@inproceedings{bb213300,
AUTHOR = "Das, A. and Kottur, S. and Moura, J.M.F. and Lee, S. and Batra, D.",
TITLE = "Learning Cooperative Visual Dialog Agents with Deep Reinforcement
Learning",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "2970-2979",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT208378"}
@inproceedings{bb213301,
AUTHOR = "de Vries, H. and Strub, F. and Chandar, S. and Pietquin, O. and Larochelle, H. and Courville, A.",
TITLE = "GuessWhat?! Visual Object Discovery through Multi-modal Dialogue",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "4466-4475",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT208379"}
@inproceedings{bb213302,
AUTHOR = "Nam, H. and Ha, J.W. and Kim, J.",
TITLE = "Dual Attention Networks for Multimodal Reasoning and Matching",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "2156-2164",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT208380"}
@inproceedings{bb213303,
AUTHOR = "Johnson, J. and Hariharan, B. and van der Maaten, L. and Hoffman, J. and Fei Fei, L. and Zitnick, C.L. and Girshick, R.",
TITLE = "Inferring and Executing Programs for Visual Reasoning",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "3008-3017",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT208381"}
@inproceedings{bb213304,
AUTHOR = "Johnson, J. and Hariharan, B. and van der Maaten, L. and Fei Fei, L. and Zitnick, C.L. and Girshick, R.",
TITLE = "CLEVR: A Diagnostic Dataset for Compositional Language and Elementary
Visual Reasoning",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "1988-1997",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT208382"}
@inproceedings{bb213305,
AUTHOR = "Das, A. and Kottur, S. and Gupta, K. and Singh, A. and Yadav, D. and Moura, J.M.F. and Parikh, D. and Batra, D.",
TITLE = "Visual Dialog",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "1080-1089",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT208383"}
@article{bb213306,
AUTHOR = "Zhou, N. and Fan, J.P.",
TITLE = "Automatic image-text alignment for large-scale web image indexing and
retrieval",
JOURNAL = PR,
VOLUME = "48",
YEAR = "2015",
NUMBER = "1",
PAGES = "205-219",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208384"}
@article{bb213307,
AUTHOR = "Huang, F.R. and Zhang, X.M. and Zhao, Z.H. and Li, Z.J.",
TITLE = "Bi-Directional Spatial-Semantic Attention Networks for Image-Text
Matching",
JOURNAL = IP,
VOLUME = "28",
YEAR = "2019",
NUMBER = "4",
MONTH = "April",
PAGES = "2008-2020",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208385"}
@article{bb213308,
AUTHOR = "Otto, C. and Springstein, M. and Anand, A. and Ewerth, R.",
TITLE = "Characterization and classification of semantic image-text relations",
JOURNAL = MultInfoRetr,
VOLUME = "9",
YEAR = "2020",
NUMBER = "1",
MONTH = "March",
PAGES = "31-45",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208386"}
@article{bb213309,
AUTHOR = "Niu, K. and Huang, Y. and Wang, L.",
TITLE = "Re-ranking image-text matching by adaptive metric fusion",
JOURNAL = PR,
VOLUME = "104",
YEAR = "2020",
PAGES = "107351",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208387"}
@article{bb213310,
AUTHOR = "Wen, K.Y. and Gu, X.D. and Cheng, Q.R.",
TITLE = "Learning Dual Semantic Relations With Graph Attention for Image-Text
Matching",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "7",
MONTH = "July",
PAGES = "2866-2879",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208388"}
@article{bb213311,
AUTHOR = "Yang, S. and Li, Q. and Li, W.H. and Li, X. and Liu, A.A.",
TITLE = "Dual-Level Representation Enhancement on Characteristic and Context
for Image-Text Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "11",
MONTH = "November",
PAGES = "8037-8050",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208389"}
@article{bb213312,
AUTHOR = "Jing, Y. and Wang, W. and Wang, L. and Tan, T.N.",
TITLE = "Learning Aligned Image-Text Representations Using Graph Attentive
Relational Network",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "1840-1852",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208390"}
@inproceedings{bb213313,
AUTHOR = "Zhao, F. and Huang, Y.Z. and Wang, L. and Tan, T.N.",
TITLE = "Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval",
BOOKTITLE = CVPR15,
YEAR = "2015",
PAGES = "1556-1564",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208391"}
@article{bb213314,
AUTHOR = "Lan, H. and Zhang, P.",
TITLE = "Learning and Integrating Multi-Level Matching Features for Image-Text
Retrieval",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "374-378",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208392"}
@article{bb213315,
AUTHOR = "Wu, J. and Wu, C.L. and Lu, J. and Wang, L.Q. and Cui, X.R.",
TITLE = "Region Reinforcement Network With Topic Constraint for Image-Text
Matching",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "1",
MONTH = "January",
PAGES = "388-397",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208393"}
@article{bb213316,
AUTHOR = "Malali, N. and Keller, Y.",
TITLE = "Learning to Embed Semantic Similarity for Joint Image-Text Retrieval",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "10252-10260",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208394"}
@article{bb213317,
AUTHOR = "Tian, M.X. and Wu, X.X. and Jia, Y.D.",
TITLE = "Adaptive Latent Graph Representation Learning for Image-Text Matching",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "471-482",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208395"}
@article{bb213318,
AUTHOR = "Li, K.P. and Zhang, Y.L. and Li, K. and Li, Y.Y. and Fu, Y.",
TITLE = "Image-Text Embedding Learning via Visual and Textual Semantic
Reasoning",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "1",
MONTH = "January",
PAGES = "641-656",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208396"}
@inproceedings{bb213319,
AUTHOR = "Li, K.P. and Zhang, Y.L. and Li, K. and Li, Y.Y. and Fu, Y.",
TITLE = "Visual Semantic Reasoning for Image-Text Matching",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "4653-4661",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208397"}
@article{bb213320,
AUTHOR = "Diao, H.W. and Zhang, Y. and Liu, W. and Ruan, X. and Lu, H.C.",
TITLE = "Plug-and-Play Regulators for Image-Text Matching",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "2322-2334",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208398"}
@article{bb213321,
AUTHOR = "Tian, Y.M. and Ding, A. and Wang, D. and Luo, X.M. and Wan, B. and Wang, Y.F.",
TITLE = "Bi-Attention enhanced representation learning for image-text matching",
JOURNAL = PR,
VOLUME = "140",
YEAR = "2023",
PAGES = "109548",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208399"}
@article{bb213322,
AUTHOR = "Zhang, K. and Mao, Z.D. and Liu, A.A. and Zhang, Y.D.",
TITLE = "Unified Adaptive Relevance Distinguishable Attention Network for
Image-Text Matching",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "1320-1332",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208400"}
@article{bb213323,
AUTHOR = "Liu, Z. and Chen, F.L. and Xu, J. and Pei, W.J. and Lu, G.M.",
TITLE = "Image-Text Retrieval With Cross-Modal Semantic Importance Consistency",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "5",
MONTH = "May",
PAGES = "2465-2476",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208401"}
@article{bb213324,
AUTHOR = "Shang, H. and Zhao, G.S. and Shi, J. and Qian, X.M.",
TITLE = "A Multiview Text Imagination Network Based on Latent Alignment for
Image-Text Matching",
JOURNAL = IEEE_Int_Sys,
VOLUME = "38",
YEAR = "2023",
NUMBER = "3",
MONTH = "May",
PAGES = "41-50",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208402"}
@article{bb213325,
AUTHOR = "Liu, C. and Zhang, Y.Q. and Wang, H. and Chen, W.H. and Wang, F. and Huang, Y. and Shen, Y.D. and Wang, L.",
TITLE = "Efficient Token-Guided Image-Text Retrieval With Consistent
Multimodal Contrastive Training",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "3622-3633",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208403"}
@article{bb213326,
AUTHOR = "Li, W.R. and Ma, Z.Y. and Deng, L.J. and Fan, X.P. and Tian, Y.H.",
TITLE = "Neuron-Based Spiking Transmission and Reasoning Network for Robust
Image-Text Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "7",
MONTH = "July",
PAGES = "3516-3528",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208404"}
@article{bb213327,
AUTHOR = "Li, W.R. and Ma, Z.Y. and Shi, J.Q. and Fan, X.P.",
TITLE = "The Style Transformer With Common Knowledge Optimization for
Image-Text Retrieval",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1197-1201",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208405"}
@article{bb213328,
AUTHOR = "Zhu, H.G. and Zhang, C.J. and Wei, Y.C. and Huang, S. and Zhao, Y.",
TITLE = "ESA: External Space Attention Aggregation for Image-Text Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "6131-6143",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208406"}
@article{bb213329,
AUTHOR = "Li, Z. and Guo, C. and Feng, Z. and Hwang, J.N. and Du, Z.T.",
TITLE = "Integrating Language Guidance Into Image-Text Matching for Correcting
False Negatives",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "103-116",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208407"}
@article{bb213330,
AUTHOR = "Zhang, Y. and Ji, Z. and Wang, D. and Pang, Y.W. and Li, X.L.",
TITLE = "USER: Unified Semantic Enhancement With Momentum Contrast for
Image-Text Retrieval",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "595-609",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208408"}
@article{bb213331,
AUTHOR = "Zhuang, J. and Yu, J. and Ding, Y. and Qu, X.Y. and Hu, Y.",
TITLE = "Towards Fast and Accurate Image-Text Retrieval With Self-Supervised
Fine-Grained Alignment",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "1361-1372",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208409"}
@article{bb213332,
AUTHOR = "Liu, X. and He, Y. and Cheung, Y.M. and Xu, X. and Wang, N.N.",
TITLE = "Learning Relationship-Enhanced Semantic Graph for Fine-Grained
Image-Text Matching",
JOURNAL = Cyber,
VOLUME = "54",
YEAR = "2024",
NUMBER = "2",
MONTH = "February",
PAGES = "948-961",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208410"}
@article{bb213333,
AUTHOR = "Li, W.H. and Yang, S. and Li, Q. and Li, X. and Liu, A.A.",
TITLE = "Commonsense-Guided Semantic and Relational Consistencies for
Image-Text Retrieval",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "1867-1880",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208411"}
@article{bb213334,
AUTHOR = "Wu, D.Q. and Li, H.H. and Gu, C. and Liu, H. and Xu, C. and Hou, Y. and Guo, L.",
TITLE = "Feature First: Advancing Image-Text Retrieval Through Improved Visual
Features",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "3827-3841",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208412"}
@article{bb213335,
AUTHOR = "Yang, R. and Wang, S. and Gu, Y. and Wang, J.H. and Sun, Y.Z. and Zhang, H. and Liao, Y. and Jiao, L.C.",
TITLE = "Continual Learning for Cross-Modal Image-Text Retrieval Based on
Domain-Selective Attention",
JOURNAL = PR,
VOLUME = "149",
YEAR = "2024",
PAGES = "110273",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208413"}
@article{bb213336,
AUTHOR = "Pan, R.J. and Yang, H. and Li, C. and Yang, J.H.",
TITLE = "Joint Intra & Inter-Grained Reasoning: A New Look Into Semantic
Consistency of Image-Text Retrieval",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "4912-4925",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208414"}
@article{bb213337,
AUTHOR = "Zhang, K. and Hu, B. and Zhang, H. and Li, Z. and Mao, Z.D.",
TITLE = "Enhanced Semantic Similarity Learning Framework for Image-Text
Matching",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "4",
MONTH = "April",
PAGES = "2973-2988",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208415"}
@inproceedings{bb213338,
AUTHOR = "Fu, Z.R. and Mao, Z.D. and Song, Y. and Zhang, Y.D.",
TITLE = "Learning Semantic Relationship among Instances for Image-Text
Matching",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "15159-15168",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208416"}
@inproceedings{bb213339,
AUTHOR = "Zhang, W. and Xu, X.W. and Tao, Y. and Wang, X.D. and Wang, C. 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#TT208417"}
@inproceedings{bb213340,
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#TT208418"}
@inproceedings{bb213341,
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#TT208419"}
@inproceedings{bb213342,
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#TT208420"}
@inproceedings{bb213343,
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#TT208421"}
@inproceedings{bb213344,
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#TT208422"}
@inproceedings{bb213345,
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#TT208423"}
@inproceedings{bb213346,
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#TT208424"}
@inproceedings{bb213347,
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#TT208425"}
@inproceedings{bb213348,
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#TT208426"}
@inproceedings{bb213349,
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#TT208427"}
@inproceedings{bb213350,
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#TT208428"}
@inproceedings{bb213351,
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#TT208429"}
@inproceedings{bb213352,
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#TT208430"}
@inproceedings{bb213353,
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#TT208431"}
@inproceedings{bb213354,
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#TT208432"}
@inproceedings{bb213355,
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#TT208433"}
@inproceedings{bb213356,
AUTHOR = "Zhang, Y. and Lu, H.C.",
TITLE = "Deep Cross-Modal Projection Learning for Image-Text Matching",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "I: 707-723",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803imt4.html#TT208434"}
@inproceedings{bb213357,
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#TT208435"}
@article{bb213358,
AUTHOR = "Liang, J.W. and Jiang, L. and Cao, L.L. and Kalantidis, Y. and Li, L.J. and Hauptmann, A.G.",
TITLE = "Focal Visual-Text Attention for Memex Question Answering",
JOURNAL = PAMI,
VOLUME = "41",
YEAR = "2019",
NUMBER = "8",
MONTH = "August",
PAGES = "1893-1908",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208437"}
@inproceedings{bb213359,
AUTHOR = "Liang, J.W. and Jiang, L. and Cao, L.L. and Li, L.J. and Hauptmann, A.G.",
TITLE = "Focal Visual-Text Attention for Visual Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "6135-6143",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208438"}
@article{bb213360,
AUTHOR = "Riquelme, F. and de Goyeneche, A. and Zhang, Y.D. and Niebles, J.C. and Soto, A.",
TITLE = "Explaining VQA predictions using visual grounding and a knowledge
base",
JOURNAL = IVC,
VOLUME = "101",
YEAR = "2020",
PAGES = "103968",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208439"}
@article{bb213361,
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#TT208440"}
@article{bb213362,
AUTHOR = "Zhang, W.X. and Ma, C. and Wu, Q. and Yang, X.K.",
TITLE = "Language-Guided Navigation via Cross-Modal Grounding and Alternate
Adversarial Learning",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "9",
MONTH = "September",
PAGES = "3469-3481",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208441"}
@article{bb213363,
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#TT208442"}
@article{bb213364,
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#TT208443"}
@article{bb213365,
AUTHOR = "Yang, W.F. and Zhang, T.Z. and Zhang, Y.D. and Wu, F.",
TITLE = "Local Correspondence Network for Weakly Supervised Temporal Sentence
Grounding",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "3252-3262",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208444"}
@inproceedings{bb213366,
AUTHOR = "Luo, W. and Zhang, T.Z. and Yang, W.F. and Liu, J.G. and Mei, T. and Wu, F. and Zhang, Y.D.",
TITLE = "Action Unit Memory Network for Weakly Supervised Temporal Action
Localization",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "9964-9974",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208445"}
@article{bb213367,
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#TT208446"}
@inproceedings{bb213368,
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#TT208447"}
@article{bb213369,
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#TT208448"}
@article{bb213370,
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#TT208449"}
@article{bb213371,
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#TT208450"}
@inproceedings{bb213372,
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#TT208450"}
@article{bb213373,
AUTHOR = "Plummer, B.A. and Shih, K.J. and Li, Y.C. and Xu, K. and Lazebnik, S. and Sclaroff, S. and Saenko, K.",
TITLE = "Revisiting Image-Language Networks for Open-Ended Phrase Detection",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "4",
MONTH = "April",
PAGES = "2155-2167",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208451"}
@inproceedings{bb213374,
AUTHOR = "Burns, A. and Tan, R. and Saenko, K. and Sclaroff, S. and Plummer, B.A.",
TITLE = "Language Features Matter: Effective Language Representations for
Vision-Language Tasks",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "7473-7482",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208452"}
@inproceedings{bb213375,
AUTHOR = "Arbelle, A. and Doveh, S. and Alfassy, A. and Shtok, J. and Lev, G. and Schwartz, E. and Kuehne, H. and Levi, H.B. and Sattigeri, P. and Panda, R. and Chen, C.F. and Bronstein, A.M. and Saenko, K. and Ullman, S. and Giryes, R. and Feris, R.S. and Karlinsky, L.",
TITLE = "Detector-Free Weakly Supervised Grounding by Separation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1781-1792",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208453"}
@inproceedings{bb213376,
AUTHOR = "Whitehead, S. and Wu, H. and Ji, H. and Feris, R.S. and Saenko, K.",
TITLE = "Separating Skills and Concepts for Novel Visual Question Answering",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "5628-5637",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208454"}
@article{bb213377,
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#TT208455"}
@article{bb213378,
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#TT208456"}
@article{bb213379,
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#TT208457"}
@article{bb213380,
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#TT208458"}
@article{bb213381,
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#TT208459"}
@article{bb213382,
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#TT208460"}
@article{bb213383,
AUTHOR = "Wang, Y. and Deng, J.J. and Zhou, W.G. and Li, H.Q.",
TITLE = "Weakly Supervised Temporal Adjacent Network for Language Grounding",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "3276-3286",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208461"}
@article{bb213384,
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#TT208462"}
@article{bb213385,
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#TT208463"}
@article{bb213386,
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#TT208464"}
@article{bb213387,
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#TT208465"}
@article{bb213388,
AUTHOR = "Tang, H.Y. and Zhu, J. and Wang, L. and Zheng, Q.H. and Zhang, T.W.",
TITLE = "Multi-Level Query Interaction for Temporal Language Grounding",
JOURNAL = ITS,
VOLUME = "23",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "25479-25488",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208466"}
@article{bb213389,
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#TT208467"}
@article{bb213390,
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#TT208468"}
@article{bb213391,
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#TT208469"}
@article{bb213392,
AUTHOR = "Zhao, L.C. and Cai, D.G. and Zhang, J. and Sheng, L. and Xu, D. and Zheng, R. and Zhao, Y.J. and Wang, L.P. and Fan, X.",
TITLE = "Toward Explainable 3D Grounded Visual Question Answering: A New
Benchmark and Strong Baseline",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "2935-2949",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208470"}
@article{bb213393,
AUTHOR = "Zhu, L.J. and Peng, L. and Zhou, W.N. and Yang, J.",
TITLE = "Dual-decoder transformer network for answer grounding in visual
question answering",
JOURNAL = PRL,
VOLUME = "171",
YEAR = "2023",
PAGES = "53-60",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT208471"}
@article{bb213394,
AUTHOR = "Chen, T. 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#TT208472"}
@article{bb213395,
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#TT208473"}
@article{bb213396,
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#TT208474"}
@inproceedings{bb213397,
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#TT208475"}
@article{bb213398,
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#TT208476"}
@inproceedings{bb213399,
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#TT208477"}
Last update:Apr 18, 2024 at 11:38:49