@article{bb152800,
        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#TT148377"}

@article{bb152801,
        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#TT148378"}

@article{bb152802,
        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#TT148379"}

@article{bb152803,
        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#TT148380"}

@inproceedings{bb152804,
        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#TT148381"}

@inproceedings{bb152805,
        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#TT148382"}

@article{bb152806,
        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#TT148383"}

@inproceedings{bb152807,
        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#TT148384"}

@article{bb152808,
        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#TT148385"}

@article{bb152809,
        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#TT148386"}

@article{bb152810,
        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#TT148387"}

@inproceedings{bb152811,
        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#TT148388"}

@inproceedings{bb152812,
        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#TT148389"}

@article{bb152813,
        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#TT148390"}

@article{bb152814,
        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#TT148391"}

@inproceedings{bb152815,
        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#TT148391"}

@article{bb152816,
        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#TT148392"}

@article{bb152817,
        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#TT148393"}

@article{bb152818,
        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#TT148394"}

@inproceedings{bb152819,
        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#TT148395"}

@inproceedings{bb152820,
        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#TT148396"}

@inproceedings{bb152821,
        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#TT148397"}

@inproceedings{bb152822,
        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#TT148398"}

@inproceedings{bb152823,
        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#TT148399"}

@inproceedings{bb152824,
        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#TT148400"}

@inproceedings{bb152825,
        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#TT148401"}

@inproceedings{bb152826,
        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#TT148402"}

@inproceedings{bb152827,
        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#TT148403"}

@inproceedings{bb152828,
        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#TT148404"}

@inproceedings{bb152829,
        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#TT148405"}

@inproceedings{bb152830,
        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#TT148406"}

@inproceedings{bb152831,
        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#TT148407"}

@inproceedings{bb152832,
        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#TT148408"}

@inproceedings{bb152833,
        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#TT148409"}

@inproceedings{bb152834,
        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#TT148410"}

@inproceedings{bb152835,
        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#TT148411"}

@inproceedings{bb152836,
        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#TT148412"}

@inproceedings{bb152837,
        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#TT148413"}

@inproceedings{bb152838,
        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#TT148414"}

@inproceedings{bb152839,
        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#TT148415"}

@inproceedings{bb152840,
        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#TT148416"}

@inproceedings{bb152841,
        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#TT148417"}

@inproceedings{bb152842,
        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#TT148418"}

@inproceedings{bb152843,
        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#TT148419"}

@inproceedings{bb152844,
        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#TT148420"}

@inproceedings{bb152845,
        AUTHOR = "Liang, J. and Jiang, L. and Cao, L. and Li, L. and Hauptmann, A.",
        TITLE = "Focal Visual-Text Attention for Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6135-6143",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148421"}

@inproceedings{bb152846,
        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#TT148422"}

@inproceedings{bb152847,
        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#TT148423"}

@inproceedings{bb152848,
        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#TT148424"}

@inproceedings{bb152849,
        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#TT148425"}

@inproceedings{bb152850,
        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#TT148426"}

@inproceedings{bb152851,
        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#TT148427"}

@inproceedings{bb152852,
        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#TT148428"}

@inproceedings{bb152853,
        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#TT148429"}

@inproceedings{bb152854,
        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#TT148430"}

@inproceedings{bb152855,
        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#TT148431"}

@inproceedings{bb152856,
        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#TT148432"}

@inproceedings{bb152857,
        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#TT148433"}

@inproceedings{bb152858,
        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#TT148434"}

@inproceedings{bb152859,
        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#TT148435"}

@inproceedings{bb152860,
        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#TT148436"}

@inproceedings{bb152861,
        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#TT148437"}

@inproceedings{bb152862,
        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#TT148438"}

@inproceedings{bb152863,
        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#TT148439"}

@inproceedings{bb152864,
        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#TT148440"}

@inproceedings{bb152865,
        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#TT148441"}

@inproceedings{bb152866,
        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#TT148442"}

@inproceedings{bb152867,
        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#TT148443"}

@inproceedings{bb152868,
        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#TT148444"}

@inproceedings{bb152869,
        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#TT148445"}

@inproceedings{bb152870,
        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#TT148446"}

@inproceedings{bb152871,
        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#TT148447"}

@inproceedings{bb152872,
        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#TT148448"}

@inproceedings{bb152873,
        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#TT148449"}

@inproceedings{bb152874,
        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#TT148450"}

@inproceedings{bb152875,
        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#TT148451"}

@inproceedings{bb152876,
        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#TT148452"}

@inproceedings{bb152877,
        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#TT148453"}

@inproceedings{bb152878,
        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#TT148454"}

@inproceedings{bb152879,
        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#TT148455"}

@inproceedings{bb152880,
        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#TT148456"}

@inproceedings{bb152881,
        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#TT148457"}

@inproceedings{bb152882,
        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#TT148458"}

@inproceedings{bb152883,
        AUTHOR = "Ben younes, H. and Cadene, R. and Cord, M. and Thome, N.",
        TITLE = "MUTAN: Multimodal Tucker Fusion for Visual Question Answering",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2631-2639",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148459"}

@inproceedings{bb152884,
        AUTHOR = "Zhu, C. and Zhao, Y. and Huang, S. and Tu, K. and Ma, Y.",
        TITLE = "Structured Attentions for Visual Question Answering",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1300-1309",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148460"}

@inproceedings{bb152885,
        AUTHOR = "Hu, R. and Andreas, J. and Rohrbach, M. and Darrell, T.J. and Saenko, K.",
        TITLE = "Learning to Reason: End-to-End Module Networks for Visual Question
Answering",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "804-813",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148461"}

@inproceedings{bb152886,
        AUTHOR = "Jain, U. and Zhang, Z.Y. and Schwing, A.",
        TITLE = "Creativity: Generating Diverse Questions Using Variational
Autoencoders",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "5415-5424",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148462"}

@inproceedings{bb152887,
        AUTHOR = "de Vries, H. and Strub, F. and Chandar, S. and Pietquin, O. and Larochelle, H. and Courville, A.",
        TITLE = "GuessWhat?! Visual Object Discovery through Multi-modal Dialogue",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "4466-4475",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148463"}

@inproceedings{bb152888,
        AUTHOR = "Nam, H. and Ha, J.W. and Kim, J.",
        TITLE = "Dual Attention Networks for Multimodal Reasoning and Matching",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "2156-2164",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148464"}

@inproceedings{bb152889,
        AUTHOR = "Johnson, J. and Hariharan, B. and van der Maaten, L. and Hoffman, J. and Fei Fei, L. and Zitnick, C.L. and Girshick, R.",
        TITLE = "Inferring and Executing Programs for Visual Reasoning",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "3008-3017",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148465"}

@inproceedings{bb152890,
        AUTHOR = "Johnson, J. and Hariharan, B. and van der Maaten, L. and Fei Fei, L. and Zitnick, C.L. and Girshick, R.",
        TITLE = "CLEVR: A Diagnostic Dataset for Compositional Language and Elementary
Visual Reasoning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1988-1997",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148466"}

@inproceedings{bb152891,
        AUTHOR = "Yu, Y. and Ko, H. and Choi, J. and Kim, G.",
        TITLE = "End-to-End Concept Word Detection for Video Captioning, Retrieval,
and Question Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3261-3269",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148467"}

@inproceedings{bb152892,
        AUTHOR = "Das, A. and Kottur, S. and Gupta, K. and Singh, A. and Yadav, D. and Moura, J.M.F. and Parikh, D. and Batra, D.",
        TITLE = "Visual Dialog",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1080-1089",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148468"}

@inproceedings{bb152893,
        AUTHOR = "Zhu, Y. and Lim, J.J. and Fei Fei, L.",
        TITLE = "Knowledge Acquisition for Visual Question Answering via Iterative
Querying",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6146-6155",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148469"}

@inproceedings{bb152894,
        AUTHOR = "Bolanos, M. and Peris, A. and Casacuberta, F. and Radeva, P.",
        TITLE = "VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question
Answering",
        BOOKTITLE = IbPRIA17,
        YEAR = "2017",
        PAGES = "372-380",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148470"}

@inproceedings{bb152895,
        AUTHOR = "Gao, P. and Li, H.S. and Li, S. and Lu, P. and Li, Y.K. and Hoi, S.C.H. and Wang, X.G.",
        TITLE = "Question-Guided Hybrid Convolution for Visual Question Answering",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "I: 485-501",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148471"}

@inproceedings{bb152896,
        AUTHOR = "Li, Y.K. and Duan, N. and Zhou, B.L. and Chu, X. and Ouyang, W.L. and Wang, X.G. and Zhou, M.",
        TITLE = "Visual Question Generation as Dual Task of Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6116-6124",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148472"}

@inproceedings{bb152897,
        AUTHOR = "Lin, Y.T. and Pang, Z.Y. and Li, Y. and Wang, D.H.",
        TITLE = "Simple and effective visual question answering in a single modality",
        BOOKTITLE = ICIP16,
        YEAR = "2016",
        PAGES = "2276-2280",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148473"}

@inproceedings{bb152898,
        AUTHOR = "Kafle, K. and Kanan, C.",
        TITLE = "An Analysis of Visual Question Answering Algorithms",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1983-1991",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148474"}

@inproceedings{bb152899,
        AUTHOR = "Kafle, K. and Kanan, C.",
        TITLE = "Answer-Type Prediction for Visual Question Answering",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4976-4984",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT148475"}

Last update:Jun 24, 2019 at 10:45:36