@inproceedings{bb154100,
        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#TT149660"}

@inproceedings{bb154101,
        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#TT149661"}

@inproceedings{bb154102,
        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#TT149662"}

@inproceedings{bb154103,
        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#TT149663"}

@inproceedings{bb154104,
        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#TT149664"}

@article{bb154105,
        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#TT149668"}

@inproceedings{bb154106,
        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#TT149669"}

@article{bb154107,
        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#TT149670"}

@inproceedings{bb154108,
        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#TT149671"}

@article{bb154109,
        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#TT149672"}

@article{bb154110,
        AUTHOR = "Xue, H. 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#TT149673"}

@article{bb154111,
        AUTHOR = "Xue, H. 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#TT149674"}

@article{bb154112,
        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#TT149675"}

@inproceedings{bb154113,
        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#TT149676"}

@article{bb154114,
        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#TT149677"}

@article{bb154115,
        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#TT149678"}

@article{bb154116,
        AUTHOR = "Tamaazousti, Y. and Borgne, H.L. 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#TT149679"}

@article{bb154117,
        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#TT149680"}

@article{bb154118,
        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#TT149681"}

@inproceedings{bb154119,
        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#TT149682"}

@inproceedings{bb154120,
        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#TT149683"}

@article{bb154121,
        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#TT149684"}

@inproceedings{bb154122,
        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#TT149685"}

@article{bb154123,
        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#TT149686"}

@article{bb154124,
        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#TT149687"}

@article{bb154125,
        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#TT149688"}

@inproceedings{bb154126,
        AUTHOR = "Zhang, Q.S. and Cao, R. 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#TT149689"}

@inproceedings{bb154127,
        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#TT149690"}

@article{bb154128,
        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#TT149691"}

@article{bb154129,
        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#TT149692"}

@inproceedings{bb154130,
        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#TT149692"}

@article{bb154131,
        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#TT149693"}

@article{bb154132,
        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#TT149694"}

@article{bb154133,
        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#TT149695"}

@article{bb154134,
        AUTHOR = "Liang, J.W. and Jiang, L. and Cao, L.L. and Kalantidis, Y. and Li, L.J. and Hauptmann, A.G.",
        TITLE = "Focal Visual-Text Attention for Memex Question Answering",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1893-1908",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149696"}

@inproceedings{bb154135,
        AUTHOR = "Liang, J.W. and Jiang, L. and Cao, L.L. and Li, L.J. and Hauptmann, A.G.",
        TITLE = "Focal Visual-Text Attention for Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6135-6143",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149697"}

@article{bb154136,
        AUTHOR = "Zhao, Z. and Zhang, Z. and Jiang, X. 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#TT149698"}

@inproceedings{bb154137,
        AUTHOR = "Liu, C.N. and Chen, D.J. and Chen, H.T. and Liu, T.L.",
        TITLE = "A2A: Attention to Attention Reasoning for Movie Question Answering",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "VI:404-419",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149699"}

@inproceedings{bb154138,
        AUTHOR = "Fang, Z.W. and Liu, J. and Tang, Q. and Li, Y. and Lu, H.Q.",
        TITLE = "Answer Distillation for Visual Question Answering",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "I:72-87",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149700"}

@inproceedings{bb154139,
        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#TT149701"}

@inproceedings{bb154140,
        AUTHOR = "Kuhnle, A. and Xie, H.Y. and Copestake, A.",
        TITLE = "How Clever Is the FiLM Model, and How Clever Can it Be?",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:162-172",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149702"}

@inproceedings{bb154141,
        AUTHOR = "Haurilet, M. and Al Halah, Z. and Stiefelhagen, R.",
        TITLE = "MoQA: A Multi-modal Question Answering Architecture",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:106-113",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149703"}

@inproceedings{bb154142,
        AUTHOR = "Li, W. and Yuan, Z.H. and Fang, X.Z. and Wang, C.",
        TITLE = "Knowing Where to Look? Analysis on Attention of Visual Question
Answering System",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:145-152",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149704"}

@inproceedings{bb154143,
        AUTHOR = "Bani, G. and Belli, D. and Dagan, G. and Geenen, A. and Skliar, A. and Venkatesh, A. and Baumgartner, T. and Bruni, E. and Fernandez, R.",
        TITLE = "Adding Object Detection Skills to Visual Dialogue Agents",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:180-187",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149705"}

@inproceedings{bb154144,
        AUTHOR = "Wagner, M. and Basevi, H. and Shetty, R. and Li, W.B. and Malinowski, M. and Fritz, M. and Leonardis, A.",
        TITLE = "Answering Visual What-If Questions: From Actions to Predicted Scene
Descriptions",
        BOOKTITLE = VLEASE18,
        YEAR = "2018",
        PAGES = "I:521-537",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149706"}

@inproceedings{bb154145,
        AUTHOR = "Zhang, Y. and Niebles, J.C. and Soto, A.",
        TITLE = "Interpretable Visual Question Answering by Visual Grounding From
Attention Supervision Mining",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "349-357",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149707"}

@inproceedings{bb154146,
        AUTHOR = "Zhuang, B. and Wu, Q. and Shen, C. and Reid, I.D. and van den Hengel, A.J.",
        TITLE = "Parallel Attention: A Unified Framework for Visual Object Discovery
Through Dialogs and Queries",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4252-4261",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149708"}

@inproceedings{bb154147,
        AUTHOR = "Yang, M. and Yang, N.S.R. and Zhang, K. and Tao, J.",
        TITLE = "Self-Talk: Responses to Users' Opinions and Challenges in Human
Computer Dialog",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "2839-2844",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149709"}

@inproceedings{bb154148,
        AUTHOR = "Duke, B. and Taylor, G.W.",
        TITLE = "Generalized Hadamard-Product Fusion Operators for Visual Question
Answering",
        BOOKTITLE = CRV18,
        YEAR = "2018",
        PAGES = "39-46",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149710"}

@inproceedings{bb154149,
        AUTHOR = "Das, A. and Datta, S. and Gkioxari, G. and Lee, S. and Parikh, D. and Batra, D.",
        TITLE = "Embodied Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "1-10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149711"}

@inproceedings{bb154150,
        AUTHOR = "Misra, I. and Girshick, R. and Fergus, R. and Hebert, M. and Gupta, A. and van der Maaten, L.",
        TITLE = "Learning by Asking Questions",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "11-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149712"}

@inproceedings{bb154151,
        AUTHOR = "Gurari, D. and Li, Q. and Stangl, A.J. and Guo, A. and Lin, C. and Grauman, K. and Luo, J. and Bigham, J.P.",
        TITLE = "VizWiz Grand Challenge: Answering Visual Questions from Blind People",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "3608-3617",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149713"}

@inproceedings{bb154152,
        AUTHOR = "Li, J. and Su, H. and Zhu, J. and Wang, S. and Zhang, B.",
        TITLE = "Textbook Question Answering Under Instructor Guidance with Memory
Networks",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "3655-3663",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149714"}

@inproceedings{bb154153,
        AUTHOR = "Gordon, D. and Kembhavi, A. and Rastegari, M. and Redmon, J. and Fox, D. and Farhadi, A.",
        TITLE = "IQA: Visual Question Answering in Interactive Environments",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4089-4098",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149715"}

@inproceedings{bb154154,
        AUTHOR = "Agrawal, A. and Batra, D. and Parikh, D. and Kembhavi, A.",
        TITLE = "Don't Just Assume; Look and Answer: Overcoming Priors for Visual
Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4971-4980",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149716"}

@inproceedings{bb154155,
        AUTHOR = "Sha, F. and Chao, W. and Hu, H.",
        TITLE = "Learning Answer Embeddings for Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "5428-5436",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149717"}

@inproceedings{bb154156,
        AUTHOR = "Kafle, K. and Price, B. and Cohen, S. and Kanan, C.",
        TITLE = "DVQA: Understanding Data Visualizations via Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "5648-5656",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149718"}

@inproceedings{bb154157,
        AUTHOR = "Sha, F. and Hu, H. and Chao, W.",
        TITLE = "Cross-Dataset Adaptation for Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "5716-5725",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149719"}

@inproceedings{bb154158,
        AUTHOR = "Jain, U. and Schwing, A. and Lazebnik, S.",
        TITLE = "Two Can Play This Game: Visual Dialog with Discriminative Question
Generation and Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "5754-5763",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149720"}

@inproceedings{bb154159,
        AUTHOR = "Anderson, P. and He, X. and Buehler, C. and Teney, D. and Johnson, M. and Gould, S. and Zhang, L.",
        TITLE = "Bottom-Up and Top-Down Attention for Image Captioning and Visual
Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6077-6086",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149721"}

@inproceedings{bb154160,
        AUTHOR = "Nguyen, D. and Okatani, T.",
        TITLE = "Improved Fusion of Visual and Language Representations by Dense
Symmetric Co-attention for Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6087-6096",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149722"}

@inproceedings{bb154161,
        AUTHOR = "Dokania, P.K. and Torr, P.H.S. and Siddharth, N. and Massiceti, D.",
        TITLE = "FLIPDIAL: A Generative Model for Two-Way Visual Dialogue",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6097-6105",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149723"}

@inproceedings{bb154162,
        AUTHOR = "Wu, Q. and Wang, P. and Shen, C. and Reid, I.D. and van den Hengel, A.J.",
        TITLE = "Are You Talking to Me? Reasoned Visual Dialog Generation Through
Adversarial Learning",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6106-6115",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149724"}

@inproceedings{bb154163,
        AUTHOR = "Gao, J. and Ge, R. and Chen, K. and Nevatia, R.",
        TITLE = "Motion-Appearance Co-memory Networks for Video Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6576-6585",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149725"}

@inproceedings{bb154164,
        AUTHOR = "Ma, C. and Shen, C. and Dick, A. and Wu, Q. and Wang, P. and van den Hengel, A.J. and Reid, I.D.",
        TITLE = "Visual Question Answering with Memory-Augmented Networks",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6975-6984",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149726"}

@inproceedings{bb154165,
        AUTHOR = "Cao, Q. and Liang, X. and Li, B. 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#TT149727"}

@inproceedings{bb154166,
        AUTHOR = "Patro, B. and Namboodiri, V.P.",
        TITLE = "Differential Attention for Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7680-7688",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149728"}

@inproceedings{bb154167,
        AUTHOR = "Su, Z. and Zhu, C. and Dong, Y. and Cai, D. and Chen, Y. and Li, J.",
        TITLE = "Learning Visual Knowledge Memory Networks for Visual Question
Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7736-7745",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149729"}

@inproceedings{bb154168,
        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#TT149730"}

@inproceedings{bb154169,
        AUTHOR = "Shin, A. and Ushiku, Y. and Harada, T.",
        TITLE = "Customized Image Narrative Generation via Interactive Visual Question
Generation and Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "8925-8933",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149731"}

@inproceedings{bb154170,
        AUTHOR = "Das, A. and Datta, S. and Gkioxari, G. and Lee, S. and Parikh, D. and Batra, D.",
        TITLE = "Embodied Question Answering",
        BOOKTITLE = DeepLearnRV18,
        YEAR = "2018",
        PAGES = "2135-213509",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149732"}

@inproceedings{bb154171,
        AUTHOR = "Cheng, W. and Huang, Y. and Wang, L.",
        TITLE = "Towards Unconstrained Pointing Problem of Visual Question Answering:
A Retrieval-based Method",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3303-3308",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149733"}

@inproceedings{bb154172,
        AUTHOR = "Teney, D. and Anderson, P. and He, X. and van den Hengel, A.J.",
        TITLE = "Tips and Tricks for Visual Question Answering:
Learnings from the 2017 Challenge",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4223-4232",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149734"}

@inproceedings{bb154173,
        AUTHOR = "Zhou, B. and Sun, Y. and Bau, D. and Torralba, A.",
        TITLE = "Interpretable Basis Decomposition for Visual Explanation",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VIII: 122-138",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149735"}

@inproceedings{bb154174,
        AUTHOR = "Kottur, S. and Moura, J.M.F. and Parikh, D. and Batra, D. and Rohrbach, M.",
        TITLE = "Visual Coreference Resolution in Visual Dialog Using Neural Module
Networks",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XV: 160-178",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149736"}

@inproceedings{bb154175,
        AUTHOR = "Strub, F. and Seurin, M. and Perez, E. and de Vries, H. and Mary, J. and Preux, P. and Courville, A. and Pietquin, O.",
        TITLE = "Visual Reasoning with Multi-hop Feature Modulation",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VI: 808-831",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149737"}

@inproceedings{bb154176,
        AUTHOR = "Shi, Y. and Furlanello, T. and Zha, S. and Anandkumar, A.",
        TITLE = "Question Type Guided Attention in Visual Question Answering",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "II: 158-175",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149738"}

@inproceedings{bb154177,
        AUTHOR = "Narasimhan, M. and Schwing, A.G.",
        TITLE = "Straight to the Facts: Learning Knowledge Base Retrieval for Factual
Visual Question Answering",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VIII: 460-477",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149739"}

@inproceedings{bb154178,
        AUTHOR = "Yang, G.R. and Ganichev, I. and Wang, X.J. and Shlens, J. and Sussillo, D.",
        TITLE = "A Dataset and Architecture for Visual Reasoning with a Working Memory",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "X: 729-745",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149740"}

@inproceedings{bb154179,
        AUTHOR = "Malinowski, M. and Doersch, C. and Santoro, A. and Battaglia, P.",
        TITLE = "Learning Visual Question Answering by Bootstrapping Hard Attention",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VI: 3-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149741"}

@inproceedings{bb154180,
        AUTHOR = "Kim, K.M. and Choi, S.H. and Kim, J.H. and Zhang, B.T.",
        TITLE = "Multimodal Dual Attention Memory for Video Story Question Answering",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XV: 698-713",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149742"}

@inproceedings{bb154181,
        AUTHOR = "Yu, Y.J. and Kim, J.S. and Kim, G.",
        TITLE = "A Joint Sequence Fusion Model for Video Question Answering and
Retrieval",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VII: 487-503",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149743"}

@inproceedings{bb154182,
        AUTHOR = "Gu, J.X. and Cai, J.F. and Joty, S. and Niu, L. and Wang, G.",
        TITLE = "Look, Imagine and Match: Improving Textual-Visual Cross-Modal
Retrieval with Generative Models",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7181-7189",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149744"}

@inproceedings{bb154183,
        AUTHOR = "Li, Q. and Tao, Q.Y. and Joty, S. and Cai, J.F. and Luo, J.B.",
        TITLE = "VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual
Questions",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VII: 570-586",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149745"}

@inproceedings{bb154184,
        AUTHOR = "Bai, Y.L. and Fu, J.L. and Zhao, T.J. and Mei, T.",
        TITLE = "Deep Attention Neural Tensor Network for Visual Question Answering",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XII: 21-37",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149746"}

@inproceedings{bb154185,
        AUTHOR = "Sinha, A. and Ayush, K.",
        TITLE = "Towards Mathematical Reasoning: A Multimodal Deep Learning Approach",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "4028-4032",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149747"}

@inproceedings{bb154186,
        AUTHOR = "Yu, D. and Gao, X. and Xiong, H.",
        TITLE = "Structured Semantic Representation for Visual Question Answering",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "2286-2290",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149748"}

@inproceedings{bb154187,
        AUTHOR = "Huang, L. and Kulkarni, K. and Jha, A. and Lohit, S. and Jayasuriya, S. and Turaga, P.",
        TITLE = "CS-VQA: Visual Question Answering with Compressively Sensed Images",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "1283-1287",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149749"}

@inproceedings{bb154188,
        AUTHOR = "Hasan Chowdhury, M.I. and Nguyen, K. and Sridharan, S. and Fookes, C.",
        TITLE = "Hierarchical Relational Attention for Video Question Answering",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "599-603",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149750"}

@inproceedings{bb154189,
        AUTHOR = "Desta, M.T. and Chen, L. and Kornuta, T.",
        TITLE = "Object-Based Reasoning in VQA",
        BOOKTITLE = WACV18,
        YEAR = "2018",
        PAGES = "1814-1823",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149751"}

@inproceedings{bb154190,
        AUTHOR = "Zhao, H. and Fan, Q. and Gutfreund, D. and Fu, Y.",
        TITLE = "Semantically Guided Visual Question Answering",
        BOOKTITLE = WACV18,
        YEAR = "2018",
        PAGES = "1852-1860",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149752"}

@inproceedings{bb154191,
        AUTHOR = "Wang, Z. and Liu, X. and Wang, L. and Qiao, Y. and Xie, X. and Fowlkes, C.C.",
        TITLE = "Structured Triplet Learning with POS-Tag Guided Attention for Visual
Question Answering",
        BOOKTITLE = WACV18,
        YEAR = "2018",
        PAGES = "1888-1896",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149753"}

@inproceedings{bb154192,
        AUTHOR = "Chowdhury, I. and Nguyen, K. and Fookes, C. and Sridharan, S.",
        TITLE = "A cascaded long short-term memory (LSTM) driven generic visual
question answering (VQA)",
        BOOKTITLE = ICIP17,
        YEAR = "2017",
        PAGES = "1842-1846",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149754"}

@inproceedings{bb154193,
        AUTHOR = "Sheng, S. and Venkitasubramanian, A.N. and Moens, M.F.",
        TITLE = "A Markov Network Based Passage Retrieval Method for Multimodal Question
Answering in the Cultural Heritage Domain",
        BOOKTITLE = MMMod18,
        YEAR = "2018",
        PAGES = "I:3-15",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149755"}

@inproceedings{bb154194,
        AUTHOR = "Rosso Mateus, A. and Gonzalez, F.A. and Montes y Gomez, M.",
        TITLE = "A Two-Step Neural Network Approach to Passage Retrieval for Open Domain
Question Answering",
        BOOKTITLE = CIARP17,
        YEAR = "2017",
        PAGES = "566-574",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149756"}

@inproceedings{bb154195,
        AUTHOR = "Gupta, T. and Shih, K.J. and Singh, S. and Hoiem, D.",
        TITLE = "Aligned Image-Word Representations Improve Inductive Transfer Across
Vision-Language Tasks",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "4223-4232",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149757"}

@inproceedings{bb154196,
        AUTHOR = "Das, A. and Kottur, S. and Moura, J.M.F. and Lee, S. and Batra, D.",
        TITLE = "Learning Cooperative Visual Dialog Agents with Deep Reinforcement
Learning",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2970-2979",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149758"}

@inproceedings{bb154197,
        AUTHOR = "Mun, J. and Seo, P.H. and Jung, I. and Han, B.",
        TITLE = "MarioQA: Answering Questions by Watching Gameplay Videos",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2886-2894",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149759"}

@inproceedings{bb154198,
        AUTHOR = "Gan, C. and Li, Y. and Li, H. and Sun, C. and Gong, B.",
        TITLE = "VQS: Linking Segmentations to Questions and Answers for Supervised
Attention in VQA and Question-Focused Semantic Segmentation",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1829-1838",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149760"}

@inproceedings{bb154199,
        AUTHOR = "Yu, Z. and Yu, J. and Fan, J. and Tao, D.",
        TITLE = "Multi-modal Factorized Bilinear Pooling with Co-attention Learning
for Visual Question Answering",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1839-1848",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT149761"}

Last update:Sep 9, 2019 at 16:26:55