@inproceedings{bb188500,
        AUTHOR = "Li, L. and Gan, Z. and Cheng, Y. and Liu, J.",
        TITLE = "Relation-Aware Graph Attention Network for Visual Question Answering",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "10312-10321",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183780"}

@inproceedings{bb188501,
        AUTHOR = "Peng, G. and You, H.X. and Zhang, Z.P. and Wang, X.G. and Li, H.S.",
        TITLE = "Multi-Modality Latent Interaction Network for Visual Question
Answering",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "5824-5834",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183781"}

@inproceedings{bb188502,
        AUTHOR = "Fan, C.",
        TITLE = "EgoVQA: An Egocentric Video Question Answering Benchmark Dataset",
        BOOKTITLE = EPIC19,
        YEAR = "2019",
        PAGES = "4359-4366",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183782"}

@inproceedings{bb188503,
        AUTHOR = "Do, T. and Tran, H. and Do, T. and Tjiputra, E. and Tran, Q.",
        TITLE = "Compact Trilinear Interaction for Visual Question Answering",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "392-401",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183783"}

@inproceedings{bb188504,
        AUTHOR = "Yang, T. and Zha, Z. and Zhang, H.",
        TITLE = "Making History Matter:
History-Advantage Sequence Training for Visual Dialog",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2561-2569",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183784"}

@inproceedings{bb188505,
        AUTHOR = "Nguyen, D.K. and Okatani, T.",
        TITLE = "Multi-Task Learning of Hierarchical Vision-Language Representation",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10484-10493",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183785"}

@inproceedings{bb188506,
        AUTHOR = "Schwartz, I. and Yu, S. and Hazan, T. and Schwing, A.G.",
        TITLE = "Factor Graph Attention",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "2039-2048",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183786"}

@inproceedings{bb188507,
        AUTHOR = "Kolesnikov, A. and Beyer, L. and Zhai, X.H. and Puigcerver, J. and Yung, J. and Gelly, S. and Houlsby, N.",
        TITLE = "Big Transfer (BIT): General Visual Representation Learning",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "V:491-507",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183787"}

@inproceedings{bb188508,
        AUTHOR = "Kolesnikov, A. and Zhai, X.H. and Beyer, L.",
        TITLE = "Revisiting Self-Supervised Visual Representation Learning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1920-1929",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183788"}

@inproceedings{bb188509,
        AUTHOR = "Xiong, P.X. and Zhan, H.Y. and Wang, X. and Sinha, B. and Wu, Y.",
        TITLE = "Visual Query Answering by Entity-Attribute Graph Matching and Reasoning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8349-8358",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183789"}

@inproceedings{bb188510,
        AUTHOR = "Singh, A. and Natarajan, V. and Shah, M. and Jiang, Y. and Chen, X.L. and Batra, D. and Parikh, D. and Rohrbach, M.",
        TITLE = "Towards VQA Models That Can Read",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8309-8318",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183790"}

@inproceedings{bb188511,
        AUTHOR = "Manjunatha, V. and Saini, N. and Davis, L.S.",
        TITLE = "Explicit Bias Discovery in Visual Question Answering Models",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "9554-9563",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183791"}

@inproceedings{bb188512,
        AUTHOR = "Guo, D. and Xu, C. and Tao, D.C.",
        TITLE = "Image-Question-Answer Synergistic Network for Visual Dialog",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10426-10435",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183792"}

@inproceedings{bb188513,
        AUTHOR = "Shrestha, R. and Kafle, K. and Kanan, C.",
        TITLE = "Answer Them All! Toward Universal Visual Question Answering Models",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10464-10473",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183793"}

@inproceedings{bb188514,
        AUTHOR = "Zadeh, A. and Chan, M. and Liang, P.P. and Tong, E. and Morency, L.P.",
        TITLE = "Social-IQ: A Question Answering Benchmark for Artificial Social
Intelligence",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8799-8809",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183794"}

@inproceedings{bb188515,
        AUTHOR = "Noh, H. and Kim, T. and Mun, J. and Han, B.H.",
        TITLE = "Transfer Learning via Unsupervised Task Discovery for Visual Question
Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8377-8386",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183795"}

@inproceedings{bb188516,
        AUTHOR = "Kim, J.Y. and Ma, M. and Kim, K. and Kim, S. and Yoo, C.D.",
        TITLE = "Progressive Attention Memory Network for Movie Story Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8329-8338",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183796"}

@inproceedings{bb188517,
        AUTHOR = "Hudson, D.A. and Manning, C.D.",
        TITLE = "GQA: A New Dataset for Real-World Visual Reasoning and Compositional
Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6693-6702",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183797"}

@inproceedings{bb188518,
        AUTHOR = "Wijmans, E. and Datta, S. and Maksymets, O. and Das, A. and Gkioxari, G. and Lee, S. and Essa, I. and Parikh, D. and Batra, D.",
        TITLE = "Embodied Question Answering in Photorealistic Environments With Point
Cloud Perception",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6652-6661",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183798"}

@inproceedings{bb188519,
        AUTHOR = "Shah, M. and Chen, X.L. and Rohrbach, M. and Parikh, D.",
        TITLE = "Cycle-Consistency for Robust Visual Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6642-6651",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183799"}

@inproceedings{bb188520,
        AUTHOR = "Zheng, Z.L. and Wang, W.G. and Qi, S.Y. and Zhu, S.C.",
        TITLE = "Reasoning Visual Dialogs With Structural and Partial Observations",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6662-6671",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183800"}

@inproceedings{bb188521,
        AUTHOR = "Li, H. and Wang, P. and Shen, C.H. and van den Hengel, A.",
        TITLE = "Visual Question Answering as Reading Comprehension",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6312-6321",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183801"}

@inproceedings{bb188522,
        AUTHOR = "Yu, L.C. and Chen, X.L. and Gkioxari, G. and Bansal, M. and Berg, T.L. and Batra, D.",
        TITLE = "Multi-Target Embodied Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6302-6311",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183802"}

@inproceedings{bb188523,
        AUTHOR = "Yu, Z. and Yu, J. and Cui, Y. and Tao, D.C. and Tian, Q.",
        TITLE = "Deep Modular Co-Attention Networks for Visual Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6274-6283",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183803"}

@inproceedings{bb188524,
        AUTHOR = "Abbasnejad, E. and Wu, Q. and Shi, Q.F. and van den Hengel, A.",
        TITLE = "What's to Know? Uncertainty as a Guide to Asking Goal-Oriented
Questions",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "4150-4159",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183804"}

@inproceedings{bb188525,
        AUTHOR = "Marino, K. and Rastegari, M. and Farhadi, A. and Mottaghi, R.",
        TITLE = "OK-VQA: A Visual Question Answering Benchmark Requiring External
Knowledge",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "3190-3199",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183805"}

@inproceedings{bb188526,
        AUTHOR = "Krishna, R. and Bernstein, M. and Fei Fei, L.",
        TITLE = "Information Maximizing Visual Question Generation",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "2008-2018",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183806"}

@inproceedings{bb188527,
        AUTHOR = "Fan, C.Y. and Zhang, X.F. and Zhang, S. and Wang, W.S. and Zhang, C. and Huang, H.",
        TITLE = "Heterogeneous Memory Enhanced Multimodal Attention Model for Video
Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1999-2007",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183807"}

@inproceedings{bb188528,
        AUTHOR = "Cadene, R. and Ben younes, H. and Cord, M. and Thome, N.",
        TITLE = "MUREL: Multimodal Relational Reasoning for Visual Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1989-1998",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183808"}

@inproceedings{bb188529,
        AUTHOR = "Haurilet, M. and Roitberg, A. and Stiefelhagen, R.",
        TITLE = "It's Not About the Journey; It's About the Destination: Following Soft
Paths Under Question-Guidance for Visual Reasoning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1930-1939",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183809"}

@inproceedings{bb188530,
        AUTHOR = "Qiu, Y. and Satoh, Y. and Suzuki, R. and Kataoka, H.",
        TITLE = "Incorporating 3D Information Into Visual Question Answering",
        BOOKTITLE = "3DV19",
        YEAR = "2019",
        PAGES = "756-765",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183810"}

@inproceedings{bb188531,
        AUTHOR = "Haurilet, M. and Al Halah, Z. and Stiefelhagen, R.",
        TITLE = "DynGraph: Visual Question Answering via Dynamic Scene Graphs",
        BOOKTITLE = GCPR19,
        YEAR = "2019",
        PAGES = "428-441",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183811"}

@inproceedings{bb188532,
        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#TT183812"}

@inproceedings{bb188533,
        AUTHOR = "Liu, F. and Liu, J. and Fang, Z. and Lu, H.",
        TITLE = "Language and Visual Relations Encoding for Visual Question Answering",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "3307-3311",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183813"}

@inproceedings{bb188534,
        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#TT183814"}

@inproceedings{bb188535,
        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#TT183815"}

@inproceedings{bb188536,
        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#TT183816"}

@inproceedings{bb188537,
        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#TT183817"}

@inproceedings{bb188538,
        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#TT183818"}

@inproceedings{bb188539,
        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#TT183819"}

@inproceedings{bb188540,
        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#TT183820"}

@inproceedings{bb188541,
        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#TT183821"}

@inproceedings{bb188542,
        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#TT183822"}

@inproceedings{bb188543,
        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#TT183823"}

@inproceedings{bb188544,
        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#TT183824"}

@inproceedings{bb188545,
        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#TT183825"}

@inproceedings{bb188546,
        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#TT183826"}

@inproceedings{bb188547,
        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#TT183827"}

@inproceedings{bb188548,
        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#TT183828"}

@inproceedings{bb188549,
        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#TT183829"}

@inproceedings{bb188550,
        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#TT183830"}

@inproceedings{bb188551,
        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#TT183831"}

@inproceedings{bb188552,
        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#TT183832"}

@inproceedings{bb188553,
        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#TT183833"}

@inproceedings{bb188554,
        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#TT183834"}

@inproceedings{bb188555,
        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#TT183835"}

@inproceedings{bb188556,
        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#TT183836"}

@inproceedings{bb188557,
        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#TT183837"}

@inproceedings{bb188558,
        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#TT183838"}

@inproceedings{bb188559,
        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#TT183839"}

@inproceedings{bb188560,
        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#TT183840"}

@inproceedings{bb188561,
        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#TT183841"}

@inproceedings{bb188562,
        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#TT183842"}

@inproceedings{bb188563,
        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#TT183843"}

@inproceedings{bb188564,
        AUTHOR = "Zhou, B. and Sun, Y. and Bau, D. and Torralba, A.B.",
        TITLE = "Interpretable Basis Decomposition for Visual Explanation",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VIII: 122-138",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183844"}

@inproceedings{bb188565,
        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#TT183845"}

@inproceedings{bb188566,
        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#TT183846"}

@inproceedings{bb188567,
        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#TT183847"}

@inproceedings{bb188568,
        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#TT183848"}

@inproceedings{bb188569,
        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#TT183849"}

@inproceedings{bb188570,
        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#TT183850"}

@inproceedings{bb188571,
        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#TT183851"}

@inproceedings{bb188572,
        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#TT183852"}

@inproceedings{bb188573,
        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#TT183853"}

@inproceedings{bb188574,
        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#TT183854"}

@inproceedings{bb188575,
        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#TT183855"}

@inproceedings{bb188576,
        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#TT183856"}

@inproceedings{bb188577,
        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#TT183857"}

@inproceedings{bb188578,
        AUTHOR = "Huang, L. and Kulkarni, K. and Jha, A. and Lohit, S. and Jayasuriya, S. and Turaga, P.K.",
        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#TT183858"}

@inproceedings{bb188579,
        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#TT183859"}

@inproceedings{bb188580,
        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#TT183860"}

@inproceedings{bb188581,
        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#TT183861"}

@inproceedings{bb188582,
        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#TT183862"}

@inproceedings{bb188583,
        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#TT183863"}

@inproceedings{bb188584,
        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#TT183864"}

@inproceedings{bb188585,
        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#TT183865"}

@inproceedings{bb188586,
        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#TT183866"}

@inproceedings{bb188587,
        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#TT183867"}

@inproceedings{bb188588,
        AUTHOR = "Mun, J. and Seo, P.H. and Jung, I. and Han, B.H.",
        TITLE = "MarioQA: Answering Questions by Watching Gameplay Videos",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2886-2894",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT183868"}

@inproceedings{bb188589,
        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#TT183869"}

@inproceedings{bb188590,
        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#TT183870"}

@inproceedings{bb188591,
        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#TT183871"}

@inproceedings{bb188592,
        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#TT183872"}

@inproceedings{bb188593,
        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#TT183873"}

@inproceedings{bb188594,
        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#TT183874"}

@inproceedings{bb188595,
        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#TT183875"}

@inproceedings{bb188596,
        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#TT183876"}

@inproceedings{bb188597,
        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#TT183877"}

@inproceedings{bb188598,
        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#TT183878"}

@inproceedings{bb188599,
        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#TT183879"}

Last update:Sep 1, 2022 at 11:00:56