@inproceedings{bb212900, AUTHOR = "Yu, Z. and Yu, J. and Cui, Y.H. 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#TT207976"} @inproceedings{bb212901, 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#TT207977"} @inproceedings{bb212902, 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#TT207978"} @inproceedings{bb212903, 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#TT207979"} @inproceedings{bb212904, 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#TT207980"} @inproceedings{bb212905, 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#TT207981"} @inproceedings{bb212906, 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#TT207982"} @inproceedings{bb212907, 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#TT207983"} @inproceedings{bb212908, 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#TT207984"} @inproceedings{bb212909, 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#TT207985"} @inproceedings{bb212910, 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#TT207986"} @inproceedings{bb212911, 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#TT207987"} @inproceedings{bb212912, 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#TT207988"} @inproceedings{bb212913, 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#TT207989"} @inproceedings{bb212914, 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#TT207990"} @inproceedings{bb212915, 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#TT207991"} @inproceedings{bb212916, 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#TT207992"} @inproceedings{bb212917, 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#TT207993"} @inproceedings{bb212918, 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#TT207994"} @inproceedings{bb212919, 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#TT207995"} @inproceedings{bb212920, 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#TT207996"} @inproceedings{bb212921, 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#TT207997"} @inproceedings{bb212922, 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#TT207998"} @inproceedings{bb212923, 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#TT207999"} @inproceedings{bb212924, 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#TT208000"} @inproceedings{bb212925, 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#TT208001"} @inproceedings{bb212926, 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#TT208002"} @inproceedings{bb212927, 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#TT208003"} @inproceedings{bb212928, 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#TT208004"} @inproceedings{bb212929, 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#TT208005"} @inproceedings{bb212930, 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#TT208006"} @inproceedings{bb212931, 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#TT208007"} @inproceedings{bb212932, 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#TT208008"} @inproceedings{bb212933, 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#TT208009"} @inproceedings{bb212934, 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#TT208010"} @inproceedings{bb212935, 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#TT208011"} @inproceedings{bb212936, 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#TT208012"} @inproceedings{bb212937, 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#TT208013"} @inproceedings{bb212938, 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#TT208014"} @inproceedings{bb212939, 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#TT208015"} @inproceedings{bb212940, 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#TT208016"} @inproceedings{bb212941, 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#TT208017"} @inproceedings{bb212942, 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#TT208018"} @inproceedings{bb212943, 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#TT208019"} @inproceedings{bb212944, 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#TT208020"} @inproceedings{bb212945, 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#TT208021"} @inproceedings{bb212946, 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#TT208022"} @inproceedings{bb212947, 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#TT208023"} @inproceedings{bb212948, 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#TT208024"} @inproceedings{bb212949, 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#TT208025"} @inproceedings{bb212950, 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#TT208026"} @inproceedings{bb212951, 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#TT208027"} @inproceedings{bb212952, 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#TT208028"} @inproceedings{bb212953, 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#TT208029"} @inproceedings{bb212954, 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#TT208030"} @inproceedings{bb212955, 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#TT208031"} @inproceedings{bb212956, 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#TT208032"} @inproceedings{bb212957, 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#TT208033"} @inproceedings{bb212958, 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#TT208034"} @inproceedings{bb212959, 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#TT208035"} @inproceedings{bb212960, 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#TT208036"} @article{bb212961, AUTHOR = "Das, A. and Agrawal, H. and Zitnick, L. and Parikh, D. and Batra, D.", TITLE = "Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?", JOURNAL = CVIU, VOLUME = "163", YEAR = "2017", NUMBER = "1", PAGES = "90-100", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208037"} @article{bb212962, AUTHOR = "Malinowski, M. and Rohrbach, M. and Fritz, M.", TITLE = "Ask Your Neurons: A Deep Learning Approach to Visual Question Answering", JOURNAL = IJCV, VOLUME = "125", YEAR = "2018", NUMBER = "1-3", MONTH = "December", PAGES = "110-135", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208038"} @inproceedings{bb212963, AUTHOR = "Malinowski, M. and Rohrbach, M. and Fritz, M.", TITLE = "Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images", BOOKTITLE = ICCV15, YEAR = "2015", PAGES = "1-9", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208039"} @inproceedings{bb212964, AUTHOR = "Dancette, C. and Whitehead, S. and Maheshwary, R. and Vedantam, R. and Scherer, S. and Chen, X.L. and Cord, M. and Rohrbach, M.", TITLE = "Improving Selective Visual Question Answering by Learning from Your Peers", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "24049-24059", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208040"} @article{bb212965, AUTHOR = "Huang, Y.Z. and Zhong, T.", TITLE = "Multitask learning for neural generative question answering", JOURNAL = RealTimeIP, VOLUME = "14", YEAR = "2018", NUMBER = "1", MONTH = "January", PAGES = "1009-1017", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208041"} @article{bb212966, AUTHOR = "Ruwa, N. and Mao, Q. and Song, H.P. and Jia, H.J. and Dong, M.", TITLE = "Triple attention network for sentimental visual question answering", JOURNAL = CVIU, VOLUME = "189", YEAR = "2019", PAGES = "102829", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208042"} @article{bb212967, AUTHOR = "Bai, Z.W. and Li, Y. and Wozniak, M. and Zhou, M.L. and Li, D.", TITLE = "DecomVQANet: Decomposing visual question answering deep network via tensor decomposition and regression", JOURNAL = PR, VOLUME = "110", YEAR = "2021", PAGES = "107538", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208043"} @article{bb212968, AUTHOR = "Zhang, Q.S. and Wu, Y.N. and Zhang, H. and Zhu, S.C.", TITLE = "Mining deep And-Or object structures via cost-sensitive question-answer-based active annotations", JOURNAL = CVIU, VOLUME = "176-177", YEAR = "2018", PAGES = "33-44", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208044"} @article{bb212969, AUTHOR = "Zhang, Q.S. and Ren, J. and Huang, G. and Cao, R.M. and Wu, Y.N. and Zhu, S.C.", TITLE = "Mining Interpretable AOG Representations From Convolutional Networks via Active Question Answering", JOURNAL = PAMI, VOLUME = "43", YEAR = "2021", NUMBER = "11", MONTH = "November", PAGES = "3949-3963", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208045"} @inproceedings{bb212970, AUTHOR = "Zhang, Q.S. and Cao, R.M. and Wu, Y.N. and Zhu, S.C.", TITLE = "Mining Object Parts from CNNs via Active Question-Answering", BOOKTITLE = CVPR17, YEAR = "2017", PAGES = "3890-3899", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208046"} @inproceedings{bb212971, AUTHOR = "Zhang, Q.S. and Wu, Y.N. and Zhu, S.C.", TITLE = "Mining And-Or Graphs for Graph Matching and Object Discovery", BOOKTITLE = ICCV15, YEAR = "2015", PAGES = "55-63", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208047"} @article{bb212972, AUTHOR = "Cao, Q.X. and Liang, X.D. and Li, B.L. and Lin, L.", TITLE = "Interpretable Visual Question Answering by Reasoning on Dependency Trees", JOURNAL = PAMI, VOLUME = "43", YEAR = "2021", NUMBER = "3", MONTH = "March", PAGES = "887-901", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208048"} @inproceedings{bb212973, AUTHOR = "Cao, Q.X. and Liang, X.D. and Li, B.L. 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/applicat803vqann4.html#TT208049"} @article{bb212974, AUTHOR = "Zhong, H.S. and Chen, J.Y. and Shen, C. and Zhang, H.W. and Huang, J.Q. and Hua, X.S.", TITLE = "Self-Adaptive Neural Module Transformer for Visual Question Answering", JOURNAL = MultMed, VOLUME = "23", YEAR = "2021", PAGES = "1264-1273", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208050"} @article{bb212975, AUTHOR = "Zheng, W.F. and Yin, L.R. and Chen, X.B. and Ma, Z. and Liu, S. and Yang, B.", TITLE = "Knowledge base graph embedding module design for Visual question answering model", JOURNAL = PR, VOLUME = "120", YEAR = "2021", PAGES = "108153", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208051"} @article{bb212976, AUTHOR = "Sharma, H. and Jalal, A.S.", TITLE = "Visual question answering model based on graph neural network and contextual attention", JOURNAL = IVC, VOLUME = "110", YEAR = "2021", PAGES = "104165", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208052"} @article{bb212977, AUTHOR = "Song, L.Y. and Li, J. and Liu, J. and Yang, Y. and Shang, X. and Sun, M.X.", TITLE = "Answering knowledge-based visual questions via the exploration of Question Purpose", JOURNAL = PR, VOLUME = "133", YEAR = "2023", PAGES = "109015", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208053"} @article{bb212978, AUTHOR = "MeshuWelde, T. and Liao, L.", TITLE = "Counting-based visual question answering with serial cascaded attention deep learning", JOURNAL = PR, VOLUME = "144", YEAR = "2023", PAGES = "109850", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208054"} @article{bb212979, AUTHOR = "Liu, Y. and Li, G.B. and Lin, L.", TITLE = "Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "10", MONTH = "October", PAGES = "11624-11641", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208055"} @inproceedings{bb212980, AUTHOR = "Cao, Q.X. and Wan, W.T. and Wang, K. and Liang, X.D. and Lin, L.", TITLE = "Linguistically Routing Capsule Network for Out-of-distribution Visual Question Answering", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "1594-1603", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208056"} @article{bb212981, AUTHOR = "Yang, S.W. and Xiao, L. and Wu, X.J. and Xu, J.J. and Wang, L.L. and He, L.", TITLE = "Simple contrastive learning in a self-supervised manner for robust visual question answering", JOURNAL = CVIU, VOLUME = "241", YEAR = "2024", PAGES = "103976", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208057"} @inproceedings{bb212982, AUTHOR = "Wang, Y. and Yasunaga, M. and Ren, H.Y. and Wada, S. and Leskovec, J.", TITLE = "VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "21525-21535", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208058"} @inproceedings{bb212983, AUTHOR = "Souza, B. and Aasan, M. and Pedrini, H. and Rivera, A.R.", TITLE = "SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering", BOOKTITLE = VLAR23, YEAR = "2023", PAGES = "4642-4647", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208059"} @inproceedings{bb212984, AUTHOR = "Haisa, G. and Altenbek, G.", TITLE = "Question Classification Based on Weak Supervision and Interrogative Pronouns Attention Mechanism", BOOKTITLE = "ICPR22", YEAR = "2022", PAGES = "2273-2278", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208060"} @inproceedings{bb212985, AUTHOR = "Nguyen, B.X. and Do, T. and Tran, H. and Tjiputra, E. and Tran, Q.D. and Nguyen, A.", TITLE = "Coarse-to-Fine Reasoning for Visual Question Answering", BOOKTITLE = MULA22, YEAR = "2022", PAGES = "4557-4565", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208061"} @inproceedings{bb212986, AUTHOR = "Liang, Y.Y. and Wang, X. and Duan, X.G. and Zhu, W.W.", TITLE = "Multi-modal Contextual Graph Neural Network for Text Visual Question Answering", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "3491-3498", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208062"} @inproceedings{bb212987, AUTHOR = "Patro, B.N. and Kurmi, V.K. and Kumar, S. and Namboodiri, V.P.", TITLE = "Deep Bayesian Network for Visual Question Generation", BOOKTITLE = WACV20, YEAR = "2020", PAGES = "1555-1565", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208063"} @inproceedings{bb212988, AUTHOR = "Singh, A.K. and Mishra, A. and Shekhar, S. and Chakraborty, A.", TITLE = "From Strings to Things: Knowledge-Enabled VQA Model That Can Read and Reason", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "4601-4611", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208064"} @inproceedings{bb212989, AUTHOR = "Wilf, A. and Ma, M.Q. and Liang, P.P. and Zadeh, A. and Morency, L.P.", TITLE = "Face-to-Face Contrastive Learning for Social Intelligence Question-Answering", BOOKTITLE = FG23, YEAR = "2023", PAGES = "1-7", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208065"} @inproceedings{bb212990, 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/applicat803vqann4.html#TT208066"} @inproceedings{bb212991, 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/applicat803vqann4.html#TT208067"} @inproceedings{bb212992, 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/applicat803vqann4.html#TT208068"} @inproceedings{bb212993, 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/applicat803vqann4.html#TT208069"} @inproceedings{bb212994, 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/applicat803vqann4.html#TT208070"} @inproceedings{bb212995, 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/applicat803vqann4.html#TT208071"} @inproceedings{bb212996, 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/applicat803vqann4.html#TT208072"} @inproceedings{bb212997, 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/applicat803vqann4.html#TT208073"} @inproceedings{bb212998, 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/applicat803vqann4.html#TT208074"} @inproceedings{bb212999, AUTHOR = "Peris, A. and Casacuberta, F.", TITLE = "Interactive-Predictive Neural Multimodal Systems", BOOKTITLE = IbPRIA19, YEAR = "2019", PAGES = "I:16-28", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqann4.html#TT208075"}