@inproceedings{bb177200,
        AUTHOR = "Fan, X.D. and Geman, D.",
        TITLE = "Hierarchical object indexing and sequential learning",
        BOOKTITLE = ICPR04,
        YEAR = "2004",
        PAGES = "III: 65-68",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat802.html#TT172537"}

@inproceedings{bb177201,
        AUTHOR = "Schneidewind, A. and Neumann, P. and Schmitt, I.",
        TITLE = "An Approach to Visualize Image Retrieval Results",
        BOOKTITLE = MMDE04,
        YEAR = "2004",
        PAGES = "148",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat802.html#TT172538"}

@inproceedings{bb177202,
        AUTHOR = "Bouchaffra, D. and Tan, J.",
        TITLE = "Introduction to the concept of structural HMM:
Application to Mining Customers' Preferences in Automotive Design",
        BOOKTITLE = ICPR04,
        YEAR = "2004",
        PAGES = "II: 493-496",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat802.html#TT172539"}

@inproceedings{bb177203,
        AUTHOR = "Chelkh, F.A. and Cramariuc, B. and Gabbouj, M.",
        TITLE = "Relevance feedback for shape query refinement",
        BOOKTITLE = ICIP03,
        YEAR = "2003",
        PAGES = "I: 745-748",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat802.html#TT172540"}

@inproceedings{bb177204,
        AUTHOR = "Tesic, J. and Manjunath, B.S.",
        TITLE = "Nearest neighbor search for relevance feedback",
        BOOKTITLE = CVPR03,
        YEAR = "2003",
        PAGES = "II: 643-648",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat802.html#TT172541"}

@inproceedings{bb177205,
        AUTHOR = "Vicario, E. and He, W.X.",
        TITLE = "Weighted walkthroughs in retrieval by contents of pictorial data",
        BOOKTITLE = CIAP97,
        YEAR = "1997",
        PAGES = "II: 132-139",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat802.html#TT172542"}

@article{bb177206,
        AUTHOR = "Wu, Y.C. and Yang, J.C.",
        TITLE = "A Robust Passage Retrieval Algorithm for Video Question Answering",
        JOURNAL = CirSysVideo,
        VOLUME = "18",
        YEAR = "2008",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "1411-1421",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172545"}

@inproceedings{bb177207,
        AUTHOR = "Wu, Y.C. and Lee, Y.S. and Yang, J.C. and Yen, S.J.",
        TITLE = "A New Passage Ranking Algorithm for Video Question Answering",
        BOOKTITLE = PSIVT06,
        YEAR = "2006",
        PAGES = "563-572",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172546"}

@article{bb177208,
        AUTHOR = "Li, G.D. and Li, H. and Ming, Z.Y. and Hong, R. and Tang, S. and Chua, T.S.",
        TITLE = "Question Answering over Community-Contributed Web Videos",
        JOURNAL = MultMedMag,
        VOLUME = "17",
        YEAR = "2010",
        NUMBER = "4",
        MONTH = "October",
        PAGES = "46-57",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172547"}

@inproceedings{bb177209,
        AUTHOR = "Song, Y.C. and Li, H.",
        TITLE = "Mash-Up Approach for Web Video Category Recommendation",
        BOOKTITLE = PSIVT10,
        YEAR = "2010",
        PAGES = "197-202",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172548"}

@article{bb177210,
        AUTHOR = "Agrawal, A. and Lu, J. and Antol, S. and Mitchell, M. and Zitnick, C.L. and Parikh, D. and Batra, D.",
        TITLE = "VQA: Visual Question Answering",
        JOURNAL = IJCV,
        VOLUME = "123",
        YEAR = "2017",
        NUMBER = "1",
        MONTH = "May",
        PAGES = "4-31",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172549"}

@article{bb177211,
        AUTHOR = "Malinowski, M. and Rohrbach, M. and Fritz, M.",
        TITLE = "Ask Your Neurons: A Deep Learning Approach to Visual Question Answering",
        JOURNAL = IJCV,
        VOLUME = "125",
        YEAR = "2018",
        NUMBER = "1-3",
        MONTH = "December",
        PAGES = "110-135",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172550"}

@inproceedings{bb177212,
        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#TT172551"}

@article{bb177213,
        AUTHOR = "Kafle, K. and Kanan, C.",
        TITLE = "Visual question answering:
Datasets, algorithms, and future challenges",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "3-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172552"}

@article{bb177214,
        AUTHOR = "Wu, Q. and Teney, D. and Wang, P. and Shen, C.H. and Dick, A. and van den Hengel, A.J.",
        TITLE = "Visual question answering: A survey of methods and datasets",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "21-40",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172553"}

@article{bb177215,
        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#TT172554"}

@article{bb177216,
        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#TT172555"}

@article{bb177217,
        AUTHOR = "Teney, D. and Wu, Q. and van den Hengel, A.J.",
        TITLE = "Visual Question Answering: A Tutorial",
        JOURNAL = SPMag,
        VOLUME = "34",
        YEAR = "2017",
        NUMBER = "6",
        MONTH = "November",
        PAGES = "63-75",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172556"}

@inproceedings{bb177218,
        AUTHOR = "Teney, D. and Liu, L. and van den Hengel, A.J.",
        TITLE = "Graph-Structured Representations for Visual Question Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3233-3241",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172557"}

@inproceedings{bb177219,
        AUTHOR = "Teney, D. and van den Hengel, A.J.",
        TITLE = "Visual Question Answering as a Meta Learning Task",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XV: 229-245",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172558"}

@article{bb177220,
        AUTHOR = "Wu, Q. and Shen, C.H. and Wang, P. and Dick, A. and van den Hengel, A.J.",
        TITLE = "Image Captioning and Visual Question Answering Based on Attributes
and External Knowledge",
        JOURNAL = PAMI,
        VOLUME = "40",
        YEAR = "2018",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "1367-1381",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172559"}

@inproceedings{bb177221,
        AUTHOR = "Wu, Q. and Wang, P. and Shen, C.H. and Dick, A. and van den Hengel, A.J.",
        TITLE = "Ask Me Anything: Free-Form Visual Question Answering Based on
Knowledge from External Sources",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4622-4630",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172560"}

@article{bb177222,
        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#TT172561"}

@article{bb177223,
        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#TT172562"}

@article{bb177224,
        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#TT172563"}

@article{bb177225,
        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#TT172564"}

@inproceedings{bb177226,
        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#TT172565"}

@inproceedings{bb177227,
        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#TT172566"}

@article{bb177228,
        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#TT172567"}

@article{bb177229,
        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#TT172568"}

@inproceedings{bb177230,
        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#TT172568"}

@article{bb177231,
        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#TT172569"}

@article{bb177232,
        AUTHOR = "Das, A. and Kottur, S. and Gupta, K. and Singh, A. and Yadav, D. and Lee, S. and Moura, J.M.F. and Parikh, D. and Batra, D.",
        TITLE = "Visual Dialog",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1242-1256",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172570"}

@article{bb177233,
        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#TT172571"}

@article{bb177234,
        AUTHOR = "Zhao, Z. and Zhang, Z. and Jiang, X.H. and Cai, D.",
        TITLE = "Multi-Turn Video Question Answering via Hierarchical Attention
Context Reinforced Networks",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "3860-3872",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172572"}

@article{bb177235,
        AUTHOR = "Guo, Z. and Zhao, Z. and Jin, W. and Wei, Z.C. and Yang, M. and Wang, N.N. and Yuan, N.J.",
        TITLE = "Multi-Turn Video Question Generation via Reinforced Multi-Choice
Attention Network",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "5",
        PAGES = "1697-1710",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172573"}

@article{bb177236,
        AUTHOR = "Gu, M. and Zhao, Z. and Jin, W. and Cai, D. and Wu, F.",
        TITLE = "Video Dialog via Multi-Grained Convolutional Self-Attention Context
Multi-Modal Networks",
        JOURNAL = CirSysVideo,
        VOLUME = "30",
        YEAR = "2020",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "4453-4466",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172574"}

@article{bb177237,
        AUTHOR = "Xue, H.Y. and Chu, W. and Zhao, Z. and Cai, D.",
        TITLE = "A Better Way to Attend: Attention With Trees for Video Question
Answering",
        JOURNAL = IP,
        VOLUME = "27",
        YEAR = "2018",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "5563-5574",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172575"}

@article{bb177238,
        AUTHOR = "Xue, H.Y. and Zhao, Z. and Cai, D.",
        TITLE = "Unifying the Video and Question Attentions for Open-Ended Video
Question Answering",
        JOURNAL = IP,
        VOLUME = "26",
        YEAR = "2017",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "5656-5666",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172576"}

@article{bb177239,
        AUTHOR = "Zhao, Z. and Xiao, S.W. and Song, Z. and Lu, C.J. and Xiao, J. and Zhuang, Y.T.",
        TITLE = "Open-Ended Video Question Answering via Multi-Modal Conditional
Adversarial Networks",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "3859-3870",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT172577"}

@article{bb177240,
        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#TT172578"}

@article{bb177241,
        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#TT172579"}

@article{bb177242,
        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#TT172580"}

@inproceedings{bb177243,
        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#TT172581"}

@article{bb177244,
        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#TT172582"}

@article{bb177245,
        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#TT172583"}

@article{bb177246,
        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#TT172584"}

@article{bb177247,
        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#TT172585"}

@article{bb177248,
        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#TT172586"}

@article{bb177249,
        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#TT172587"}

@inproceedings{bb177250,
        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#TT172588"}

@inproceedings{bb177251,
        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#TT172589"}

@article{bb177252,
        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#TT172590"}

@article{bb177253,
        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#TT172591"}

@inproceedings{bb177254,
        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#TT172592"}

@article{bb177255,
        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#TT172593"}

@article{bb177256,
        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#TT172594"}

@article{bb177257,
        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#TT172595"}

@article{bb177258,
        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#TT172596"}

@article{bb177259,
        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#TT172597"}

@article{bb177260,
        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#TT172598"}

@article{bb177261,
        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#TT172599"}

@inproceedings{bb177262,
        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#TT172600"}

@inproceedings{bb177263,
        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#TT172601"}

@article{bb177264,
        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#TT172602"}

@article{bb177265,
        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#TT172603"}

@article{bb177266,
        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#TT172604"}

@inproceedings{bb177267,
        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#TT172605"}

@article{bb177268,
        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#TT172606"}

@article{bb177269,
        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#TT172607"}

@article{bb177270,
        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#TT172608"}

@article{bb177271,
        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#TT172609"}

@article{bb177272,
        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#TT172610"}

@article{bb177273,
        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#TT172611"}

@article{bb177274,
        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#TT172612"}

@article{bb177275,
        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#TT172613"}

@article{bb177276,
        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#TT172614"}

@article{bb177277,
        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#TT172615"}

@article{bb177278,
        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#TT172616"}

@inproceedings{bb177279,
        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#TT172617"}

@article{bb177280,
        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#TT172618"}

@article{bb177281,
        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#TT172619"}

@article{bb177282,
        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#TT172620"}

@article{bb177283,
        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#TT172621"}

@article{bb177284,
        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#TT172622"}

@article{bb177285,
        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#TT172623"}

@article{bb177286,
        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#TT172624"}

@article{bb177287,
        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#TT172625"}

@inproceedings{bb177288,
        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#TT172626"}

@article{bb177289,
        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#TT172627"}

@article{bb177290,
        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#TT172628"}

@article{bb177291,
        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#TT172629"}

@article{bb177292,
        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#TT172630"}

@article{bb177293,
        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#TT172631"}

@article{bb177294,
        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#TT172632"}

@article{bb177295,
        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#TT172633"}

@article{bb177296,
        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#TT172634"}

@article{bb177297,
        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#TT172635"}

@article{bb177298,
        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#TT172636"}

@article{bb177299,
        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#TT172637"}

Last update:Oct 20, 2021 at 09:45:26