@inproceedings{bb235500,
        AUTHOR = "Sahu, P.P. and Raut, A. and Samant, J.S. and Gorijala, M. and Lakshminarayanan, V. and Bhaskar, P.",
        TITLE = "POP-VQA: Privacy preserving, On-device, Personalized Visual Question
Answering",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "8455-8464",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230466"}

@inproceedings{bb235501,
        AUTHOR = "Li, J.P. and Wei, P. and Han, W.J. and Fan, L.F.",
        TITLE = "IntentQA: Context-aware Video Intent Reasoning",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "11929-11940",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230467"}

@inproceedings{bb235502,
        AUTHOR = "Hu, Y.S. and Hua, H. and Yang, Z.Y. and Shi, W.J. and Smith, N.A. and Luo, J.B.",
        TITLE = "PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "2951-2963",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230468"}

@inproceedings{bb235503,
        AUTHOR = "Naik, N. and Potts, C. and Kreiss, E.",
        TITLE = "Context-VQA: Towards Context-Aware and Purposeful Visual Question
Answering",
        BOOKTITLE = CLVL23,
        YEAR = "2023",
        PAGES = "2813-2817",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230469"}

@inproceedings{bb235504,
        AUTHOR = "Hu, Y.S. and Liu, B. and Kasai, J. and Wang, Y.Z. and Ostendorf, M. and Krishna, R. and Smith, N.A.",
        TITLE = "TIFA: Accurate and Interpretable Text-to-Image Faithfulness
Evaluation with Question Answering",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "20349-20360",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230470"}

@inproceedings{bb235505,
        AUTHOR = "Zhang, Y.W. and Ho, C.H. and Vasconcelos, N.M.",
        TITLE = "Toward Unsupervised Realistic Visual Question Answering",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "15567-15578",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230471"}

@inproceedings{bb235506,
        AUTHOR = "Liang, K. and Albanie, S.",
        TITLE = "Simple Baselines for Interactive Video Retrieval with Questions and
Answers",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "11057-11067",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230472"}

@inproceedings{bb235507,
        AUTHOR = "Mensink, T. and Uijlings, J. and Castrejon, L. and Goel, A. and Cadar, F. and Zhou, H. and Sha, F. and Araujo, A. and Ferrari, V.",
        TITLE = "Encyclopedic VQA: Visual questions about detailed properties of
fine-grained categories",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "3090-3101",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230473"}

@inproceedings{bb235508,
        AUTHOR = "Bruni, P. and Falcon, A. and Radeva, P.",
        TITLE = "Time-aware Circulant Matrices for Question-based Temporal Localization",
        BOOKTITLE = CIAP23,
        YEAR = "2023",
        PAGES = "II:182-195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230474"}

@inproceedings{bb235509,
        AUTHOR = "Ferreira, B.C.L. and Oliveira, H.G. and Silva, C.",
        TITLE = "Leveraging Question Answering for Domain-Agnostic Information
Extraction",
        BOOKTITLE = CIARP23,
        YEAR = "2023",
        PAGES = "I:244-256",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230475"}

@inproceedings{bb235510,
        AUTHOR = "Wu, Z.H. and Shu, X.Y. and Yan, S.Y. and Lu, Z.Y.",
        TITLE = "FGCVQA: Fine-Grained Cross-Attention for Medical VQA",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "975-979",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230476"}

@inproceedings{bb235511,
        AUTHOR = "Zhu, H. and Togo, R. and Ogawa, T. and Haseyama, M.",
        TITLE = "Interpretable Visual Question Answering Referring to Outside
Knowledge",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "2140-2144",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230477"}

@inproceedings{bb235512,
        AUTHOR = "Parelli, M. and Mallis, D. and Diomataris, M. and Pitsikalis, V.",
        TITLE = "Interpretable Visual Question Answering Via Reasoning Supervision",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "2525-2529",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230478"}

@inproceedings{bb235513,
        AUTHOR = "Hegde, S. and Jahagirdar, S. and Gangisetty, S.",
        TITLE = "Making the V in Text-VQA Matter",
        BOOKTITLE = ODRUM23,
        YEAR = "2023",
        PAGES = "5580-5588",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230479"}

@inproceedings{bb235514,
        AUTHOR = "Suo, W. and Sun, M.Y. and Liu, W.S. and Gao, Y.Q. and Wang, P. and Zhang, Y.N. and Wu, Q.",
        TITLE = "S3C: Semi-Supervised VQA Natural Language Explanation via
Self-Critical Learning",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "2646-2656",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230480"}

@inproceedings{bb235515,
        AUTHOR = "Alampalle, C. and Hegde, S. and Jahagirdar, S. and Gangisetty, S.",
        TITLE = "Weakly Supervised Visual Question Answer Generation",
        BOOKTITLE = ODRUM23,
        YEAR = "2023",
        PAGES = "5589-5597",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230481"}

@inproceedings{bb235516,
        AUTHOR = "Jiang, J.J. and Zheng, N.N.",
        TITLE = "MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource
Visual Question Answering",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "24203-24213",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230482"}

@inproceedings{bb235517,
        AUTHOR = "Wang, Y. and Pfeiffer, J. and Carion, N. and Le Cun, Y.L. and Kamath, A.",
        TITLE = "Adapting Grounded Visual Question Answering Models to Low Resource
Languages",
        BOOKTITLE = MULA23,
        YEAR = "2023",
        PAGES = "2596-2605",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230483"}

@inproceedings{bb235518,
        AUTHOR = "Wang, M. and Mahjoubfar, A. and Joshi, A.",
        TITLE = "FashionVQA: A Domain-Specific Visual Question Answering System",
        BOOKTITLE = CVFAD23,
        YEAR = "2023",
        PAGES = "3514-3519",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230484"}

@inproceedings{bb235519,
        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#TT230485"}

@inproceedings{bb235520,
        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#TT230486"}

@inproceedings{bb235521,
        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#TT230487"}

@inproceedings{bb235522,
        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#TT230488"}

@inproceedings{bb235523,
        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#TT230489"}

@inproceedings{bb235524,
        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#TT230490"}

@inproceedings{bb235525,
        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#TT230491"}

@inproceedings{bb235526,
        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#TT230492"}

@inproceedings{bb235527,
        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#TT230493"}

@inproceedings{bb235528,
        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#TT230494"}

@inproceedings{bb235529,
        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#TT230495"}

@inproceedings{bb235530,
        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#TT230496"}

@inproceedings{bb235531,
        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#TT230497"}

@inproceedings{bb235532,
        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#TT230498"}

@inproceedings{bb235533,
        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#TT230499"}

@inproceedings{bb235534,
        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#TT230500"}

@inproceedings{bb235535,
        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#TT230501"}

@inproceedings{bb235536,
        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#TT230502"}

@inproceedings{bb235537,
        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#TT230503"}

@inproceedings{bb235538,
        AUTHOR = "Li, G.Y. and Wei, Y. and Tian, Y.P. 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#TT230504"}

@inproceedings{bb235539,
        AUTHOR = "Chen, C.Y. 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#TT230505"}

@inproceedings{bb235540,
        AUTHOR = "Li, C.H. and Li, Z. and Jing, C.C. and Wu, Y.W. and Zhai, M.L. and Jia, Y.D.",
        TITLE = "Compositional Substitutivity of Visual Reasoning for Visual Question
Answering",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XLVIII: 143-160",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230506"}

@inproceedings{bb235541,
        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#TT230507"}

@inproceedings{bb235542,
        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#TT230508"}

@inproceedings{bb235543,
        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#TT230509"}

@inproceedings{bb235544,
        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#TT230510"}

@inproceedings{bb235545,
        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#TT230511"}

@inproceedings{bb235546,
        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#TT230512"}

@inproceedings{bb235547,
        AUTHOR = "Zhou, Y.Y. and Ren, T.H. 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#TT230513"}

@inproceedings{bb235548,
        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#TT230514"}

@inproceedings{bb235549,
        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#TT230515"}

@inproceedings{bb235550,
        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#TT230516"}

@inproceedings{bb235551,
        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#TT230517"}

@inproceedings{bb235552,
        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#TT230518"}

@inproceedings{bb235553,
        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#TT230519"}

@inproceedings{bb235554,
        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#TT230520"}

@inproceedings{bb235555,
        AUTHOR = "Jung, S.J. and Byun, J.Y. 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#TT230521"}

@inproceedings{bb235556,
        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#TT230522"}

@inproceedings{bb235557,
        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#TT230523"}

@inproceedings{bb235558,
        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#TT230524"}

@inproceedings{bb235559,
        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#TT230525"}

@inproceedings{bb235560,
        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#TT230526"}

@inproceedings{bb235561,
        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#TT230527"}

@inproceedings{bb235562,
        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#TT230528"}

@inproceedings{bb235563,
        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#TT230529"}

@inproceedings{bb235564,
        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#TT230530"}

@inproceedings{bb235565,
        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#TT230531"}

@inproceedings{bb235566,
        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#TT230532"}

@inproceedings{bb235567,
        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#TT230533"}

@inproceedings{bb235568,
        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#TT230534"}

@inproceedings{bb235569,
        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#TT230535"}

@inproceedings{bb235570,
        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#TT230536"}

@inproceedings{bb235571,
        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#TT230537"}

@inproceedings{bb235572,
        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#TT230538"}

@inproceedings{bb235573,
        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#TT230539"}

@inproceedings{bb235574,
        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#TT230540"}

@inproceedings{bb235575,
        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#TT230541"}

@inproceedings{bb235576,
        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#TT230542"}

@inproceedings{bb235577,
        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#TT230543"}

@inproceedings{bb235578,
        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#TT230544"}

@inproceedings{bb235579,
        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#TT230545"}

@inproceedings{bb235580,
        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#TT230546"}

@inproceedings{bb235581,
        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#TT230547"}

@inproceedings{bb235582,
        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#TT230548"}

@inproceedings{bb235583,
        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#TT230549"}

@inproceedings{bb235584,
        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#TT230550"}

@inproceedings{bb235585,
        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#TT230551"}

@inproceedings{bb235586,
        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#TT230552"}

@inproceedings{bb235587,
        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#TT230553"}

@inproceedings{bb235588,
        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#TT230554"}

@inproceedings{bb235589,
        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#TT230555"}

@inproceedings{bb235590,
        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#TT230556"}

@inproceedings{bb235591,
        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#TT230557"}

@inproceedings{bb235592,
        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#TT230558"}

@inproceedings{bb235593,
        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#TT230559"}

@inproceedings{bb235594,
        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#TT230560"}

@inproceedings{bb235595,
        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#TT230561"}

@inproceedings{bb235596,
        AUTHOR = "Li, L.J. and Gan, Z. and Cheng, Y. and Liu, J.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#TT230562"}

@inproceedings{bb235597,
        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#TT230563"}

@inproceedings{bb235598,
        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#TT230564"}

@inproceedings{bb235599,
        AUTHOR = "Kolesnikov, A. and Beyer, L. and Zhai, X.H. and Puigcerver, J. and Yung, J. and Gelly, S. and Houlsby, N.",
        TITLE = "Big Transfer (BIT): General Visual Representation Learning",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "V:491-507",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT230565"}

Last update:Nov 10, 2025 at 14:27:42