@inproceedings{bb242000,
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#TT236916"}
@inproceedings{bb242001,
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#TT236917"}
@inproceedings{bb242002,
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#TT236918"}
@inproceedings{bb242003,
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#TT236919"}
@inproceedings{bb242004,
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#TT236920"}
@inproceedings{bb242005,
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#TT236921"}
@inproceedings{bb242006,
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#TT236922"}
@inproceedings{bb242007,
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#TT236923"}
@inproceedings{bb242008,
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#TT236924"}
@article{bb242009,
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#TT236925"}
@article{bb242010,
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#TT236926"}
@article{bb242011,
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#TT236927"}
@article{bb242012,
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#TT236928"}
@inproceedings{bb242013,
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#TT236929"}
@article{bb242014,
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#TT236930"}
@article{bb242015,
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#TT236931"}
@article{bb242016,
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#TT236932"}
@inproceedings{bb242017,
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#TT236932"}
@article{bb242018,
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#TT236933"}
@article{bb242019,
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#TT236934"}
@article{bb242020,
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#TT236935"}
@article{bb242021,
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#TT236936"}
@article{bb242022,
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#TT236937"}
@article{bb242023,
AUTHOR = "Ding, X.P. and Wang, N.N. and Zhang, S.W. and Huang, Z.Y. and Li, X.M. and Tang, M.Q. and Liu, T.L. and Gao, X.B.",
TITLE = "Exploring Language Hierarchy for Video Grounding",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "4693-4706",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236938"}
@article{bb242024,
AUTHOR = "Xu, Z. and Chen, D. and Wei, K. and Deng, C. and Xue, H.",
TITLE = "HiSA: Hierarchically Semantic Associating for Video Temporal
Grounding",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "5178-5188",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236939"}
@article{bb242025,
AUTHOR = "Gao, J.L. and Sun, X. and Ghanem, B. and Zhou, X. and Ge, S.M.",
TITLE = "Efficient Video Grounding With Which-Where Reading Comprehension",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "10",
MONTH = "October",
PAGES = "6900-6913",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236940"}
@article{bb242026,
AUTHOR = "Zhou, H. and Zhang, C.Y. and Luo, Y. and Hu, C.P. and Zhang, W.J.",
TITLE = "Thinking Inside Uncertainty: Interest Moment Perception for Diverse
Temporal Grounding",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "10",
MONTH = "October",
PAGES = "7190-7203",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236941"}
@article{bb242027,
AUTHOR = "Tang, Z.H. and Liao, Y. and Liu, S. and Li, G.B. and Jin, X.J. and Jiang, H.X. and Yu, Q. and Xu, D.",
TITLE = "Human-Centric Spatio-Temporal Video Grounding With Visual
Transformers",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "8238-8249",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236942"}
@article{bb242028,
AUTHOR = "Wang, W. and Gao, J.Y. and Xu, C.S.",
TITLE = "Weakly-Supervised Video Object Grounding via Causal Intervention",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "3",
MONTH = "March",
PAGES = "3933-3948",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236943"}
@article{bb242029,
AUTHOR = "Wang, W. and Gao, J.Y. and Xu, C.S.",
TITLE = "Weakly-Supervised Video Object Grounding via Learning Uni-Modal
Associations",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "6329-6340",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236944"}
@article{bb242030,
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#TT236945"}
@article{bb242031,
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#TT236946"}
@article{bb242032,
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#TT236947"}
@article{bb242033,
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#TT236948"}
@inproceedings{bb242034,
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#TT236949"}
@article{bb242035,
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#TT236950"}
@inproceedings{bb242036,
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#TT236951"}
@article{bb242037,
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#TT236952"}
@article{bb242038,
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#TT236953"}
@article{bb242039,
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#TT236954"}
@article{bb242040,
AUTHOR = "Xu, Z. and Wei, K. and Yang, X. and Deng, C.",
TITLE = "Point-Supervised Video Temporal Grounding",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "6121-6131",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236955"}
@article{bb242041,
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#TT236956"}
@article{bb242042,
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#TT236957"}
@article{bb242043,
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#TT236958"}
@article{bb242044,
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#TT236959"}
@article{bb242045,
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#TT236960"}
@article{bb242046,
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#TT236961"}
@article{bb242047,
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#TT236962"}
@article{bb242048,
AUTHOR = "Lu, Y. and Quan, R.J. and Zhu, L.C. and Yang, Y.",
TITLE = "Zero-Shot Video Grounding With Pseudo Query Lookup and Verification",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "1643-1654",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236963"}
@article{bb242049,
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#TT236964"}
@article{bb242050,
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#TT236965"}
@article{bb242051,
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#TT236966"}
@article{bb242052,
AUTHOR = "Shi, F.Y. and Huang, W.L. and Wang, L.M.",
TITLE = "End-to-end dense video grounding via parallel regression",
JOURNAL = CVIU,
VOLUME = "242",
YEAR = "2024",
PAGES = "103980",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236967"}
@article{bb242053,
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#TT236968"}
@inproceedings{bb242054,
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#TT236969"}
@article{bb242055,
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#TT236970"}
@article{bb242056,
AUTHOR = "Wu, Q.Q. and Guo, L.J. and Zhang, R. and Qian, J.B. and Gao, S.",
TITLE = "QSMT-net: A query-sensitive proposal and multi-temporal-span matching
network for video grounding",
JOURNAL = IVC,
VOLUME = "149",
YEAR = "2024",
PAGES = "105188",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236971"}
@article{bb242057,
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#TT236972"}
@article{bb242058,
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#TT236973"}
@inproceedings{bb242059,
AUTHOR = "Fang, X. and Xiong, Z. and Fang, W.L. and Qu, X.Y. and Chen, C. and Dongd, J.F. and Tang, K. and Zhou, P. and Cheng, Y. and Liu, D.Z.",
TITLE = "Rethinking Weakly-supervised Video Temporal Grounding From a Game
Perspective",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLV: 290-311",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236974"}
@article{bb242060,
AUTHOR = "Xiong, Z. and Liu, D.Z. and Fang, X. and Qu, X.Y. and Dong, J.F. and Zhu, J.H. and Tang, K. and Zhou, P.",
TITLE = "Rethinking Video Sentence Grounding from a Tracking Perspective With
Memory Network and Masked Attention",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "11204-11218",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236975"}
@article{bb242061,
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#TT236976"}
@article{bb242062,
AUTHOR = "Dong, J.X. and Yin, Z.Z.",
TITLE = "Graph-based Dense Event Grounding with relative positional encoding",
JOURNAL = CVIU,
VOLUME = "251",
YEAR = "2025",
PAGES = "104257",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236977"}
@article{bb242063,
AUTHOR = "Tang, K.F. and He, L.H. and Wang, N.N. and Gao, X.B.",
TITLE = "Dual Semantic Reconstruction Network for Weakly Supervised Temporal
Sentence Grounding",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "95-107",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236978"}
@article{bb242064,
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#TT236979"}
@inproceedings{bb242065,
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#TT236980"}
@article{bb242066,
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#TT236981"}
@article{bb242067,
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#TT236982"}
@article{bb242068,
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#TT236983"}
@article{bb242069,
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#TT236984"}
@article{bb242070,
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#TT236985"}
@article{bb242071,
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#TT236986"}
@article{bb242072,
AUTHOR = "Liu, K. and Qu, M.X. and Liu, Y. and Wei, Y.C. and Zhe, W.M. and Zhao, Y. and Liu, W.",
TITLE = "Single-Frame Supervision for Spatio-Temporal Video Grounding",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "5177-5191",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236987"}
@article{bb242073,
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#TT236988"}
@article{bb242074,
AUTHOR = "Hu, J.J. and Guo, D. and Li, K. and Si, Z. and Yang, X. and Chang, X.J. and Wang, M.",
TITLE = "Unified Static and Dynamic Network: Efficient Temporal Filtering for
Video Grounding",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "6445-6462",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT236989"}
@article{bb242075,
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#TT236990"}
@article{bb242076,
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#TT236991"}
@article{bb242077,
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#TT236992"}
@article{bb242078,
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#TT236993"}
@article{bb242079,
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#TT236994"}
@article{bb242080,
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#TT236995"}
@article{bb242081,
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#TT236996"}
@article{bb242082,
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#TT236997"}
@article{bb242083,
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#TT236998"}
@article{bb242084,
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#TT236999"}
@inproceedings{bb242085,
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#TT237000"}
@article{bb242086,
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#TT237001"}
@inproceedings{bb242087,
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#TT237002"}
@article{bb242088,
AUTHOR = "Ran, R. and Wei, J. and He, S.Y. and Zhou, Y.Y. and Wang, P. and Yang, Y. and Shen, H.T.",
TITLE = "Fine-Grained Alignment and Interaction for Video Grounding With
Cross-Modal Semantic Hierarchical Graph",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "11641-11654",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237003"}
@article{bb242089,
AUTHOR = "Wang, M.Z. and Li, H.F. and Zhang, Y.F. and Li, J.X. and Tao, D.P. and Yu, Z.T.",
TITLE = "Disentangling Inter- and Intra-Video Relations for Multi-Event
Video-Text Retrieval and Grounding",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "7558-7571",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237004"}
@article{bb242090,
AUTHOR = "Yang, J. and Wei, P.",
TITLE = "Learning unified patterns of multimodalities for video temporal
grounding",
JOURNAL = PR,
VOLUME = "172",
YEAR = "2026",
PAGES = "112484",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237005"}
@article{bb242091,
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#TT237006"}
@article{bb242092,
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#TT237007"}
@article{bb242093,
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#TT237008"}
@article{bb242094,
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#TT237009"}
@article{bb242095,
AUTHOR = "Liu, Y. and Zheng, M.H. and Chen, Q.C. and Gong, S.G. and Peng, Y.X.",
TITLE = "Large-Scale Pre-Trained Models Empowering Phrase Generalization in
Temporal Sentence Localization",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "53",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237010"}
@inproceedings{bb242096,
AUTHOR = "Zheng, M.H. and Cai, X.H. and Chen, Q.C. and Peng, Y.X. and Liu, Y.",
TITLE = "Training-Free Video Temporal Grounding Using Large-Scale Pre-Trained
Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXII: 20-37",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237011"}
@article{bb242097,
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#TT237012"}
@article{bb242098,
AUTHOR = "Li, A. and Liu, H.J. and Zhu, Y.Q. and Ge, Y.X.",
TITLE = "Efficient Pre-Trained Semantics Refinement for Video Temporal
Grounding",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "1406-1418",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT237013"}
@article{bb242099,
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#TT237014"}
Last update:Apr 6, 2026 at 11:28:57