@inproceedings{bb198700,
        AUTHOR = "Schwenk, D. and Khandelwal, A. and Clark, C. and Marino, K. and Mottaghi, R.",
        TITLE = "A-OKVQA: A Benchmark for Visual Question Answering Using World
Knowledge",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "VIII:146-162",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193901"}

@inproceedings{bb198701,
        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#TT193902"}

@inproceedings{bb198702,
        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#TT193903"}

@inproceedings{bb198703,
        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#TT193904"}

@inproceedings{bb198704,
        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#TT193905"}

@inproceedings{bb198705,
        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#TT193906"}

@inproceedings{bb198706,
        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#TT193907"}

@inproceedings{bb198707,
        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#TT193908"}

@inproceedings{bb198708,
        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#TT193909"}

@inproceedings{bb198709,
        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#TT193910"}

@inproceedings{bb198710,
        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#TT193911"}

@inproceedings{bb198711,
        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#TT193912"}

@inproceedings{bb198712,
        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#TT193913"}

@inproceedings{bb198713,
        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#TT193914"}

@inproceedings{bb198714,
        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#TT193915"}

@inproceedings{bb198715,
        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#TT193916"}

@inproceedings{bb198716,
        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#TT193917"}

@inproceedings{bb198717,
        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#TT193918"}

@inproceedings{bb198718,
        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#TT193919"}

@inproceedings{bb198719,
        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#TT193920"}

@inproceedings{bb198720,
        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#TT193921"}

@inproceedings{bb198721,
        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#TT193922"}

@inproceedings{bb198722,
        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#TT193923"}

@inproceedings{bb198723,
        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#TT193924"}

@inproceedings{bb198724,
        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#TT193925"}

@inproceedings{bb198725,
        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#TT193926"}

@inproceedings{bb198726,
        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#TT193927"}

@inproceedings{bb198727,
        AUTHOR = "Su, Z. and Zhu, C. and Dong, Y.P. and Cai, D.Q. and Chen, Y.R. and Li, J.G.",
        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#TT193928"}

@inproceedings{bb198728,
        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#TT193929"}

@inproceedings{bb198729,
        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#TT193930"}

@inproceedings{bb198730,
        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#TT193931"}

@inproceedings{bb198731,
        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#TT193932"}

@inproceedings{bb198732,
        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#TT193933"}

@inproceedings{bb198733,
        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#TT193934"}

@inproceedings{bb198734,
        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#TT193935"}

@inproceedings{bb198735,
        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#TT193936"}

@inproceedings{bb198736,
        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#TT193937"}

@inproceedings{bb198737,
        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#TT193938"}

@inproceedings{bb198738,
        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#TT193939"}

@inproceedings{bb198739,
        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#TT193940"}

@inproceedings{bb198740,
        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#TT193941"}

@inproceedings{bb198741,
        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#TT193942"}

@inproceedings{bb198742,
        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#TT193943"}

@inproceedings{bb198743,
        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#TT193944"}

@inproceedings{bb198744,
        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#TT193945"}

@inproceedings{bb198745,
        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#TT193946"}

@inproceedings{bb198746,
        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#TT193947"}

@inproceedings{bb198747,
        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#TT193948"}

@inproceedings{bb198748,
        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#TT193949"}

@inproceedings{bb198749,
        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#TT193950"}

@inproceedings{bb198750,
        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#TT193951"}

@inproceedings{bb198751,
        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#TT193952"}

@inproceedings{bb198752,
        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#TT193953"}

@inproceedings{bb198753,
        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#TT193954"}

@inproceedings{bb198754,
        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#TT193955"}

@inproceedings{bb198755,
        AUTHOR = "Peris, A. and Casacuberta, F.",
        TITLE = "Interactive-Predictive Neural Multimodal Systems",
        BOOKTITLE = "IbPRIA",
        PAGES = "I:16-28",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193956"}

@inproceedings{bb198756,
        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#TT193957"}

@inproceedings{bb198757,
        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#TT193958"}

@inproceedings{bb198758,
        AUTHOR = "Uehara, K. and Duan, N. and Harada, T.",
        TITLE = "Learning to Ask Informative Sub-Questions for Visual Question
Answering",
        BOOKTITLE = MULA22,
        YEAR = "2022",
        PAGES = "4680-4689",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193959"}

@inproceedings{bb198759,
        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#TT193960"}

@inproceedings{bb198760,
        AUTHOR = "Gao, P. and Jiang, Z.K. and You, H.X. and Lu, P. and Hoi, S.C.H. and Wang, X.G. and Li, H.S.",
        TITLE = "Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual
Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6632-6641",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193961"}

@inproceedings{bb198761,
        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#TT193962"}

@inproceedings{bb198762,
        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#TT193963"}

@inproceedings{bb198763,
        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#TT193964"}

@inproceedings{bb198764,
        AUTHOR = "Wang, P. and Wu, Q. and Shen, C. and van den Hengel, A.J.",
        TITLE = "The VQA-Machine: Learning How to Use Existing Vision Algorithms to
Answer New Questions",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3909-3918",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193965"}

@inproceedings{bb198765,
        AUTHOR = "Yu, D. and Fu, J. and Mei, T. and Rui, Y.",
        TITLE = "Multi-level Attention Networks for Visual Question Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "4187-4195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193966"}

@inproceedings{bb198766,
        AUTHOR = "Kembhavi, A. and Seo, M. and Schwenk, D. and Choi, J. and Farhadi, A. and Hajishirzi, H.",
        TITLE = "Are You Smarter Than a Sixth Grader? Textbook Question Answering for
Multimodal Machine Comprehension",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "5376-5384",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193967"}

@inproceedings{bb198767,
        AUTHOR = "Ganju, S. and Russakovsky, O. and Gupta, A.",
        TITLE = "What's in a Question:
Using Visual Questions as a Form of Supervision",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6422-6431",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193968"}

@inproceedings{bb198768,
        AUTHOR = "Ramakrishnan, S.K. and Pal, A. and Sharma, G. and Mittal, A.",
        TITLE = "An Empirical Evaluation of Visual Question Answering for Novel
Objects",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "7312-7321",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193969"}

@inproceedings{bb198769,
        AUTHOR = "Xu, H.J. and Saenko, K.",
        TITLE = "Ask, Attend and Answer:
Exploring Question-Guided Spatial Attention for Visual Question Answering",
        BOOKTITLE = ECCV16,
        YEAR = "2016",
        PAGES = "VII: 451-466",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193970"}

@inproceedings{bb198770,
        AUTHOR = "Jabri, A. and Joulin, A. and van der Maaten, L.",
        TITLE = "Revisiting Visual Question Answering Baselines",
        BOOKTITLE = ECCV16,
        YEAR = "2016",
        PAGES = "VIII: 727-739",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193971"}

@inproceedings{bb198771,
        AUTHOR = "Yang, Z.C. and He, X.D. and Gao, J.F. and Deng, L. and Smola, A.",
        TITLE = "Stacked Attention Networks for Image Question Answering",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "21-29",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193972"}

@inproceedings{bb198772,
        AUTHOR = "Sadeghi, F. and Divvala, S.K. and Farhadi, A.",
        TITLE = "VisKE: Visual knowledge extraction and question answering by visual
verification of relation phrases",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "1456-1464",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193973"}

@inproceedings{bb198773,
        AUTHOR = "Liu, Y. and Liu, J. and Wang, D. and Cheng, J.",
        TITLE = "A robust multivariate reranking algorithm for Question Answering
enrichment",
        BOOKTITLE = ICIP12,
        YEAR = "2012",
        PAGES = "1917-1920",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193974"}

@inproceedings{bb198774,
        AUTHOR = "Varekamp, C. and van de Walle, P. and de Putter, M.",
        TITLE = "Question interface for 3D picture creation on an autostereoscopic
digital picture frame",
        BOOKTITLE = "3DTV09",
        YEAR = "2009",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT193975"}

@article{bb198775,
        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/applicat803vidq2.html#TT193976"}

@inproceedings{bb198776,
        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/applicat803vidq2.html#TT193977"}

@article{bb198777,
        AUTHOR = "Li, G.D. and Li, H.J. and Ming, Z.Y. and Hong, R.C. 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/applicat803vidq2.html#TT193978"}

@inproceedings{bb198778,
        AUTHOR = "Song, Y.C. and Li, H.J.",
        TITLE = "Mash-Up Approach for Web Video Category Recommendation",
        BOOKTITLE = PSIVT10,
        YEAR = "2010",
        PAGES = "197-202",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193979"}

@article{bb198779,
        AUTHOR = "Guo, Z.Y. and Zhao, Z. and Jin, W. and Wei, Z.C. and Yang, M. and Wang, N.N. and Yuan, N.J.",
        TITLE = "Multi-Turn Video Question Generation via Reinforced Multi-Choice
Attention Network",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "5",
        PAGES = "1697-1710",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193980"}

@article{bb198780,
        AUTHOR = "Xue, H.Y. and Chu, W. and Zhao, Z. and Cai, D.",
        TITLE = "A Better Way to Attend: Attention With Trees for Video Question
Answering",
        JOURNAL = IP,
        VOLUME = "27",
        YEAR = "2018",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "5563-5574",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193981"}

@article{bb198781,
        AUTHOR = "Xue, H.Y. and Zhao, Z. and Cai, D.",
        TITLE = "Unifying the Video and Question Attentions for Open-Ended Video
Question Answering",
        JOURNAL = IP,
        VOLUME = "26",
        YEAR = "2017",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "5656-5666",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193982"}

@article{bb198782,
        AUTHOR = "Zhao, Z. and Xiao, S.W. and Song, Z. and Lu, C.J. and Xiao, J. and Zhuang, Y.T.",
        TITLE = "Open-Ended Video Question Answering via Multi-Modal Conditional
Adversarial Networks",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "3859-3870",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193983"}

@article{bb198783,
        AUTHOR = "Zhao, Z. and Zhang, Z. and Xiao, S.W. and Xiao, Z.X. and Yan, X.H. and Yu, J. and Cai, D. and Wu, F.",
        TITLE = "Long-Form Video Question Answering via Dynamic Hierarchical
Reinforced Networks",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "5939-5952",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193984"}

@article{bb198784,
        AUTHOR = "Yu, T. and Yu, J. and Yu, Z. and Huang, Q.M. and Tian, Q.",
        TITLE = "Long-Term Video Question Answering via Multimodal Hierarchical Memory
Attentive Networks",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "931-944",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193985"}

@article{bb198785,
        AUTHOR = "Jang, Y. and Song, Y. and Kim, C.D. and Yu, Y. and Kim, Y. and Kim, G.",
        TITLE = "Video Question Answering with Spatio-Temporal Reasoning",
        JOURNAL = IJCV,
        VOLUME = "127",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "1385-1412",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193986"}

@inproceedings{bb198786,
        AUTHOR = "Jang, Y. and Song, Y. and Yu, Y. and Kim, Y. and Kim, G.",
        TITLE = "TGIF-QA:
Toward Spatio-Temporal Reasoning in Visual Question Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1359-1367",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193987"}

@article{bb198787,
        AUTHOR = "Yu, T. and Yu, J. and Yu, Z. and Tao, D.",
        TITLE = "Compositional Attention Networks With Two-Stream Fusion for Video
Question Answering",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        NUMBER = "",
        PAGES = "1204-1218",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193988"}

@article{bb198788,
        AUTHOR = "Wang, W.N. and Huang, Y. and Wang, L.",
        TITLE = "Long video question answering: A Matching-guided Attention Model",
        JOURNAL = PR,
        VOLUME = "102",
        YEAR = "2020",
        PAGES = "107248",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193989"}

@article{bb198789,
        AUTHOR = "Zhang, W. and Tang, S. and Cao, Y. and Pu, S. and Wu, F. and Zhuang, Y.",
        TITLE = "Frame Augmented Alternating Attention Network for Video Question
Answering",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1032-1041",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193990"}

@article{bb198790,
        AUTHOR = "Chen, J. and Shao, J. and He, C.",
        TITLE = "Movie fill in the blank by joint learning from video and text with
adaptive temporal attention",
        JOURNAL = PRL,
        VOLUME = "132",
        YEAR = "2020",
        PAGES = "62-68",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193991"}

@article{bb198791,
        AUTHOR = "Wang, A. and Luu, A.T. and Foo, C. and Zhu, H. and Tay, Y. and Chandrasekhar, V.",
        TITLE = "Holistic Multi-Modal Memory Network for Movie Question Answering",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        NUMBER = "1",
        PAGES = "489-499",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193992"}

@article{bb198792,
        AUTHOR = "Yuan, Z.Q. and Sun, S.Y. and Duan, L.X. and Li, C.S. and Wu, X. and Xu, C.S.",
        TITLE = "Adversarial Multimodal Network for Movie Story Question Answering",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "1744-1756",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193993"}

@article{bb198793,
        AUTHOR = "Gu, M. and Zhao, Z. and Jin, W. and Hong, R. and Wu, F.",
        TITLE = "Graph-Based Multi-Interaction Network for Video Question Answering",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "2758-2770",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193994"}

@article{bb198794,
        AUTHOR = "Xie, Z. and Wu, K.W. and Zhang, X.Y. and Yang, X.M. and Hou, J.K.",
        TITLE = "Learning continuous temporal embedding of videos using pattern theory",
        JOURNAL = PRL,
        VOLUME = "146",
        YEAR = "2021",
        PAGES = "222-229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193995"}

@article{bb198795,
        AUTHOR = "Liu, Y. and Zhang, X.M. and Zhang, Q.Y. and Li, C.Z. and Huang, F. and Tang, X.H. and Li, Z.J.",
        TITLE = "Dual self-attention with co-attention networks for visual question
answering",
        JOURNAL = PR,
        VOLUME = "117",
        YEAR = "2021",
        PAGES = "107956",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193996"}

@article{bb198796,
        AUTHOR = "Liu, Y. and Zhang, X.M. and Huang, F. and Shen, S.X. and Tian, P. and Li, L. and Li, Z.J.",
        TITLE = "Dynamic Self-Attention with Vision Synchronization Networks for Video
Question Answering",
        JOURNAL = PR,
        VOLUME = "132",
        YEAR = "2022",
        PAGES = "108959",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193997"}

@article{bb198797,
        AUTHOR = "Liu, Y. and Zhang, X.M. and Huang, F. and Zhang, B. and Li, Z.J.",
        TITLE = "Cross-Attentional Spatio-Temporal Semantic Graph Networks for Video
Question Answering",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "1684-1696",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193998"}

@article{bb198798,
        AUTHOR = "Jin, W. and Zhao, Z. and Cao, X.C. and Zhu, J.M. and He, X.Q. and Zhuang, Y.T.",
        TITLE = "Adaptive Spatio-Temporal Graph Enhanced Vision-Language
Representation for Video QA",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "5477-5489",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT193999"}

@article{bb198799,
        AUTHOR = "Gao, L. and Chen, T.M. and Li, X.P. and Zeng, P.P. and Zhao, L. and Li, Y.F.",
        TITLE = "Generalized pyramid co-attention with learnable aggregation net for
video question answering",
        JOURNAL = PR,
        VOLUME = "120",
        YEAR = "2021",
        PAGES = "108145",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT194000"}