@inproceedings{bb163800,
        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#TT159256"}

@inproceedings{bb163801,
        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#TT159257"}

@inproceedings{bb163802,
        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#TT159258"}

@inproceedings{bb163803,
        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#TT159259"}

@inproceedings{bb163804,
        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#TT159260"}

@inproceedings{bb163805,
        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#TT159261"}

@inproceedings{bb163806,
        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#TT159262"}

@inproceedings{bb163807,
        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#TT159263"}

@inproceedings{bb163808,
        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#TT159264"}

@inproceedings{bb163809,
        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#TT159265"}

@inproceedings{bb163810,
        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#TT159266"}

@inproceedings{bb163811,
        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#TT159267"}

@inproceedings{bb163812,
        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#TT159268"}

@inproceedings{bb163813,
        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#TT159269"}

@inproceedings{bb163814,
        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#TT159270"}

@inproceedings{bb163815,
        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#TT159271"}

@inproceedings{bb163816,
        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#TT159272"}

@inproceedings{bb163817,
        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#TT159273"}

@inproceedings{bb163818,
        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#TT159274"}

@inproceedings{bb163819,
        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#TT159275"}

@inproceedings{bb163820,
        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#TT159276"}

@inproceedings{bb163821,
        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#TT159277"}

@inproceedings{bb163822,
        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#TT159278"}

@inproceedings{bb163823,
        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#TT159279"}

@inproceedings{bb163824,
        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#TT159280"}

@inproceedings{bb163825,
        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#TT159281"}

@inproceedings{bb163826,
        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#TT159282"}

@inproceedings{bb163827,
        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#TT159283"}

@inproceedings{bb163828,
        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#TT159284"}

@inproceedings{bb163829,
        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#TT159285"}

@inproceedings{bb163830,
        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#TT159286"}

@inproceedings{bb163831,
        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#TT159287"}

@inproceedings{bb163832,
        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#TT159288"}

@inproceedings{bb163833,
        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#TT159289"}

@inproceedings{bb163834,
        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#TT159290"}

@inproceedings{bb163835,
        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#TT159291"}

@inproceedings{bb163836,
        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#TT159292"}

@inproceedings{bb163837,
        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#TT159293"}

@inproceedings{bb163838,
        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#TT159294"}

@inproceedings{bb163839,
        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#TT159295"}

@inproceedings{bb163840,
        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#TT159296"}

@inproceedings{bb163841,
        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#TT159297"}

@inproceedings{bb163842,
        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#TT159298"}

@inproceedings{bb163843,
        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#TT159299"}

@inproceedings{bb163844,
        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#TT159300"}

@inproceedings{bb163845,
        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#TT159301"}

@inproceedings{bb163846,
        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#TT159302"}

@inproceedings{bb163847,
        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#TT159303"}

@inproceedings{bb163848,
        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#TT159304"}

@inproceedings{bb163849,
        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#TT159305"}

@inproceedings{bb163850,
        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#TT159306"}

@inproceedings{bb163851,
        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#TT159307"}

@inproceedings{bb163852,
        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#TT159308"}

@inproceedings{bb163853,
        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#TT159309"}

@inproceedings{bb163854,
        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#TT159310"}

@inproceedings{bb163855,
        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#TT159311"}

@inproceedings{bb163856,
        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#TT159312"}

@inproceedings{bb163857,
        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#TT159313"}

@inproceedings{bb163858,
        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#TT159314"}

@inproceedings{bb163859,
        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#TT159315"}

@inproceedings{bb163860,
        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#TT159316"}

@inproceedings{bb163861,
        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#TT159317"}

@inproceedings{bb163862,
        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#TT159318"}

@inproceedings{bb163863,
        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#TT159319"}

@inproceedings{bb163864,
        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#TT159320"}

@inproceedings{bb163865,
        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#TT159321"}

@inproceedings{bb163866,
        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#TT159322"}

@inproceedings{bb163867,
        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#TT159323"}

@inproceedings{bb163868,
        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#TT159324"}

@inproceedings{bb163869,
        AUTHOR = "Maharaj, T. and Ballas, N. and Rohrbach, A. and Courville, A. and Pal, C.",
        TITLE = "A Dataset and Exploration of Models for Understanding Video Data
through Fill-in-the-Blank Question-Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "7359-7368",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT159325"}

@inproceedings{bb163870,
        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#TT159326"}

@inproceedings{bb163871,
        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#TT159327"}

@inproceedings{bb163872,
        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#TT159328"}

@inproceedings{bb163873,
        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#TT159329"}

@inproceedings{bb163874,
        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#TT159330"}

@inproceedings{bb163875,
        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#TT159331"}

@article{bb163876,
        AUTHOR = "Su, H.H. and Chen, T.W. and Kao, C.C. and Hsu, W.H. and Chien, S.Y.",
        TITLE = "Preference-Aware View Recommendation System for Scenic Photos Based on
Bag-of-Aesthetics-Preserving Features",
        JOURNAL = MultMed,
        VOLUME = "14",
        YEAR = "2012",
        NUMBER = "3",
        PAGES = "833-843",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159332"}

@article{bb163877,
        AUTHOR = "Chen, L. and Xu, D. and Tsang, I.W. and Luo, J.",
        TITLE = "Tag-Based Image Retrieval Improved by Augmented Features and
Group-Based Refinement",
        JOURNAL = MultMed,
        VOLUME = "14",
        YEAR = "2012",
        NUMBER = "4",
        PAGES = "1057-1067",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159333"}

@article{bb163878,
        AUTHOR = "Chen, L. and Xu, D. and Tsang, I.W. and Li, X.",
        TITLE = "Spectral Embedded Hashing for Scalable Image Retrieval",
        JOURNAL = Cyber,
        VOLUME = "44",
        YEAR = "2014",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1180-1190",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159334"}

@article{bb163879,
        AUTHOR = "Jiao, B. and Yang, L. and Xu, J. and Tian, Q. and Wu, F.",
        TITLE = "Visually Summarizing Web Pages Through Internal and External Images",
        JOURNAL = MultMed,
        VOLUME = "14",
        YEAR = "2012",
        NUMBER = "6",
        PAGES = "1673-1683",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159335"}

@article{bb163880,
        AUTHOR = "Sawant, N. and Wang, J.Z. and Li, J.",
        TITLE = "Enhancing Training Collections for Image Annotation:
An Instance-Weighted Mixture Modeling Approach",
        JOURNAL = IP,
        VOLUME = "22",
        YEAR = "2013",
        NUMBER = "9",
        PAGES = "3562-3577",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159336"}

@article{bb163881,
        AUTHOR = "Zhou, N. and Fan, J.P.",
        TITLE = "Automatic image-text alignment for large-scale web image indexing and
retrieval",
        JOURNAL = PR,
        VOLUME = "48",
        YEAR = "2015",
        NUMBER = "1",
        PAGES = "205-219",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159337"}

@article{bb163882,
        AUTHOR = "Tian, J. and Huang, Y. and Guo, Z. and Qi, X. and Chen, Z. and Huang, T.",
        TITLE = "A Multi-Modal Topic Model for Image Annotation Using Text Analysis",
        JOURNAL = SPLetters,
        VOLUME = "22",
        YEAR = "2015",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "886-890",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159338"}

@article{bb163883,
        AUTHOR = "Rodriguez Vaamonde, S. and Torresani, L. and Fitzgibbon, A.W.",
        TITLE = "What Can Pictures Tell Us About Web Pages? Improving Document Search
Using Images",
        JOURNAL = PAMI,
        VOLUME = "37",
        YEAR = "2015",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "1274-1285",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159339"}

@article{bb163884,
        AUTHOR = "Tirkaz, C. and Eisenstein, J. and Sezgin, T.M. and Yanikoglu, B.A.",
        TITLE = "Identifying visual attributes for object recognition from text and
taxonomy",
        JOURNAL = CVIU,
        VOLUME = "137",
        YEAR = "2015",
        NUMBER = "1",
        PAGES = "12-23",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159340"}

@article{bb163885,
        AUTHOR = "Lu, Y.J. and Yang, L. and Yang, K. and Rui, Y.",
        TITLE = "Mining Latent Attributes From Click-Through Logs for Image
Recognition",
        JOURNAL = MultMed,
        VOLUME = "17",
        YEAR = "2015",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1213-1224",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159341"}

@article{bb163886,
        AUTHOR = "Fu, J. and Wang, J. and Rui, Y. and Wang, X. and Mei, T. and Lu, H.",
        TITLE = "Image Tag Refinement With View-Dependent Concept Representations",
        JOURNAL = CirSysVideo,
        VOLUME = "25",
        YEAR = "2015",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1409-1422",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159342"}

@article{bb163887,
        AUTHOR = "Belongie, S. and Perona, P.",
        TITLE = "Visipedia circa 2015",
        JOURNAL = PRL,
        VOLUME = "72",
        YEAR = "2016",
        NUMBER = "1",
        PAGES = "15-24",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159343"}

@article{bb163888,
        AUTHOR = "Niu, L. and Li, W. and Xu, D.",
        TITLE = "Exploiting Privileged Information from Web Data for Action and Event
Recognition",
        JOURNAL = IJCV,
        VOLUME = "118",
        YEAR = "2016",
        NUMBER = "2",
        MONTH = "June",
        PAGES = "130-150",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159344"}

@inproceedings{bb163889,
        AUTHOR = "Li, W. and Niu, L. and Xu, D.",
        TITLE = "Exploiting Privileged Information from Web Data for Image
Categorization",
        BOOKTITLE = ECCV14,
        YEAR = "2014",
        PAGES = "V: 437-452",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159345"}

@article{bb163890,
        AUTHOR = "Sejal, D. and Rashmi, V. and Venugopal, K.R. and Iyengar, S.S. and Patnaik, L.M.",
        TITLE = "Image recommendation based on keyword relevance using absorbing Markov
chain and image features",
        JOURNAL = MultInfoRetr,
        VOLUME = "5",
        YEAR = "2016",
        NUMBER = "3",
        MONTH = "September",
        PAGES = "185-199",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159346"}

@article{bb163891,
        AUTHOR = "Yan, Y. and Nie, F.P. and Li, W. and Gao, C.Q. and Yang, Y. and Xu, D.",
        TITLE = "Image Classification by Cross-Media Active Learning With Privileged
Information",
        JOURNAL = MultMed,
        VOLUME = "18",
        YEAR = "2016",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "2494-2502",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159347"}

@article{bb163892,
        AUTHOR = "Qian, X. and Li, C. and Lan, K. and Hou, X. and Li, Z. and Han, J.",
        TITLE = "POI Summarization by Aesthetics Evaluation From Crowd Source Social
Media",
        JOURNAL = IP,
        VOLUME = "27",
        YEAR = "2018",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "1178-1189",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159348"}

@article{bb163893,
        AUTHOR = "Li, Z.C. and Tang, J.H. and Mei, T.",
        TITLE = "Deep Collaborative Embedding for Social Image Understanding",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "9",
        MONTH = "Sep",
        PAGES = "2070-2083",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159349"}

@inproceedings{bb163894,
        AUTHOR = "Long, C.J. and Collins, R. and Swears, E. and Hoogs, A.",
        TITLE = "Deep Neural Networks in Fully Connected CRF for Image Labeling with
Social Network Metadata",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "1607-1615",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159350"}

@inproceedings{bb163895,
        AUTHOR = "Niu, L. and Tang, Q.T. and Veeraraghavan, A. and Sabharwal, A.",
        TITLE = "Learning from Noisy Web Data with Category-Level Supervision",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7689-7698",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159351"}

@inproceedings{bb163896,
        AUTHOR = "Guo, S. and Huang, W.L. and Zhang, H.Z. and Zhuang, C.F. and Dong, D. and Scott, M.R. and Huang, D.L.",
        TITLE = "CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "X: 139-154",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159352"}

@inproceedings{bb163897,
        AUTHOR = "Chang, X.O. and Xiang, T. and Hospedales, T.M.",
        TITLE = "L_1 Graph Based Sparse Model for Label De-noising",
        BOOKTITLE = BMVC16,
        YEAR = "2016",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159353"}

@inproceedings{bb163898,
        AUTHOR = "Vadicamo, L. and Carrara, F. and Cimino, A. and Cresci, S. and Dell'Orletta, F. and Falchi, F. and Tesconi, M.",
        TITLE = "Cross-Media Learning for Image Sentiment Analysis in the Wild",
        BOOKTITLE = WSM17,
        YEAR = "2017",
        PAGES = "308-317",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159354"}

@inproceedings{bb163899,
        AUTHOR = "Fernandez, D. and Varas, D. and Espadaler, J. and Masuda, I. and Ferreira, J. and Woodward, A. and Rodriguez, D. and Giro i Nieto, X. and Riveiro, J.C. and Bou, E.",
        TITLE = "ViTS: Video Tagging System from Massive Web Multimedia Collections",
        BOOKTITLE = WSM17,
        YEAR = "2017",
        PAGES = "337-346",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT159355"}

Last update:Aug 4, 2020 at 13:31:31