasoning for Zero-Shot Visual Grounding",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "4844-4855",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237489"}
@article{bb242576,
AUTHOR = "Ran, R. and Wei, J. and Zhou, Y.Y. and Guan, X. and Yang, Y. and Shen, H.T.",
TITLE = "HCFMN: Hierarchical Cross-Modal Fine-Grained Mining Network for
Temporal Sentence Grounding",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "6462-6474",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237490"}
@article{bb242577,
AUTHOR = "Wang, M.Z. and Li, H.F. and Zhang, Y.F. and Li, J.X. and Xie, M.H. and Tao, D.P.",
TITLE = "Dual-Task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval
and Grounding",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "5879-5894",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237491"}
@article{bb242578,
AUTHOR = "Dong, L. and Zhang, H. and Zhang, H.J. and Huang, Y.F. and Ling, Z.H. and Qiao, Y. and Wang, L.M. and Wang, Y.",
TITLE = "Weakly Supervised Temporal Sentence Grounding via Positive Sample
Mining",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "10",
MONTH = "October",
PAGES = "10396-10409",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237492"}
@article{bb242579,
AUTHOR = "Zhu, Z.H. and Huang, Y.F. and Zhang, M.F. and Ouyang, L.Y. and Sato, Y.",
TITLE = "Prompt-Augmented Boundary Attentive Learning for Weakly Supervised
Temporal Sentence Grounding",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "11404-11415",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237493"}
@inproceedings{bb242580,
AUTHOR = "Huang, Y.F. and Yang, L. and Sato, Y.",
TITLE = "Weakly Supervised Temporal Sentence Grounding with Uncertainty-Guided
Self-training",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18908-18918",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237494"}
@article{bb242581,
AUTHOR = "Xu, X.X. and Yuan, Y.T. and Zhang, Q.D. and Wu, W.H. and Jie, Z.Q. and Ma, L. and Wang, X.",
TITLE = "Weakly-Supervised 3D Visual Grounding Based on Visual Language
Alignment",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "7662-7674",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237495"}
@inproceedings{bb242582,
AUTHOR = "Liu, Y.F. and Wan, B. and Ma, L. and He, X.M.",
TITLE = "Relation-aware Instance Refinement for Weakly Supervised Visual
Grounding",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "5608-5617",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237496"}
@article{bb242583,
AUTHOR = "Dai, M. and Cheng, W.X. and Liu, J.J. and Yang, L.F. and Feng, Z.H. and Yang, W.K. and Wang, J.D.",
TITLE = "Improving Generalized Visual Grounding With Instance-Aware Joint
Learning",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "448-465",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237497"}
@article{bb242584,
AUTHOR = "Zhu, Y. and Chen, D. and Wang, H. and Jia, T. and Deng, S.Z.",
TITLE = "DCART: A dual contrastive alignment residual transformer model for
visual grounding",
JOURNAL = PR,
VOLUME = "172",
YEAR = "2026",
PAGES = "112688",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237498"}
@article{bb242585,
AUTHOR = "Shi, L.T. and Liu, T. and Hu, X.T. and Hu, Y. and Yin, Q. and Hong, R.C.",
TITLE = "SwimVG: Step-Wise Multimodal Fusion and Adaption for Visual Grounding",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "9776-9787",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237499"}
@article{bb242586,
AUTHOR = "Fu, Z. and Mao, Z.D. and Zhang, L. and Zhang, Y.D.",
TITLE = "Boosting Faithful Multi-Modal LLMs via Complementary Visual Grounding",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "8641-8655",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237500"}
@article{bb242587,
AUTHOR = "Hu, M. and Yang, K. and Li, J.",
TITLE = "Text-Injected Discriminative Model for Remote Sensing Visual
Grounding",
JOURNAL = RS,
VOLUME = "18",
YEAR = "2026",
NUMBER = "1",
PAGES = "161",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237501"}
@article{bb242588,
AUTHOR = "Xiao, L.H. and Yang, X.S. and Lan, X.Y. and Wang, Y.W. and Xu, C.S.",
TITLE = "Toward Visual Grounding: A Survey",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "2749-2771",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237502"}
@article{bb242589,
AUTHOR = "Zhou, Y. and Chen, J. and Zhang, Z. and Huang, P.H. and Ding, R. and Zou, Z.T. and Gao, P. and Wei, Y.C. and Li, K. and Yang, X. and Jiang, X. and Yang, H.X. and Li, J.",
TITLE = "DVGBench: Implicit-to-explicit visual grounding benchmark in UAV
imagery with large vision-language models",
JOURNAL = PandRS,
VOLUME = "232",
YEAR = "2026",
PAGES = "831-847",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237503"}
@article{bb242590,
AUTHOR = "Ren, Y.L. and Du, J.Y. and Liu, X. and Su, Q.X. and Deng, Y. and Li, H.J.",
TITLE = "MTRAG: Multi-Target Referring and Grounding via Hybrid
Semantic-Spatial Integration",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "2167-2181",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237504"}
@article{bb242591,
AUTHOR = "Dai, M. and Chen, K. and Cheng, W.X. and Zhuang, J. and Feng, Z.H. and Zhu, P.F. and Yang, W.K.",
TITLE = "GC3VG: Generalized Multi-Task Visual Grounding With Coarse-to-Fine
Consistency Constraints",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "4",
MONTH = "April",
PAGES = "4827-4841",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237505"}
@inproceedings{bb242592,
AUTHOR = "Iwakata, S. and Oshima, R. and Tsunashima, H. and Feng, Q. and Kataoka, H. and Morishima, S.",
TITLE = "Viewpoint-Dependent 3D Visual Grounding for Mobile Robots",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "1690-1695",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237506"}
@inproceedings{bb242593,
AUTHOR = "Zhao, H.R. and Chen, T.Y. and Wang, Z.",
TITLE = "On the Robustness of GUI Grounding Models Against Image Attacks",
BOOKTITLE = TrustworthyOpen25,
YEAR = "2025",
PAGES = "1609-1614",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237507"}
@inproceedings{bb242594,
AUTHOR = "Zheng, Y.H. and Lin, G.S. and Chang, K.Y.",
TITLE = "Transformer-based Visual Grounding with Inter-Modality Cross
Attention",
BOOKTITLE = MVA25,
YEAR = "2025",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237508"}
@inproceedings{bb242595,
AUTHOR = "Lin, X.W. and Lin, T.W. and Huang, L.C. and Xie, H.Y. and Su, Z.Z.",
TITLE = "BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "9007-9016",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237509"}
@inproceedings{bb242596,
AUTHOR = "Chang, Y. and Fermoselle, L. and Ta, D. and Bucher, B. and Carlone, L. and Wang, J.",
TITLE = "ASHiTA: Automatic Scene-Grounded HIerarchical Task Analysis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29458-29468",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237510"}
@inproceedings{bb242597,
AUTHOR = "Yang, Y. and Yang, H. and Zhou, J.C. and Chen, P.H. and Zhang, H.X. and Du, Y.L. and Gan, C.",
TITLE = "3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "17294-17303",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237511"}
@inproceedings{bb242598,
AUTHOR = "Peng, Q.H. and Zheng, H. and Huang, G.",
TITLE = "ProxyTransformation: Preshaping Point Cloud Manifold With Proxy
Attention For 3D Visual Grounding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24582-24592",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237512"}
@inproceedings{bb242599,
AUTHOR = "Zong, Y.S. and Zhang, Q. and An, D.S. and Li, Z.H. and Xu, X. and Xu, L.H. and Tu, Z.W. and Xing, Y.F. and Dabeer, O.",
TITLE = "Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24635-24645",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237513"}
Last update:Apr 23, 2026 at 15:05:02