@article{bb177300,
        AUTHOR = "Zhao, Z. and Zhang, Z. and Xiao, S.W. and Xiao, Z.X. and Yan, X.H. and Yu, J. and Cai, D. and Wu, F.",
        TITLE = "Long-Form Video Question Answering via Dynamic Hierarchical
Reinforced Networks",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "5939-5952",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172638"}

@article{bb177301,
        AUTHOR = "Yu, T. and Yu, J. and Yu, Z. and Huang, Q.M. and Tian, Q.",
        TITLE = "Long-Term Video Question Answering via Multimodal Hierarchical Memory
Attentive Networks",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "931-944",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172639"}

@article{bb177302,
        AUTHOR = "Jang, Y. and Song, Y. and Kim, C.D. and Yu, Y. and Kim, Y. and Kim, G.",
        TITLE = "Video Question Answering with Spatio-Temporal Reasoning",
        JOURNAL = IJCV,
        VOLUME = "127",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "1385-1412",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172640"}

@inproceedings{bb177303,
        AUTHOR = "Jang, Y. and Song, Y. and Yu, Y. and Kim, Y. and Kim, G.",
        TITLE = "TGIF-QA:
Toward Spatio-Temporal Reasoning in Visual Question Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1359-1367",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172641"}

@article{bb177304,
        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#TT172642"}

@article{bb177305,
        AUTHOR = "Wang, A. and Luu, A.T. and Foo, C. and Zhu, H. and Tay, Y. and Chandrasekhar, V.",
        TITLE = "Holistic Multi-Modal Memory Network for Movie Question Answering",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        NUMBER = "1",
        PAGES = "489-499",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172643"}

@article{bb177306,
        AUTHOR = "Yu, T. and Yu, J. and Yu, Z. and Tao, D.",
        TITLE = "Compositional Attention Networks With Two-Stream Fusion for Video
Question Answering",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        NUMBER = "",
        PAGES = "1204-1218",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172644"}

@article{bb177307,
        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#TT172645"}

@article{bb177308,
        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#TT172646"}

@article{bb177309,
        AUTHOR = "Tommasi, T. and Mallya, A. and Plummer, B.A. and Lazebnik, S. and Berg, A.C. and Berg, T.L.",
        TITLE = "Combining Multiple Cues for Visual Madlibs Question Answering",
        JOURNAL = IJCV,
        VOLUME = "127",
        YEAR = "2019",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "38-60",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172647"}

@inproceedings{bb177310,
        AUTHOR = "Tommasi, T. and Mallya, A. and Plummer, B.A. and Lazebnik, S. and Berg, A.C. and Berg, T.L.",
        TITLE = "Solving Visual Madlibs with Multiple Cues",
        BOOKTITLE = BMVC16,
        YEAR = "2016",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172648"}

@inproceedings{bb177311,
        AUTHOR = "Yu, L.C. and Park, E. and Berg, A.C. and Berg, T.L.",
        TITLE = "Visual Madlibs:
Fill in the Blank Description Generation and Question Answering",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "2461-2469",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172649"}

@article{bb177312,
        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#TT172650"}

@article{bb177313,
        AUTHOR = "Liu, F. and Xiang, T. and Hospedales, T.M. and Yang, W. and Sun, C.",
        TITLE = "Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis
Tool",
        JOURNAL = PAMI,
        VOLUME = "42",
        YEAR = "2020",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "460-474",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172651"}

@inproceedings{bb177314,
        AUTHOR = "Liu, F. and Xiang, T. and Hospedales, T.M. and Yang, W. and Sun, C.",
        TITLE = "iVQA: Inverse Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "8611-8619",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172652"}

@article{bb177315,
        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#TT172653"}

@article{bb177316,
        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#TT172654"}

@article{bb177317,
        AUTHOR = "Wang, W. and Huang, Y. and Wang, L.",
        TITLE = "Long video question answering: A Matching-guided Attention Model",
        JOURNAL = PR,
        VOLUME = "102",
        YEAR = "2020",
        PAGES = "107248",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172655"}

@article{bb177318,
        AUTHOR = "Zhang, W. and Tang, S. and Cao, Y. and Pu, S. and Wu, F. and Zhuang, Y.",
        TITLE = "Frame Augmented Alternating Attention Network for Video Question
Answering",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1032-1041",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172656"}

@article{bb177319,
        AUTHOR = "Chen, J. and Shao, J. and He, C.",
        TITLE = "Movie fill in the blank by joint learning from video and text with
adaptive temporal attention",
        JOURNAL = PRL,
        VOLUME = "132",
        YEAR = "2020",
        PAGES = "62-68",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172657"}

@article{bb177320,
        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#TT172658"}

@article{bb177321,
        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#TT172659"}

@inproceedings{bb177322,
        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#TT172660"}

@inproceedings{bb177323,
        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#TT172661"}

@article{bb177324,
        AUTHOR = "Guo, D. and Wang, H. and Wang, S. and Wang, M.",
        TITLE = "Textual-Visual Reference-Aware Attention Network for Visual Dialog",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "6655-6666",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172662"}

@article{bb177325,
        AUTHOR = "Patil, C. and Patwardhan, M.",
        TITLE = "Visual Question Generation: The State of the Art",
        JOURNAL = Surveys,
        VOLUME = "53",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "May",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172663"}

@article{bb177326,
        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#TT172664"}

@inproceedings{bb177327,
        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#TT172665"}

@article{bb177328,
        AUTHOR = "Vu, M.H. and Lofstedt, T. and Nyholm, T. and Sznitman, R.",
        TITLE = "A Question-Centric Model for Visual Question Answering in Medical
Imaging",
        JOURNAL = MedImg,
        VOLUME = "39",
        YEAR = "2020",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2856-2868",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172666"}

@article{bb177329,
        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#TT172667"}

@article{bb177330,
        AUTHOR = "Patro, B.N. and Anupriy and Namboodiri, V.P.",
        TITLE = "Probabilistic framework for solving visual dialog",
        JOURNAL = PR,
        VOLUME = "110",
        YEAR = "2021",
        PAGES = "107586",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172668"}

@article{bb177331,
        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#TT172669"}

@article{bb177332,
        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#TT172670"}

@article{bb177333,
        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#TT172671"}

@article{bb177334,
        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#TT172672"}

@article{bb177335,
        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#TT172673"}

@article{bb177336,
        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#TT172674"}

@article{bb177337,
        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#TT172675"}

@article{bb177338,
        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#TT172676"}

@inproceedings{bb177339,
        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#TT172677"}

@article{bb177340,
        AUTHOR = "Gu, M. and Zhao, Z. and Jin, W. and Hong, R. and Wu, F.",
        TITLE = "Graph-Based Multi-Interaction Network for Video Question Answering",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "2758-2770",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172678"}

@article{bb177341,
        AUTHOR = "Zhao, L. and Lyu, X.Y. and Song, J.K. and Gao, L.L.",
        TITLE = "GuessWhich? Visual dialog with attentive memory network",
        JOURNAL = PR,
        VOLUME = "114",
        YEAR = "2021",
        PAGES = "107823",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172679"}

@article{bb177342,
        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#TT172680"}

@article{bb177343,
        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#TT172681"}

@article{bb177344,
        AUTHOR = "Xie, Z. and Wu, K.W. and Zhang, X.Y. and Yang, X.M. and Hou, J.K.",
        TITLE = "Learning continuous temporal embedding of videos using pattern theory",
        JOURNAL = PRL,
        VOLUME = "146",
        YEAR = "2021",
        PAGES = "222-229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172682"}

@article{bb177345,
        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#TT172683"}

@article{bb177346,
        AUTHOR = "Yuan, Z. and Sun, S.Y. and Duan, L.X. and Li, C.S. and Wu, X. and Xu, C.S.",
        TITLE = "Adversarial Multimodal Network for Movie Story Question Answering",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "1744-1756",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172684"}

@article{bb177347,
        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#TT172685"}

@inproceedings{bb177348,
        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#TT172686"}

@article{bb177349,
        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#TT172687"}

@article{bb177350,
        AUTHOR = "Liu, Y. and Zhang, X.M. and Zhang, Q.Y. and Li, C.Z. and Huang, F. and Tang, X.H. and Li, Z.J.",
        TITLE = "Dual self-attention with co-attention networks for visual question
answering",
        JOURNAL = PR,
        VOLUME = "117",
        YEAR = "2021",
        PAGES = "107956",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172688"}

@article{bb177351,
        AUTHOR = "Jin, W. and Zhao, Z. and Cao, X.C. and Zhu, J.M. and He, X.Q. and Zhuang, Y.T.",
        TITLE = "Adaptive Spatio-Temporal Graph Enhanced Vision-Language
Representation for Video QA",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "5477-5489",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172689"}

@article{bb177352,
        AUTHOR = "He, F.J. and Wang, Y.X. and Miao, X.L. and Sun, X.",
        TITLE = "Interpretable visual reasoning: A survey",
        JOURNAL = IVC,
        VOLUME = "112",
        YEAR = "2021",
        PAGES = "104194",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172690"}

@article{bb177353,
        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#TT172691"}

@article{bb177354,
        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#TT172692"}

@article{bb177355,
        AUTHOR = "Gao, L. and Chen, T.M. and Li, X.P. and Zeng, P.P. and Zhao, L. and Li, Y.F.",
        TITLE = "Generalized pyramid co-attention with learnable aggregation net for
video question answering",
        JOURNAL = PR,
        VOLUME = "120",
        YEAR = "2021",
        PAGES = "108145",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172693"}

@article{bb177356,
        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#TT172694"}

@article{bb177357,
        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#TT172695"}

@article{bb177358,
        AUTHOR = "Al Sadi, A. and Al Ayyoub, M. and Jararweh, Y. and Costen, F.",
        TITLE = "Visual question answering in the medical domain based on deep
learning approaches: A comprehensive study",
        JOURNAL = PRL,
        VOLUME = "150",
        YEAR = "2021",
        PAGES = "57-75",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172696"}

@article{bb177359,
        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#TT172697"}

@article{bb177360,
        AUTHOR = "Le, T.M. and Le, V. and Venkatesh, S. and Tran, T.",
        TITLE = "Hierarchical Conditional Relation Networks for Multimodal Video
Question Answering",
        JOURNAL = IJCV,
        VOLUME = "129",
        YEAR = "2021",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "3027-3050",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172698"}

@inproceedings{bb177361,
        AUTHOR = "Le, T.M. and Le, V. and Venkatesh, S. and Tran, T.",
        TITLE = "Hierarchical Conditional Relation Networks for Video Question
Answering",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "9969-9978",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172699"}

@article{bb177362,
        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#TT172700"}

@article{bb177363,
        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#TT172701"}

@article{bb177364,
        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#TT172702"}

@article{bb177365,
        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#TT172703"}

@inproceedings{bb177366,
        AUTHOR = "Cho, J.W. and Kim, D.J. and Choi, J. and Jung, Y. and Kweon, I.S.",
        TITLE = "Dealing with Missing Modalities in the Visual Question
Answer-Difference Prediction Task through Knowledge Distillation",
        BOOKTITLE = MULA21,
        YEAR = "2021",
        PAGES = "1592-1601",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172704"}

@inproceedings{bb177367,
        AUTHOR = "Dua, R. and Kancheti, S.S. and Balasubramanian, V.N.",
        TITLE = "Beyond VQA: Generating Multi-word Answers and Rationales to Visual
Questions",
        BOOKTITLE = MULA21,
        YEAR = "2021",
        PAGES = "1623-1632",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172705"}

@inproceedings{bb177368,
        AUTHOR = "Rahman, T. and Chou, S.H. and Sigal, L. and Carenini, G.",
        TITLE = "An Improved Attention for Visual Question Answering",
        BOOKTITLE = MULA21,
        YEAR = "2021",
        PAGES = "1653-1662",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172706"}

@inproceedings{bb177369,
        AUTHOR = "Mathew, M. and Karatzas, D. and Jawahar, C.V.",
        TITLE = "DocVQA: A Dataset for VQA on Document Images",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "2199-2208",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172707"}

@inproceedings{bb177370,
        AUTHOR = "Chen, X.W. and Liu, R. and Song, X.M. and Han, Y.H.",
        TITLE = "Locating Visual Explanations for Video Question Answering",
        BOOKTITLE = MMMod21,
        YEAR = "2021",
        PAGES = "I:290-302",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172708"}

@inproceedings{bb177371,
        AUTHOR = "Jiang, T.L. and Ji, Y. and Liu, C.P.",
        TITLE = "Integrating Historical States and Co-attention Mechanism for Visual
Dialog",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "2041-2048",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172709"}

@inproceedings{bb177372,
        AUTHOR = "Stefanini, M. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "A Novel Attention-based Aggregation Function to Combine Vision and
Language",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "1212-1219",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172710"}

@inproceedings{bb177373,
        AUTHOR = "Jolly, S. and Palacio, S. and Folz, J. and Raue, F. and Hees, J. and Dengel, A.",
        TITLE = "P  NP, at least in Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "2748-2754",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172711"}

@inproceedings{bb177374,
        AUTHOR = "Liang, Y.Y. and Wang, X. and Duan, X.G. and Zhu, W.W.",
        TITLE = "Multi-modal Contextual Graph Neural Network for Text Visual Question
Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "3491-3498",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172712"}

@inproceedings{bb177375,
        AUTHOR = "Farazi, M. and Khan, S. and Barnes, N.",
        TITLE = "Question-Agnostic Attention for Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "3542-3549",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172713"}

@inproceedings{bb177376,
        AUTHOR = "Li, Y. and Lin, Y. and Zhao, H.H. and Wang, D.H.",
        TITLE = "Dual Path Multi-Modal High-Order Features for Textual Content based
Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "4324-4331",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172714"}

@inproceedings{bb177377,
        AUTHOR = "Mishra, A. and Anand, A. and Guha, P.",
        TITLE = "Multi-stage Attention based Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "9407-9414",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172715"}

@inproceedings{bb177378,
        AUTHOR = "Bozinis, T. and Passalis, N. and Tefas, A.",
        TITLE = "Improving Visual Question Answering using Active Perception on Static
Images",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "879-884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172716"}

@inproceedings{bb177379,
        AUTHOR = "Huang, H.T. and Han, T. and Han, W. and Yap, D. and Chiang, C.M.",
        TITLE = "Answer-checking in Context:
A Multi-modal Fully Attention Network for Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "1173-1180",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172717"}

@inproceedings{bb177380,
        AUTHOR = "Kocaman, V. and Talby, D.",
        TITLE = "Biomedical Named Entity Recognition at Scale",
        BOOKTITLE = "CADL20",
        YEAR = "2020",
        PAGES = "635-646",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172718"}

@inproceedings{bb177381,
        AUTHOR = "Sun, Q. and Xie, B. and Fu, Y.W.",
        TITLE = "Second Order Enhanced Multi-Glimpse Attention in Visual Question
Answering",
        BOOKTITLE = ACCV20,
        YEAR = "2020",
        PAGES = "IV:87-103",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172719"}

@inproceedings{bb177382,
        AUTHOR = "Goel, V. and Chandak, M. and Anand, A. and Guha, P.",
        TITLE = "IQ-VQA: Intelligent Visual Question Answering",
        BOOKTITLE = VTIUR20,
        YEAR = "2020",
        PAGES = "357-370",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172720"}

@inproceedings{bb177383,
        AUTHOR = "Patel, D. and Parikh, R. and Shastri, Y.",
        TITLE = "Recent Advances in Video Question Answering:
A Review of Datasets and Methods",
        BOOKTITLE = VTIUR20,
        YEAR = "2020",
        PAGES = "339-356",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172721"}

@inproceedings{bb177384,
        AUTHOR = "Nguyen, V.Q. and Suganuma, M. and Okatani, T.",
        TITLE = "Efficient Attention Mechanism for Visual Dialog that Can Handle All the
Interactions Between Multiple Inputs",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXIV:223-240",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172722"}

@inproceedings{bb177385,
        AUTHOR = "Murahari, V. and Batra, D. and Parikh, D. and Das, A.",
        TITLE = "Large-scale Pretraining for Visual Dialog:
A Simple State-of-the-art Baseline",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVIII:336-352",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172723"}

@inproceedings{bb177386,
        AUTHOR = "Garcia, N. and Nakashima, Y.",
        TITLE = "Knowledge-based Video Question Answering with Unsupervised Scene
Descriptions",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVIII:581-598",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172724"}

@inproceedings{bb177387,
        AUTHOR = "Gouthaman, K.V. and Mittal, A.",
        TITLE = "Reducing Language Biases in Visual Question Answering with
Visually-grounded Question Encoder",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIII:18-34",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172725"}

@inproceedings{bb177388,
        AUTHOR = "Tan, S. and Xiang, W. and Liu, H.P. and Guo, D. and Sun, F.C.",
        TITLE = "Multi-agent Embodied Question Answering in Interactive Environments",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIII:663-678",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172726"}

@inproceedings{bb177389,
        AUTHOR = "Qiao, Y. and Yu, Z. and Liu, J.",
        TITLE = "VC-VQA: Visual Calibration Mechanism For Visual Question Answering",
        BOOKTITLE = ICIP20,
        YEAR = "2020",
        PAGES = "1481-1485",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172727"}

@inproceedings{bb177390,
        AUTHOR = "Jain, V. and Lodhavia, J.",
        TITLE = "Automatic Question Tagging using k-Nearest Neighbors and Random
Forest",
        BOOKTITLE = ISCV20,
        YEAR = "2020",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172728"}

@inproceedings{bb177391,
        AUTHOR = "Tang, R.X. and Ma, C. and Zhang, W.E. and Wu, Q. and Yang, X.K.",
        TITLE = "Semantic Equivalent Adversarial Data Augmentation for Visual Question
Answering",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIX:437-453",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172729"}

@inproceedings{bb177392,
        AUTHOR = "Zhu, Y. and Wu, Y. and Yang, Y. and Yan, Y.",
        TITLE = "Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXIII:153-169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172730"}

@inproceedings{bb177393,
        AUTHOR = "Gokhale, T. and Banerjee, P. and Baral, C. and Yang, Y.Z.",
        TITLE = "VQA-LOL: Visual Question Answering Under the Lens of Logic",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXI:379-396",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172731"}

@inproceedings{bb177394,
        AUTHOR = "Yang, X.F. and Lin, G.S. and Lv, F.M. and Liu, F.",
        TITLE = "TRRNET:
Tiered Relation Reasoning for Compositional Visual Question Answering",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXI:414-430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172732"}

@inproceedings{bb177395,
        AUTHOR = "Bansal, A. and Zhang, Y. and Chellappa, R.",
        TITLE = "Visual Question Answering on Image Sets",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXI:51-67",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172733"}

@inproceedings{bb177396,
        AUTHOR = "Han, X.Z. and Wang, S.H. and Su, C. and Zhang, W.G. and Huang, Q.M. and Tian, Q.",
        TITLE = "Interpretable Visual Reasoning via Probabilistic Formulation Under
Natural Supervision",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "IX:553-570",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172734"}

@inproceedings{bb177397,
        AUTHOR = "Kant, Y. and Batra, D. and Anderson, P. and Schwing, A. and Parikh, D. and Lu, J. and Agrawal, H.",
        TITLE = "Spatially Aware Multimodal Transformers for TextVQA",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "IX:715-732",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172735"}

@inproceedings{bb177398,
        AUTHOR = "Li, Q. and Huang, S.Y. and Hong, Y. and Zhu, S.C.",
        TITLE = "A Competence-aware Curriculum for Visual Concepts Learning via Question
Answering",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "II:141-157",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172736"}

@inproceedings{bb177399,
        AUTHOR = "Zheng, W.B. and Yan, L. and Gou, C. and Wang, F.Y.",
        TITLE = "Webly Supervised Knowledge Embedding Model for Visual Reasoning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "12442-12451",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172737"}

Last update:Oct 24, 2021 at 16:35:58