@inproceedings{bb198500,
AUTHOR = "Malinowski, M. and Rohrbach, M. and Fritz, M.",
TITLE = "Ask Your Neurons:
A Neural-Based Approach to Answering Questions about Images",
BOOKTITLE = ICCV15,
YEAR = "2015",
PAGES = "1-9",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193702"}
@article{bb198501,
AUTHOR = "Tamaazousti, Y. and Le Borgne, H. and Popescu, A. and Gadeski, E. and Ginsca, A. and Hudelot, C.",
TITLE = "Vision-language integration using constrained local semantic features",
JOURNAL = CVIU,
VOLUME = "163",
YEAR = "2017",
NUMBER = "1",
PAGES = "41-57",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193703"}
@article{bb198502,
AUTHOR = "Das, A. and Agrawal, H. and Zitnick, L. and Parikh, D. and Batra, D.",
TITLE = "Human Attention in Visual Question Answering:
Do Humans and Deep Networks Look at the Same Regions?",
JOURNAL = CVIU,
VOLUME = "163",
YEAR = "2017",
NUMBER = "1",
PAGES = "90-100",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193704"}
@article{bb198503,
AUTHOR = "Lioutas, V. and Passalis, N. and Tefas, A.",
TITLE = "Explicit ensemble attention learning for improving visual question
answering",
JOURNAL = PRL,
VOLUME = "111",
YEAR = "2018",
PAGES = "51-57",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193705"}
@article{bb198504,
AUTHOR = "Huang, Y.Z. and Zhong, T.",
TITLE = "Multitask learning for neural generative question answering",
JOURNAL = RealTimeIP,
VOLUME = "14",
YEAR = "2018",
NUMBER = "1",
MONTH = "January",
PAGES = "1009-1017",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193706"}
@article{bb198505,
AUTHOR = "Zhang, Q.S. and Wu, Y.N. and Zhang, H. and Zhu, S.C.",
TITLE = "Mining deep And-Or object structures via cost-sensitive
question-answer-based active annotations",
JOURNAL = CVIU,
VOLUME = "176-177",
YEAR = "2018",
PAGES = "33-44",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193707"}
@article{bb198506,
AUTHOR = "Zhang, Q.S. and Ren, J. and Huang, G. and Cao, R.M. and Wu, Y.N. and Zhu, S.C.",
TITLE = "Mining Interpretable AOG Representations From Convolutional Networks
via Active Question Answering",
JOURNAL = PAMI,
VOLUME = "43",
YEAR = "2021",
NUMBER = "11",
MONTH = "November",
PAGES = "3949-3963",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193708"}
@inproceedings{bb198507,
AUTHOR = "Zhang, Q.S. and Cao, R.M. and Wu, Y.N. and Zhu, S.C.",
TITLE = "Mining Object Parts from CNNs via Active Question-Answering",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "3890-3899",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193709"}
@inproceedings{bb198508,
AUTHOR = "Zhang, Q.S. and Wu, Y.N. and Zhu, S.C.",
TITLE = "Mining And-Or Graphs for Graph Matching and Object Discovery",
BOOKTITLE = ICCV15,
YEAR = "2015",
PAGES = "55-63",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193710"}
@article{bb198509,
AUTHOR = "Garg, S. and Srivastava, R.",
TITLE = "Object sequences: encoding categorical and spatial information for a
yes/no visual question answering task",
JOURNAL = IET-CV,
VOLUME = "12",
YEAR = "2018",
NUMBER = "8",
MONTH = "December",
PAGES = "1141-1150",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193711"}
@article{bb198510,
AUTHOR = "Goyal, Y. and Khot, T. and Agrawal, A. and Summers Stay, D. and Batra, D. and Parikh, D.",
TITLE = "Making the V in VQA Matter: Elevating the Role of Image Understanding
in Visual Question Answering",
JOURNAL = IJCV,
VOLUME = "127",
YEAR = "2019",
NUMBER = "4",
MONTH = "April",
PAGES = "398-414",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193712"}
@inproceedings{bb198511,
AUTHOR = "Goyal, Y. and Khot, T. and Summers Stay, D. and Batra, D. and Parikh, D.",
TITLE = "Making the V in VQA Matter: Elevating the Role of Image Understanding
in Visual Question Answering",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "6325-6334",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193712"}
@article{bb198512,
AUTHOR = "Fang, Z.W. and Liu, J. and Li, Y. and Qiao, Y.Y. and Lu, H.Q.",
TITLE = "Improving visual question answering using dropout and enhanced
question encoder",
JOURNAL = PR,
VOLUME = "90",
YEAR = "2019",
PAGES = "404-414",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193713"}
@article{bb198513,
AUTHOR = "Osman, A. and Samek, W.",
TITLE = "DRAU: Dual Recurrent Attention Units for Visual Question Answering",
JOURNAL = CVIU,
VOLUME = "185",
YEAR = "2019",
PAGES = "24-30",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193714"}
@article{bb198514,
AUTHOR = "Toor, A.S. and Wechsler, H. and Nappi, M.",
TITLE = "Biometric surveillance using visual question answering",
JOURNAL = PRL,
VOLUME = "126",
YEAR = "2019",
PAGES = "111-118",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193715"}
@article{bb198515,
AUTHOR = "Ruwa, N. and Mao, Q. and Song, H.P. and Jia, H.J. and Dong, M.",
TITLE = "Triple attention network for sentimental visual question answering",
JOURNAL = CVIU,
VOLUME = "189",
YEAR = "2019",
PAGES = "102829",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193716"}
@article{bb198516,
AUTHOR = "Li, W.W. and Song, M.M. and Tian, Y.Y.",
TITLE = "An Ontology-Driven Cyberinfrastructure for Intelligent Spatiotemporal
Question Answering and Open Knowledge Discovery",
JOURNAL = IJGI,
VOLUME = "8",
YEAR = "2019",
NUMBER = "11",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193717"}
@article{bb198517,
AUTHOR = "Xi, Y.L. and Zhang, Y.N. and Ding, S.T. and Wan, S.H.",
TITLE = "Visual Question Answering Model Based on Visual Relationship
Detection",
JOURNAL = SP:IC,
VOLUME = "80",
YEAR = "2020",
PAGES = "115648",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193718"}
@article{bb198518,
AUTHOR = "Wu, Y. and Jiang, L. and Yang, Y.",
TITLE = "Revisiting EmbodiedQA: A Simple Baseline and Beyond",
JOURNAL = IP,
VOLUME = "29",
YEAR = "2020",
PAGES = "3984-3992",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193719"}
@article{bb198519,
AUTHOR = "Huang, C. and Yao, L. and Wang, X.Z. and Benatallah, B. and Zhang, X.",
TITLE = "Software expert discovery via knowledge domain embeddings in a
collaborative network",
JOURNAL = PRL,
VOLUME = "130",
YEAR = "2020",
PAGES = "46-53",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193720"}
@article{bb198520,
AUTHOR = "Li, W. and Sun, J.H. and Liu, G. and Zhao, L. and Fang, X.Z.",
TITLE = "Visual question answering with attention transfer and a cross-modal
gating mechanism",
JOURNAL = PRL,
VOLUME = "133",
YEAR = "2020",
PAGES = "334-340",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193721"}
@article{bb198521,
AUTHOR = "Messina, N. and Amato, G. and Carrara, F. and Falchi, F. and Gennaro, C.",
TITLE = "Learning visual features for relational CBIR",
JOURNAL = MultInfoRetr,
VOLUME = "9",
YEAR = "2020",
NUMBER = "2",
MONTH = "June",
PAGES = "113-124",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193722"}
@inproceedings{bb198522,
AUTHOR = "Messina, N. and Amato, G. and Carrara, F. and Falchi, F. and Gennaro, C.",
TITLE = "Learning Relationship-Aware Visual Features",
BOOKTITLE = CEFR-LCV18,
YEAR = "2018",
PAGES = "IV:486-501",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193723"}
@inproceedings{bb198523,
AUTHOR = "Methani, N. and Ganguly, P. and Khapra, M.M. and Kumar, P.",
TITLE = "PlotQA: Reasoning over Scientific Plots",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "1516-1525",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193724"}
@article{bb198524,
AUTHOR = "Yu, J. and Zhu, Z.H. and Wang, Y.J. and Zhang, W.F. and Hu, Y. and Tan, J.L.",
TITLE = "Cross-modal knowledge reasoning for knowledge-based visual question
answering",
JOURNAL = PR,
VOLUME = "108",
YEAR = "2020",
PAGES = "107563",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193725"}
@inproceedings{bb198525,
AUTHOR = "Yang, Z.Q. and Qin, Z.C. and Yu, J. and Wan, T.",
TITLE = "Prior Visual Relationship Reasoning For Visual Question Answering",
BOOKTITLE = ICIP20,
YEAR = "2020",
PAGES = "1411-1415",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193726"}
@article{bb198526,
AUTHOR = "Bai, Z.W. and Li, Y. and Wozniak, M. and Zhou, M.L. and Li, D.",
TITLE = "DecomVQANet: Decomposing visual question answering deep network via
tensor decomposition and regression",
JOURNAL = PR,
VOLUME = "110",
YEAR = "2021",
PAGES = "107538",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193727"}
@article{bb198527,
AUTHOR = "Farazi, M.R. and Khan, S.H. and Barnes, N.",
TITLE = "From known to the unknown: Transferring knowledge to answer questions
about novel visual and semantic concepts",
JOURNAL = IVC,
VOLUME = "103",
YEAR = "2020",
PAGES = "103985",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193728"}
@article{bb198528,
AUTHOR = "Terao, K. and Tamaki, T. and Raytchev, B. and Kaneda, K. and Satoh, S.",
TITLE = "Rephrasing Visual Questions by Specifying the Entropy of the Answer
Distribution",
JOURNAL = IEICE,
VOLUME = "E103-D",
YEAR = "2020",
NUMBER = "11",
MONTH = "November",
PAGES = "2362-2370",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193729"}
@article{bb198529,
AUTHOR = "Yu, J. and Zhang, W.F. and Lu, Y.H. and Qin, Z.C. and Hu, Y. and Tan, J.L. and Wu, Q.",
TITLE = "Reasoning on the Relation: Enhancing Visual Representation for Visual
Question Answering and Cross-Modal Retrieval",
JOURNAL = MultMed,
VOLUME = "22",
YEAR = "2020",
NUMBER = "12",
MONTH = "December",
PAGES = "3196-3209",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193730"}
@article{bb198530,
AUTHOR = "Lobry, S. and Marcos, D. and Murray, J. and Tuia, D.",
TITLE = "RSVQA: Visual Question Answering for Remote Sensing Data",
JOURNAL = GeoRS,
VOLUME = "58",
YEAR = "2020",
NUMBER = "12",
MONTH = "December",
PAGES = "8555-8566",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193731"}
@inproceedings{bb198531,
AUTHOR = "Faure, M. and Lobry, S. and Kurtz, C. and Wendling, L.",
TITLE = "Embedding Spatial Relations in Visual Question Answering for Remote
Sensing",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "310-316",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193732"}
@inproceedings{bb198532,
AUTHOR = "Chappuis, C. and Zermatten, V. and Lobry, S. and Le Saux, B. and Tuia, D.",
TITLE = "Prompt-RSVQA: Prompting visual context to a language model for Remote
Sensing Visual Question Answering",
BOOKTITLE = EarthVision22,
YEAR = "2022",
PAGES = "1371-1380",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193733"}
@article{bb198533,
AUTHOR = "Sun, B. and Yao, Z. and Zhang, Y.H. and Yu, L.J.",
TITLE = "Local relation network with multilevel attention for visual question
answering",
JOURNAL = JVCIR,
VOLUME = "73",
YEAR = "2020",
PAGES = "102762",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193734"}
@article{bb198534,
AUTHOR = "Wang, J.M. and Cui, E. and Liu, K.L. and Sun, Y.K. and Liang, J.Y. and Yuan, C.M. and Duan, X.J. and Jin, G.H. and Chung, T.S.",
TITLE = "Referring expression comprehension model with matching detection and
linguistic feedback",
JOURNAL = IET-CV,
VOLUME = "14",
YEAR = "2020",
NUMBER = "8",
MONTH = "December",
PAGES = "625-633",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193735"}
@article{bb198535,
AUTHOR = "Li, X. and Yuan, A. and Lu, X.",
TITLE = "Vision-to-Language Tasks Based on Attributes and Attention Mechanism",
JOURNAL = Cyber,
VOLUME = "51",
YEAR = "2021",
NUMBER = "2",
MONTH = "February",
PAGES = "913-926",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193736"}
@article{bb198536,
AUTHOR = "Cao, Q.X. and Liang, X.D. and Li, B.L. and Lin, L.",
TITLE = "Interpretable Visual Question Answering by Reasoning on Dependency
Trees",
JOURNAL = PAMI,
VOLUME = "43",
YEAR = "2021",
NUMBER = "3",
MONTH = "March",
PAGES = "887-901",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193737"}
@inproceedings{bb198537,
AUTHOR = "Cao, Q.X. and Liang, X.D. and Li, B.L. and Li, G. and Lin, L.",
TITLE = "Visual Question Reasoning on General Dependency Tree",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7249-7257",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193738"}
@article{bb198538,
AUTHOR = "Shao, Y. and Lin, J.C.W. and Srivastava, G. and Jolfaei, A. and Guo, D.D. and Hu, Y.",
TITLE = "Self-attention-based conditional random fields latent variables model
for sequence labeling",
JOURNAL = PRL,
VOLUME = "145",
YEAR = "2021",
PAGES = "157-164",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193739"}
@article{bb198539,
AUTHOR = "Zhong, H.S. and Chen, J.Y. and Shen, C. and Zhang, H.W. and Huang, J.Q. and Hua, X.S.",
TITLE = "Self-Adaptive Neural Module Transformer for Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "1264-1273",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193740"}
@article{bb198540,
AUTHOR = "Sharma, H. and Jalal, A.S.",
TITLE = "Visual question answering model based on graph neural network and
contextual attention",
JOURNAL = IVC,
VOLUME = "110",
YEAR = "2021",
PAGES = "104165",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193741"}
@article{bb198541,
AUTHOR = "Wu, Y. and Ma, Y.T. and Wan, S.H.",
TITLE = "Multi-scale relation reasoning for multi-modal Visual Question
Answering",
JOURNAL = SP:IC,
VOLUME = "96",
YEAR = "2021",
PAGES = "116319",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193742"}
@inproceedings{bb198542,
AUTHOR = "Ma, Y.T. and Lu, T. and Wu, Y.",
TITLE = "Multi-scale Relational Reasoning with Regional Attention for Visual
Question Answering",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "5642-5649",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193743"}
@article{bb198543,
AUTHOR = "dos S Silva, F.H. and Bezerra, G.M. and Holanda, G.B. and de Souza, J.W.M. and Rego, P.A.L. and Lira Neto, A.V. and de Albuquerque, V.H.C. and Reboucas Filho, P.P.",
TITLE = "A novel feature extractor for human action recognition in visual
question answering",
JOURNAL = PRL,
VOLUME = "147",
YEAR = "2021",
PAGES = "41-47",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193744"}
@article{bb198544,
AUTHOR = "Guo, W. and Zhang, Y. and Yang, J.F. and Yuan, X.J.",
TITLE = "Re-Attention for Visual Question Answering",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "6730-6743",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193745"}
@article{bb198545,
AUTHOR = "Hu, J. and Qian, S. and Fang, Q. and Xu, C.S.",
TITLE = "Heterogeneous Community Question Answering via Social-Aware
Multi-Modal Co-Attention Convolutional Matching",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "2321-2334",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193746"}
@article{bb198546,
AUTHOR = "Farazi, M. and Khan, S. and Barnes, N.",
TITLE = "Accuracy vs. complexity: A trade-off in visual question answering
models",
JOURNAL = PR,
VOLUME = "120",
YEAR = "2021",
PAGES = "108106",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193747"}
@article{bb198547,
AUTHOR = "Zheng, W.F. and Yin, L.R. and Chen, X.B. and Ma, Z. and Liu, S. and Yang, B.",
TITLE = "Knowledge base graph embedding module design for Visual question
answering model",
JOURNAL = PR,
VOLUME = "120",
YEAR = "2021",
PAGES = "108153",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193748"}
@article{bb198548,
AUTHOR = "Barra, S. and Bisogni, C. and de Marsico, M. and Ricciardi, S.",
TITLE = "Visual question answering: Which investigated applications?",
JOURNAL = PRL,
VOLUME = "151",
YEAR = "2021",
PAGES = "325-331",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193749"}
@article{bb198549,
AUTHOR = "Manmadhan, S. and Kovoor, B.C.",
TITLE = "Multi-Tier Attention Network using Term-weighted Question Features
for Visual Question Answering",
JOURNAL = IVC,
VOLUME = "115",
YEAR = "2021",
PAGES = "104291",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193750"}
@article{bb198550,
AUTHOR = "Liu, A.A. and Lu, Z. and Xu, N. and Nie, W.Z. and Li, W.H.",
TITLE = "Multi-type decision fusion network for visual Q&A",
JOURNAL = IVC,
VOLUME = "115",
YEAR = "2021",
PAGES = "104281",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193751"}
@article{bb198551,
AUTHOR = "Patro, B.N. and Kurmi, V.K. and Kumar, S. and Namboodiri, V.P.",
TITLE = "MUMC: Minimizing uncertainty of mixture of cues",
JOURNAL = IVC,
VOLUME = "115",
YEAR = "2021",
PAGES = "104280",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193752"}
@article{bb198552,
AUTHOR = "Liu, F. and Liu, J. and Fang, Z.W. and Hong, R.C. and Lu, H.Q.",
TITLE = "Visual Question Answering With Dense Inter- and Intra-Modality
Interactions",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "3518-3529",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193753"}
@article{bb198553,
AUTHOR = "Wu, J.J. and Du, J. and Wang, F. and Yang, C. and Jiang, X.Z. and Hu, J. and Yin, B. and Zhang, J.S. and Dai, L.R.",
TITLE = "A multimodal attention fusion network with a dynamic vocabulary for
TextVQA",
JOURNAL = PR,
VOLUME = "122",
YEAR = "2022",
PAGES = "108214",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193754"}
@article{bb198554,
AUTHOR = "Narayanan, A. and Rao, A. and Prasad, A. and Natarajan, S.",
TITLE = "VQA as a factoid question answering problem: A novel approach for
knowledge-aware and explainable visual question answering",
JOURNAL = IVC,
VOLUME = "116",
YEAR = "2021",
PAGES = "104328",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193755"}
@article{bb198555,
AUTHOR = "Guo, Y.Y. and Nie, L.Q. and Cheng, Z.Y. and Tian, Q. and Zhang, M.",
TITLE = "Loss Re-Scaling VQA: Revisiting the Language Prior Problem From a
Class-Imbalance View",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "227-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193756"}
@article{bb198556,
AUTHOR = "Peng, L. and Yang, Y. and Wang, Z. and Huang, Z. and Shen, H.T.",
TITLE = "MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "1",
MONTH = "January",
PAGES = "318-329",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193757"}
@article{bb198557,
AUTHOR = "Manogaran, G. and Shakeel, P.M. and Burhanuddin, M.A. and Baskar, S. and Saravanan, V. and Crespo, R.G. and Martinez, O.S.",
TITLE = "ADCCF: Adaptive deep concatenation coder framework for visual
question answering",
JOURNAL = PRL,
VOLUME = "152",
YEAR = "2021",
PAGES = "348-355",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193758"}
@article{bb198558,
AUTHOR = "Zhou, Y. and Ji, R.R. and Sun, X.S. and Su, J.S. and Meng, D.Y. and Gao, Y. and Shen, C.H.",
TITLE = "Plenty is Plague: Fine-Grained Learning for Visual Question Answering",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "2",
MONTH = "February",
PAGES = "697-709",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193759"}
@article{bb198559,
AUTHOR = "E, W.N. and Zhou, Y.",
TITLE = "A Mathematical Model for Universal Semantics",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "3",
MONTH = "March",
PAGES = "1124-1132",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193760"}
@article{bb198560,
AUTHOR = "Li, X.P. and Wu, B. and Song, J.K. and Gao, L.L. and Zeng, P.P. and Gan, C.",
TITLE = "Text-instance graph: Exploring the relational semantics for
text-based visual question answering",
JOURNAL = PR,
VOLUME = "124",
YEAR = "2022",
PAGES = "108455",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193761"}
@article{bb198561,
AUTHOR = "Shao, X.J. and Xiang, Z.L. and Li, Y.X.",
TITLE = "Visual question answering with gated relation-aware auxiliary",
JOURNAL = IET-IPR,
VOLUME = "16",
YEAR = "2022",
NUMBER = "5",
PAGES = "1424-1432",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193762"}
@article{bb198562,
AUTHOR = "Liu, Y. and Zhang, X.M. and Zhao, Z.Y. and Zhang, B. and Cheng, L. and Li, Z.J.",
TITLE = "ALSA: Adversarial Learning of Supervised Attentions for Visual
Question Answering",
JOURNAL = Cyber,
VOLUME = "52",
YEAR = "2022",
NUMBER = "6",
MONTH = "June",
PAGES = "4520-4533",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193763"}
@article{bb198563,
AUTHOR = "Ouyang, N.L. and Huang, Q.B. and Li, P.J. and Cai, Y. and Liu, B. and Leung, H.F. and Li, Q.",
TITLE = "Suppressing Biased Samples for Robust VQA",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "3405-3415",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193764"}
@article{bb198564,
AUTHOR = "Shuang, K. and Guo, J. and Wang, Z.",
TITLE = "Comprehensive-perception dynamic reasoning for visual question
answering",
JOURNAL = PR,
VOLUME = "131",
YEAR = "2022",
PAGES = "108878",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193765"}
@article{bb198565,
AUTHOR = "Gouthaman, K.V. and Mittal, A.",
TITLE = "On the role of question encoder sequence model in robust visual
question answering",
JOURNAL = PR,
VOLUME = "131",
YEAR = "2022",
PAGES = "108883",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193766"}
@article{bb198566,
AUTHOR = "Zhou, K.Y. and Yang, J.K. and Loy, C.C. and Liu, Z.W.",
TITLE = "Learning to Prompt for Vision-Language Models",
JOURNAL = IJCV,
VOLUME = "130",
YEAR = "2022",
NUMBER = "9",
MONTH = "September",
PAGES = "2337-2348",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193767"}
@inproceedings{bb198567,
AUTHOR = "Zhou, K.Y. and Yang, J.K. and Loy, C.C. and Liu, Z.",
TITLE = "Conditional Prompt Learning for Vision-Language Models",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16795-16804",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193768"}
@article{bb198568,
AUTHOR = "Chen, C.Q. and Han, D.Z. and Chang, C.C.",
TITLE = "CAAN: Context-Aware attention network for visual question answering",
JOURNAL = PR,
VOLUME = "132",
YEAR = "2022",
PAGES = "108980",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193769"}
@article{bb198569,
AUTHOR = "Song, L.Y. and Li, J. and Liu, J. and Yang, Y. and Shang, X. and Sun, M.X.",
TITLE = "Answering knowledge-based visual questions via the exploration of
Question Purpose",
JOURNAL = PR,
VOLUME = "133",
YEAR = "2023",
PAGES = "109015",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193770"}
@article{bb198570,
AUTHOR = "Xie, J.Y. and Fang, W.H. and Cai, Y. and Huang, Q.B. and Li, Q.",
TITLE = "Knowledge-Based Visual Question Generation",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "11",
MONTH = "November",
PAGES = "7547-7558",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193771"}
@article{bb198571,
AUTHOR = "Gao, C. and Zhu, Q. and Wang, P. and Li, H. and Liu, Y.L. and van den Hengel, A.J. and Wu, Q.",
TITLE = "Structured Multimodal Attentions for TextVQA",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "9603-9614",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193772"}
@article{bb198572,
AUTHOR = "Jin, Z.X. and Wu, H. and Yang, C. and Zhou, F. and Qin, J.Y. and Xiao, L. and Yin, X.C.",
TITLE = "RUArt: A Novel Text-Centered Solution for Text-Based Visual Question
Answering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "1-12",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193773"}
@article{bb198573,
AUTHOR = "Beckham, C. and Weiss, M. and Golemo, F. and Honari, S. and Nowrouzezahrai, D. and Pal, C.",
TITLE = "Visual question answering from another perspective: CLEVR mental
rotation tests",
JOURNAL = PR,
VOLUME = "136",
YEAR = "2023",
PAGES = "109209",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193774"}
@article{bb198574,
AUTHOR = "Zhang, H. and Zeng, P.P. and Hu, Y.X. and Qian, J. and Song, J. and Gao, L.",
TITLE = "Learning visual question answering on controlled semantic noisy
labels",
JOURNAL = PR,
VOLUME = "138",
YEAR = "2023",
PAGES = "109339",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193775"}
@article{bb198575,
AUTHOR = "Zeng, G. and Zhang, Y. and Zhou, Y. and Yang, X.M. and Jiang, N. and Zhao, G.Q. and Wang, W.P. and Yin, X.C.",
TITLE = "Beyond OCR + VQA: Towards end-to-end reading and reasoning for robust
and accurate textvqa",
JOURNAL = PR,
VOLUME = "138",
YEAR = "2023",
PAGES = "109337",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193776"}
@inproceedings{bb198576,
AUTHOR = "Jha, A. and Patro, B. and Van Gool, L.J. and Tuytelaars, T.",
TITLE = "Barlow constrained optimization for Visual Question Answering",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "1084-1093",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193777"}
@inproceedings{bb198577,
AUTHOR = "Ravi, S. and Chinchure, A. and Sigal, L. and Liao, R.J. and Shwartz, V.",
TITLE = "VLC-BERT: Visual Question Answering with Contextualized Commonsense
Knowledge",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "1155-1165",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193778"}
@inproceedings{bb198578,
AUTHOR = "Uehara, K. and Harada, T.",
TITLE = "K-VQG: Knowledge-aware Visual Question Generation for Common-sense
Acquisition",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "4390-4398",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193779"}
@inproceedings{bb198579,
AUTHOR = "Etesam, Y. and Kochiev, L. and Chang, A.X.",
TITLE = "3DVQA: Visual Question Answering for 3D Environments",
BOOKTITLE = CRV22,
YEAR = "2022",
PAGES = "233-240",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193780"}
@inproceedings{bb198580,
AUTHOR = "Haisa, G. and Altenbek, G.",
TITLE = "Question Classification Based on Weak Supervision and Interrogative
Pronouns Attention Mechanism",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "2273-2278",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193781"}
@inproceedings{bb198581,
AUTHOR = "Ramamurthy, P. and Aakur, S.N.",
TITLE = "ISD-QA: Iterative Distillation of Commonsense Knowledge from General
Language Models for Unsupervised Question Answering",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "1229-1235",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193782"}
@inproceedings{bb198582,
AUTHOR = "Zhang, H. and Wu, W.",
TITLE = "CAT: Re-Conv Attention in Transformer for Visual Question Answering",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "1471-1477",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193783"}
@inproceedings{bb198583,
AUTHOR = "Liu, L. and Su, X.D. and Guo, H. and Zhu, D.",
TITLE = "A Transformer-based Medical Visual Question Answering Model",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "1712-1718",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193784"}
@inproceedings{bb198584,
AUTHOR = "Boecking, B. and Usuyama, N. and Bannur, S. and Castro, D.C. and Schwaighofer, A. and Hyland, S. and Wetscherek, M. and Naumann, T. and Nori, A. and Alvarez Valle, J. and Poon, H. and Oktay, O.",
TITLE = "Making the Most of Text Semantics to Improve Biomedical Vision-Language
Processing",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:1-21",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193785"}
@inproceedings{bb198585,
AUTHOR = "Cui, Q. and Zhou, B. and Guo, Y. and Yin, W.D. and Wu, H. and Yoshie, O. and Chen, Y.",
TITLE = "Contrastive Vision-Language Pre-training with Limited Resources",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:236-253",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193786"}
@inproceedings{bb198586,
AUTHOR = "Wu, X.Y. and Lu, J.F. and Li, Z.F. and Xiong, F.C.",
TITLE = "Ques-to-Visual Guided Visual Question Answering",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "4193-4197",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193787"}
@inproceedings{bb198587,
AUTHOR = "Sarkar, A. and Rahnemoonfar, M.",
TITLE = "Grad-Cam Aware Supervised Attention for Visual Question Answering for
Post-Disaster Damage Assessment",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "3783-3787",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193788"}
@inproceedings{bb198588,
AUTHOR = "Whitehead, S. and Petryk, S. and Shakib, V. and Gonzalez, J. and Darrell, T.J. and Rohrbach, A. and Rohrbach, M.",
TITLE = "Reliable Visual Question Answering: Abstain Rather Than Answer
Incorrectly",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:148-166",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193789"}
@inproceedings{bb198589,
AUTHOR = "Chen, L. and Zheng, Y.H. and Xiao, J.",
TITLE = "Rethinking Data Augmentation for Robust Visual Question Answering",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:95-112",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193790"}
@inproceedings{bb198590,
AUTHOR = "Zhang, H.T. and Wu, W.",
TITLE = "Context Relation Fusion Model for Visual Question Answering",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2112-2116",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193791"}
@inproceedings{bb198591,
AUTHOR = "Biten, A.F. and Litman, R. and Xie, Y.S. and Appalaraju, S. and Manmatha, R.",
TITLE = "LaTr: Layout-Aware Transformer for Scene-Text VQA",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16527-16537",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193792"}
@inproceedings{bb198592,
AUTHOR = "Lu, J.Y. and Ye, X. and Ren, Y. and Yang, Y.Z.",
TITLE = "Good, Better, Best: Textual Distractors Generation for
Multiple-Choice Visual Question Answering via Reinforcement Learning",
BOOKTITLE = ODRUM22,
YEAR = "2022",
PAGES = "4917-4926",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193793"}
@inproceedings{bb198593,
AUTHOR = "Nguyen, B.X. and Do, T. and Tran, H. and Tjiputra, E. and Tran, Q.D. and Nguyen, A.",
TITLE = "Coarse-to-Fine Reasoning for Visual Question Answering",
BOOKTITLE = MULA22,
YEAR = "2022",
PAGES = "4557-4565",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193794"}
@inproceedings{bb198594,
AUTHOR = "Ding, Y.H. and Huang, Z. and Wang, R. and Zhang, Y.H. and Chen, X. and Ma, Y.Z. and Chung, H. and Han, S.C.",
TITLE = "V-Doc: Visual questions answers with Documents",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "21460-21466",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193795"}
@inproceedings{bb198595,
AUTHOR = "Azuma, D. and Miyanishi, T. and Kurita, S.H. and Kawanabe, M.",
TITLE = "ScanQA: 3D Question Answering for Spatial Scene Understanding",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19107-19117",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193796"}
@inproceedings{bb198596,
AUTHOR = "Li, G.Y. and Wei, Y. and Tian, Y. and Xu, C.L. and Wen, J.R. and Hu, D.",
TITLE = "Learning to Answer Questions in Dynamic Audio-Visual Scenarios",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19086-19096",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193797"}
@inproceedings{bb198597,
AUTHOR = "Chen, C. and Anjum, S. and Gurari, D.",
TITLE = "Grounding Answers for Visual Questions Asked by Visually Impaired
People",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19076-19085",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193798"}
@inproceedings{bb198598,
AUTHOR = "Guo, X.Y. and Duan, J.L. and Kuo, C.C.J. and Gichoya, J.W. and Banerjee, I.",
TITLE = "Augmenting Vision Language Pretraining by Learning Codebook with
Visual Semantics",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "4779-4785",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193799"}
@inproceedings{bb198599,
AUTHOR = "Yang, J. and Duan, J.L. and Tran, S. and Xu, Y. and Chanda, S. and Chen, L.Q. and Zeng, B. and Chilimbi, T. and Huang, J.Z.",
TITLE = "Vision-Language Pre-Training with Triple Contrastive Learning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15650-15659",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193800"}
Last update:Mar 27, 2023 at 09:32:08