@inproceedings{bb210600,
        AUTHOR = "Shao, Z.W. and Yu, Z. and Wang, M. and Yu, J.",
        TITLE = "Prompting Large Language Models with Answer Heuristics for
Knowledge-Based Visual Question Answering",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "14974-14983",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205686"}

@inproceedings{bb210601,
        AUTHOR = "Tascon Morales, S. and Marquez Neila, P. and Sznitman, R.",
        TITLE = "Logical Implications for Visual Question Answering Consistency",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "6725-6735",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205687"}

@inproceedings{bb210602,
        AUTHOR = "Chen, S. and Zhao, Q.",
        TITLE = "Divide and Conquer: Answering Questions with Object Factorization and
Compositional Reasoning",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "6736-6745",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205688"}

@inproceedings{bb210603,
        AUTHOR = "Guo, J.X. and Li, J. and Li, D.X. and Tiong, A.M.H. and Li, B.Y. and Tao, D.C. and Hoi, S.",
        TITLE = "From Images to Textual Prompts: Zero-shot Visual Question Answering
with Frozen Large Language Models",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "10867-10877",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205689"}

@inproceedings{bb210604,
        AUTHOR = "Basu, A. and Addepalli, S. and Babu, R.V.",
        TITLE = "RMLVQA: A Margin Loss Approach For Visual Question Answering with
Language Biases",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "11671-11680",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205690"}

@inproceedings{bb210605,
        AUTHOR = "Li, B.J. and Wang, J. and Zhao, M. and Zhou, S.",
        TITLE = "Two-stage Multimodality Fusion for High-performance Text-based Visual
Question Answering",
        BOOKTITLE = ACCV22,
        YEAR = "2022",
        PAGES = "IV:658-674",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205691"}

@inproceedings{bb210606,
        AUTHOR = "Vivoli, E. and Biten, A.F. and Mafla, A. and Karatzas, D. and Gomez, L.",
        TITLE = "MUST-VQA: Multilingual Scene-Text VQA",
        BOOKTITLE = TextEvery22,
        YEAR = "2022",
        PAGES = "345-358",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205692"}

@inproceedings{bb210607,
        AUTHOR = "Chai, Z. and Wan, X.J. and Han, S.C. and Poon, J.",
        TITLE = "Visual Question Generation Under Multi-granularity Cross-Modal
Interaction",
        BOOKTITLE = MMMod23,
        YEAR = "2023",
        PAGES = "I: 255-266",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205693"}

@inproceedings{bb210608,
        AUTHOR = "Wang, J.H. and Hu, M.H. and Song, Y.G. and Yang, X.S.",
        TITLE = "Health-Oriented Multimodal Food Question Answering",
        BOOKTITLE = MMMod23,
        YEAR = "2023",
        PAGES = "I: 191-203",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205694"}

@inproceedings{bb210609,
        AUTHOR = "Bongini, P. and Becattini, F. and del Bimbo, A.",
        TITLE = "Is GPT-3 All You Need for Visual Question Answering in Cultural
Heritage?",
        BOOKTITLE = VisArt22,
        YEAR = "2022",
        PAGES = "268-281",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205695"}

@inproceedings{bb210610,
        AUTHOR = "Jha, A. and Patro, B. and Van Gool, L.J. and Tuytelaars, T.",
        TITLE = "Barlow constrained optimization for Visual Question Answering",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "1084-1093",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205696"}

@inproceedings{bb210611,
        AUTHOR = "Ravi, S. and Chinchure, A. and Sigal, L. and Liao, R.J. and Shwartz, V.",
        TITLE = "VLC-BERT: Visual Question Answering with Contextualized Commonsense
Knowledge",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "1155-1165",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205697"}

@inproceedings{bb210612,
        AUTHOR = "Uehara, K. and Harada, T.",
        TITLE = "K-VQG: Knowledge-aware Visual Question Generation for Common-sense
Acquisition",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "4390-4398",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205698"}

@inproceedings{bb210613,
        AUTHOR = "Etesam, Y. and Kochiev, L. and Chang, A.X.",
        TITLE = "3DVQA: Visual Question Answering for 3D Environments",
        BOOKTITLE = CRV22,
        YEAR = "2022",
        PAGES = "233-240",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205699"}

@inproceedings{bb210614,
        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/applicat803vqa1.html#TT205700"}

@inproceedings{bb210615,
        AUTHOR = "Ramamurthy, P. and Aakur, S.N.",
        TITLE = "ISD-QA: Iterative Distillation of Commonsense Knowledge from General
Language Models for Unsupervised Question Answering",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "1229-1235",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205701"}

@inproceedings{bb210616,
        AUTHOR = "Zhang, H.T. and Wu, W.",
        TITLE = "CAT: Re-Conv Attention in Transformer for Visual Question Answering",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "1471-1477",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205702"}

@inproceedings{bb210617,
        AUTHOR = "Liu, L. and Su, X.D. and Guo, H. and Zhu, D.",
        TITLE = "A Transformer-based Medical Visual Question Answering Model",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "1712-1718",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205703"}

@inproceedings{bb210618,
        AUTHOR = "Wu, X.Y. and Lu, J.F. and Li, Z.F. and Xiong, F.C.",
        TITLE = "Ques-to-Visual Guided Visual Question Answering",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "4193-4197",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205704"}

@inproceedings{bb210619,
        AUTHOR = "Sarkar, A. and Rahnemoonfar, M.",
        TITLE = "Grad-Cam Aware Supervised Attention for Visual Question Answering for
Post-Disaster Damage Assessment",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "3783-3787",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205705"}

@inproceedings{bb210620,
        AUTHOR = "Whitehead, S. and Petryk, S. and Shakib, V. and Gonzalez, J. and Darrell, T.J. and Rohrbach, A. and Rohrbach, M.",
        TITLE = "Reliable Visual Question Answering: Abstain Rather Than Answer
Incorrectly",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXVI:148-166",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205706"}

@inproceedings{bb210621,
        AUTHOR = "Chen, L. and Zheng, Y.H. and Xiao, J.",
        TITLE = "Rethinking Data Augmentation for Robust Visual Question Answering",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXVI:95-112",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205707"}

@inproceedings{bb210622,
        AUTHOR = "Zhang, H.T. and Wu, W.",
        TITLE = "Context Relation Fusion Model for Visual Question Answering",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "2112-2116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205708"}

@inproceedings{bb210623,
        AUTHOR = "Biten, A.F. and Litman, R. and Xie, Y.S. and Appalaraju, S. and Manmatha, R.",
        TITLE = "LaTr: Layout-Aware Transformer for Scene-Text VQA",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "16527-16537",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205709"}

@inproceedings{bb210624,
        AUTHOR = "Lu, J.Y. and Ye, X. and Ren, Y. and Yang, Y.Z.",
        TITLE = "Good, Better, Best: Textual Distractors Generation for
Multiple-Choice Visual Question Answering via Reinforcement Learning",
        BOOKTITLE = ODRUM22,
        YEAR = "2022",
        PAGES = "4917-4926",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205710"}

@inproceedings{bb210625,
        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/applicat803vqa1.html#TT205711"}

@inproceedings{bb210626,
        AUTHOR = "Ding, Y.H. and Huang, Z. and Wang, R. and Zhang, Y.H. and Chen, X. and Ma, Y.Z. and Chung, H. and Han, S.C.",
        TITLE = "V-Doc: Visual questions answers with Documents",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "21460-21466",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205712"}

@inproceedings{bb210627,
        AUTHOR = "Azuma, D. and Miyanishi, T. and Kurita, S.H. and Kawanabe, M.",
        TITLE = "ScanQA: 3D Question Answering for Spatial Scene Understanding",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "19107-19117",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205713"}

@inproceedings{bb210628,
        AUTHOR = "Li, G.Y. and Wei, Y. and Tian, Y. and Xu, C.L. and Wen, J.R. and Hu, D.",
        TITLE = "Learning to Answer Questions in Dynamic Audio-Visual Scenarios",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "19086-19096",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205714"}

@inproceedings{bb210629,
        AUTHOR = "Chen, C. and Anjum, S. and Gurari, D.",
        TITLE = "Grounding Answers for Visual Questions Asked by Visually Impaired
People",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "19076-19085",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205715"}

@inproceedings{bb210630,
        AUTHOR = "Jing, C.C. and Jia, Y.D. and Wu, Y.W. and Liu, X.Y. and Wu, Q.",
        TITLE = "Maintaining Reasoning Consistency in Compositional Visual Question
Answering",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "5089-5098",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205716"}

@inproceedings{bb210631,
        AUTHOR = "Cascante Bonilla, P. and Wu, H. and Wang, L. and Feris, R.S. and Ordonez, V.",
        TITLE = "Sim VQA: Exploring Simulated Environments for Visual Question
Answering",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "5046-5056",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205717"}

@inproceedings{bb210632,
        AUTHOR = "Gupta, V. and Li, Z.W. and Kortylewski, A. and Zhang, C.Y. and Li, Y.W. and Yuille, A.L.",
        TITLE = "SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual
Context in Visual Question Answering",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "5068-5078",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205718"}

@inproceedings{bb210633,
        AUTHOR = "Burghouts, G.J. and Huizinga, W.",
        TITLE = "Coarse-to-Fine Visual Question Answering by Iterative, Conditional
Refinement",
        BOOKTITLE = CIAP22,
        YEAR = "2022",
        PAGES = "II:418-428",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205719"}

@inproceedings{bb210634,
        AUTHOR = "Kant, Y. and Moudgil, A. and Batra, D. and Parikh, D. and Agrawal, H.",
        TITLE = "Contrast and Classify: Training Robust VQA Models",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1584-1593",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205720"}

@inproceedings{bb210635,
        AUTHOR = "Han, X.Z. and Wang, S.H. and Su, C. and Huang, Q.M. and Tian, Q.",
        TITLE = "Greedy Gradient Ensemble for Robust Visual Question Answering",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1564-1573",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205721"}

@inproceedings{bb210636,
        AUTHOR = "Dancette, C. and Cadene, R. and Teney, D. and Cord, M.",
        TITLE = "Beyond Question-Based Biases:
Assessing Multimodal Shortcut Learning in Visual Question Answering",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1554-1563",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205722"}

@inproceedings{bb210637,
        AUTHOR = "Zhou, Y. and Ren, T. and Zhu, C.Y. and Sun, X.S. and Liu, J.Z. and Ding, X.H. and Xu, M.L. and Ji, R.R.",
        TITLE = "TRAR: Routing the Attention Spans in Transformer for Visual Question
Answering",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2054-2064",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205723"}

@inproceedings{bb210638,
        AUTHOR = "Yang, X. and Gao, C.Y. and Zhang, H.W. and Cai, J.F.",
        TITLE = "Auto-Parsing Network for Image Captioning and Visual Question
Answering",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2177-2187",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205724"}

@inproceedings{bb210639,
        AUTHOR = "Banerjee, P. and Gokhale, T. and Yang, Y.Z. and Baral, C.",
        TITLE = "Weakly Supervised Relative Spatial Reasoning for Visual Question
Answering",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1888-1898",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205725"}

@inproceedings{bb210640,
        AUTHOR = "Li, L.J. and Lei, J. and Gan, Z. and Liu, J.J.",
        TITLE = "Adversarial VQA:
A New Benchmark for Evaluating the Robustness of VQA Models",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2022-2031",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205726"}

@inproceedings{bb210641,
        AUTHOR = "Askarian, N. and Abbasnejad, E. and Zukerman, I. and Buntine, W. and Haffari, G.",
        TITLE = "Inductive Biases for Low Data VQA: A Data Augmentation Approach",
        BOOKTITLE = Novelty22,
        YEAR = "2022",
        PAGES = "231-240",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205727"}

@inproceedings{bb210642,
        AUTHOR = "Mathew, M. and Bagal, V. and Tito, R. and Karatzas, D. and Valveny, E. and Jawahar, C.V.",
        TITLE = "InfographicVQA",
        BOOKTITLE = WACV22,
        YEAR = "2022",
        PAGES = "2582-2591",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205728"}

@inproceedings{bb210643,
        AUTHOR = "Kumar, S. and Patro, B.N. and Namboodiri, V.P.",
        TITLE = "Auto QA: The Question Is Not Only What, but Also Where",
        BOOKTITLE = Novelty22,
        YEAR = "2022",
        PAGES = "272-281",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205729"}

@inproceedings{bb210644,
        AUTHOR = "Kolling, C. and More, M. and Gavenski, N. and Pooch, E. and Parraga, O. and Barros, R.C.",
        TITLE = "Efficient Counterfactual Debiasing for Visual Question Answering",
        BOOKTITLE = WACV22,
        YEAR = "2022",
        PAGES = "2572-2581",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205730"}

@inproceedings{bb210645,
        AUTHOR = "Jung, S.J. and Byun, J. and Shim, K. and Hwang, S.Y. and Kim, C.",
        TITLE = "Understanding VQA for Negative Answers Through Visual and Linguistic
Inference",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "2873-2877",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205731"}

@inproceedings{bb210646,
        AUTHOR = "Felix, R. and Repasky, B. and Hodge, S. and Zolfaghari, R. and Abbasnejad, E. and Sherrah, J.",
        TITLE = "Cross-Modal Visual Question Answering for Remote Sensing Data: the
International Conference on Digital Image Computing: Techniques and
Applications (DICTA 2021)",
        BOOKTITLE = DICTA21,
        YEAR = "2021",
        PAGES = "1-9",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205732"}

@inproceedings{bb210647,
        AUTHOR = "Le, T. and Nguyen, H.T. and Nguyen, M.L.",
        TITLE = "Vision and Text Transformer for Predicting Answerability on Visual
Question Answering",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "934-938",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205733"}

@inproceedings{bb210648,
        AUTHOR = "Huang, Z.Q. and Zhu, H.Y. and Sun, Y. and Choi, D. and Tan, C. and Lim, J.H.",
        TITLE = "A Diagnostic Study of Visual Question Answering With Analogical
Reasoning",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "2463-2467",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205734"}

@inproceedings{bb210649,
        AUTHOR = "Chen, H.Y. and Liu, R.F. and Peng, B.",
        TITLE = "Cross-modal Relational Reasoning Network for Visual Question
Answering",
        BOOKTITLE = MAIR2-21,
        YEAR = "2021",
        PAGES = "3939-3948",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205735"}

@inproceedings{bb210650,
        AUTHOR = "Wang, Z.X. and Miao, Y. and Specia, L.",
        TITLE = "Latent Variable Models for Visual Question Answering",
        BOOKTITLE = CLVL21,
        YEAR = "2021",
        PAGES = "3137-3141",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205736"}

@inproceedings{bb210651,
        AUTHOR = "Hirota, Y. and Garcia, N. and Otani, M. and Chu, C. and Nakashima, Y. and Taniguchi, I. and Onoye, T.",
        TITLE = "Visual Question Answering with Textual Representations for Images",
        BOOKTITLE = CLVL21,
        YEAR = "2021",
        PAGES = "3147-3150",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205737"}

@inproceedings{bb210652,
        AUTHOR = "Ye, K. and Kovashka, A.",
        TITLE = "Linguistic Structures as Weak Supervision for Visual Scene Graph
Generation",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "8285-8295",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205738"}

@inproceedings{bb210653,
        AUTHOR = "Xiao, J.B. and Shang, X. and Yao, A. and Chua, T.S.",
        TITLE = "NExT-QA: Next Phase of Question-Answering to Explaining Temporal
Actions",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "9772-9781",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205739"}

@inproceedings{bb210654,
        AUTHOR = "Chen, X.Y. and Jiang, M. and Zhao, Q.",
        TITLE = "Predicting Human Scanpaths in Visual Question Answering",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "10871-10880",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205740"}

@inproceedings{bb210655,
        AUTHOR = "Qi, Y.G. and Zhang, K. and Sain, A. and Song, Y.Z.",
        TITLE = "PQA: Perceptual Question Answering",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "12051-12059",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205741"}

@inproceedings{bb210656,
        AUTHOR = "Yuan, Y.Y. and Wang, S. and Jiang, M.Y. and Chen, T.Y.",
        TITLE = "Perception Matters: Detecting Perception Failures of VQA Models Using
Metamorphic Testing",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "16903-16912",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205742"}

@inproceedings{bb210657,
        AUTHOR = "Marino, K. and Chen, X.L. and Parikh, D. and Gupta, A. and Rohrbach, M.",
        TITLE = "KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain
Knowledge-Based VQA",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "14106-14116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205743"}

@inproceedings{bb210658,
        AUTHOR = "Niu, Y. and Tang, K. and Zhang, H.W. and Lu, Z.W. and Hua, X.S. and Wen, J.R.",
        TITLE = "Counterfactual VQA: A Cause-Effect Look at Language Bias",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "12695-12705",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205744"}

@inproceedings{bb210659,
        AUTHOR = "Yang, Z.Y. and Lu, Y.J. and Wang, J.F. and Yin, X. and Florencio, D. and Wang, L.J. and Zhang, C. and Zhang, L. and Luo, J.B.",
        TITLE = "TAP: Text-Aware Pre-training for Text-VQA and Text-Caption",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "8747-8757",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205745"}

@inproceedings{bb210660,
        AUTHOR = "Kervadec, C. and Jaunet, T. and Antipov, G. and Baccouche, M. and Vuillemot, R. and Wolf, C.",
        TITLE = "How Transferable are Reasoning Patterns in VQA?",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "4205-4214",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205746"}

@inproceedings{bb210661,
        AUTHOR = "Kervadec, C. and Antipov, G. and Baccouche, M. and Wolf, C.",
        TITLE = "Roses are Red, Violets are Blue… But Should VQA expect Them To?",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "2775-2784",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205747"}

@inproceedings{bb210662,
        AUTHOR = "Dua, R. and Kancheti, S.S. and Balasubramanian, V.N.",
        TITLE = "Beyond VQA: Generating Multi-word Answers and Rationales to Visual
Questions",
        BOOKTITLE = MULA21,
        YEAR = "2021",
        PAGES = "1623-1632",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205748"}

@inproceedings{bb210663,
        AUTHOR = "Rahman, T. and Chou, S.H. and Sigal, L. and Carenini, G.",
        TITLE = "An Improved Attention for Visual Question Answering",
        BOOKTITLE = MULA21,
        YEAR = "2021",
        PAGES = "1653-1662",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205749"}

@inproceedings{bb210664,
        AUTHOR = "Jolly, S. and Palacio, S. and Folz, J. and Raue, F. and Hees, J. and Dengel, A.",
        TITLE = "P ˜ NP, at least in Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "2748-2754",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205750"}

@inproceedings{bb210665,
        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/applicat803vqa1.html#TT205751"}

@inproceedings{bb210666,
        AUTHOR = "Farazi, M. and Khan, S. and Barnes, N.M.",
        TITLE = "Question-Agnostic Attention for Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "3542-3549",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205752"}

@inproceedings{bb210667,
        AUTHOR = "Li, Y. and Lin, Y. and Zhao, H.H. and Wang, D.H.",
        TITLE = "Dual Path Multi-Modal High-Order Features for Textual Content based
Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "4324-4331",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205753"}

@inproceedings{bb210668,
        AUTHOR = "Mishra, A. and Anand, A. and Guha, P.",
        TITLE = "Multi-stage Attention based Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "9407-9414",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205754"}

@inproceedings{bb210669,
        AUTHOR = "Bozinis, T. and Passalis, N. and Tefas, A.",
        TITLE = "Improving Visual Question Answering using Active Perception on Static
Images",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "879-884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205755"}

@inproceedings{bb210670,
        AUTHOR = "Huang, H.T. and Han, T. and Han, W. and Yap, D. and Chiang, C.M.",
        TITLE = "Answer-checking in Context:
A Multi-modal Fully Attention Network for Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "1173-1180",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205756"}

@inproceedings{bb210671,
        AUTHOR = "Sun, Q. and Xie, B.H. and Fu, Y.W.",
        TITLE = "Second Order Enhanced Multi-Glimpse Attention in Visual Question
Answering",
        BOOKTITLE = ACCV20,
        YEAR = "2020",
        PAGES = "IV:87-103",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205757"}

@inproceedings{bb210672,
        AUTHOR = "Goel, V. and Chandak, M. and Anand, A. and Guha, P.",
        TITLE = "IQ-VQA: Intelligent Visual Question Answering",
        BOOKTITLE = VTIUR20,
        YEAR = "2020",
        PAGES = "357-370",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205758"}

@inproceedings{bb210673,
        AUTHOR = "Qiao, Y. and Yu, Z. and Liu, J.",
        TITLE = "VC-VQA: Visual Calibration Mechanism For Visual Question Answering",
        BOOKTITLE = ICIP20,
        YEAR = "2020",
        PAGES = "1481-1485",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205759"}

@inproceedings{bb210674,
        AUTHOR = "Tang, R.X. and Ma, C. and Zhang, W.E. and Wu, Q. and Yang, X.K.",
        TITLE = "Semantic Equivalent Adversarial Data Augmentation for Visual Question
Answering",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIX:437-453",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205760"}

@inproceedings{bb210675,
        AUTHOR = "Gokhale, T. and Banerjee, P. and Baral, C. and Yang, Y.Z.",
        TITLE = "VQA-LOL: Visual Question Answering Under the Lens of Logic",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXI:379-396",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205761"}

@inproceedings{bb210676,
        AUTHOR = "Yang, X.F. and Lin, G.S. and Lv, F.M. and Liu, F.Y.",
        TITLE = "TRRNET:
Tiered Relation Reasoning for Compositional Visual Question Answering",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXI:414-430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205762"}

@inproceedings{bb210677,
        AUTHOR = "Bansal, A. and Zhang, Y. and Chellappa, R.",
        TITLE = "Visual Question Answering on Image Sets",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXI:51-67",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205763"}

@inproceedings{bb210678,
        AUTHOR = "Han, X.Z. and Wang, S.H. and Su, C. and Zhang, W.G. and Huang, Q.M. and Tian, Q.",
        TITLE = "Interpretable Visual Reasoning via Probabilistic Formulation Under
Natural Supervision",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "IX:553-570",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205764"}

@inproceedings{bb210679,
        AUTHOR = "Kant, Y. and Batra, D. and Anderson, P. and Schwing, A. and Parikh, D. and Lu, J. and Agrawal, H.",
        TITLE = "Spatially Aware Multimodal Transformers for TextVQA",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "IX:715-732",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205765"}

@inproceedings{bb210680,
        AUTHOR = "Li, Q. and Huang, S.Y. and Hong, Y. and Zhu, S.C.",
        TITLE = "A Competence-aware Curriculum for Visual Concepts Learning via Question
Answering",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "II:141-157",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205766"}

@inproceedings{bb210681,
        AUTHOR = "Bajaj, G. and Bandyopadhyay, B. and Schmidt, D. and Maneriker, P. and Myers, C. and Parthasarathy, S.",
        TITLE = "Understanding Knowledge Gaps in Visual Question Answering:
Implications for Gap Identification and Testing",
        BOOKTITLE = MVM20,
        YEAR = "2020",
        PAGES = "1563-1566",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205767"}

@inproceedings{bb210682,
        AUTHOR = "Vatashsky, B. and Ullman, S.",
        TITLE = "VQA With No Questions-Answers Training",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10373-10383",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205768"}

@inproceedings{bb210683,
        AUTHOR = "Jiang, H. and Misra, I. and Rohrbach, M. and Learned Miller, E.G. and Chen, X.",
        TITLE = "In Defense of Grid Features for Visual Question Answering",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10264-10273",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205769"}

@inproceedings{bb210684,
        AUTHOR = "Wang, X. and Liu, Y. and Shen, C. and Ng, C.C. and Luo, C. and Jin, L. and Chan, C.S. and van den Hengel, A. and Wang, L.",
        TITLE = "On the General Value of Evidence, and Bilingual Scene-Text Visual
Question Answering",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10123-10132",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205770"}

@inproceedings{bb210685,
        AUTHOR = "Xiong, P. and Wu, Y.",
        TITLE = "TA-Student VQA: Multi-Agents Training by Self-Questioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10062-10072",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205771"}

@inproceedings{bb210686,
        AUTHOR = "Agarwal, V. and Shetty, R. and Fritz, M.",
        TITLE = "Towards Causal VQA: Revealing and Reducing Spurious Correlations by
Invariant and Covariant Semantic Editing",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "9687-9695",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205772"}

@inproceedings{bb210687,
        AUTHOR = "Hu, R. and Singh, A. and Darrell, T.J. and Rohrbach, M.",
        TITLE = "Iterative Answer Prediction With Pointer-Augmented Multimodal
Transformers for TextVQA",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "9989-9999",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205773"}

@inproceedings{bb210688,
        AUTHOR = "Kafle, K. and Shrestha, R. and Price, B. and Cohen, S. and Kanan, C.",
        TITLE = "Answering Questions about Data Visualizations using Efficient Bimodal
Fusion",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1487-1496",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205774"}

@inproceedings{bb210689,
        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/applicat803vqa1.html#TT205775"}

@inproceedings{bb210690,
        AUTHOR = "Patro, B.N. and Patel, S. and Namboodiri, V.P.",
        TITLE = "Robust Explanations for Visual Question Answering",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1566-1575",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205776"}

@inproceedings{bb210691,
        AUTHOR = "Chou, S. and Chao, W. and Lai, W. and Sun, M. and Yang, M.",
        TITLE = "Visual Question Answering on 360° Images",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1596-1605",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205777"}

@inproceedings{bb210692,
        AUTHOR = "Chaudhry, R. and Shekhar, S. and Gupta, U. and Maneriker, P. and Bansal, P. and Joshi, A.",
        TITLE = "LEAF-QA: Locate, Encode Attend for Figure Question Answering",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "3501-3510",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205778"}

@inproceedings{bb210693,
        AUTHOR = "Liang, Y.Z. and Bai, Y.L. and Zhang, W. and Qian, X.M. and Zhu, L. and Mei, T.",
        TITLE = "VrR-VG: Refocusing Visually-Relevant Relationships",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "10402-10411",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205779"}

@inproceedings{bb210694,
        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/applicat803vqa1.html#TT205780"}

@inproceedings{bb210695,
        AUTHOR = "Bhattacharya, N. and Li, Q. and Gurari, D.",
        TITLE = "Why Does a Visual Question Have Different Answers?",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4270-4279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205781"}

@inproceedings{bb210696,
        AUTHOR = "Li, L. and Gan, Z. and Cheng, Y. and Liu, J.",
        TITLE = "Relation-Aware Graph Attention Network for Visual Question Answering",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "10312-10321",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205782"}

@inproceedings{bb210697,
        AUTHOR = "Peng, G. and You, H.X. and Zhang, Z.P. and Wang, X.G. and Li, H.S.",
        TITLE = "Multi-Modality Latent Interaction Network for Visual Question
Answering",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "5824-5834",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205783"}

@inproceedings{bb210698,
        AUTHOR = "Do, T. and Tran, H. and Do, T. and Tjiputra, E. and Tran, Q.",
        TITLE = "Compact Trilinear Interaction for Visual Question Answering",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "392-401",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205784"}

@inproceedings{bb210699,
        AUTHOR = "Schwartz, I. and Yu, S. and Hazan, T. and Schwing, A.G.",
        TITLE = "Factor Graph Attention",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "2039-2048",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT205785"}

Last update:Jan 30, 2024 at 20:33:16