@inproceedings{bb244300,
AUTHOR = "Liu, H. and Ilievski, F. and Snoek, C.G.M.",
TITLE = "Commonsense Video Question Answering through Video-Grounded
Entailment Tree Reasoning",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3262-3271",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239206"}
@inproceedings{bb244301,
AUTHOR = "Choudhary, N. and Goyal, P. and Siwatch, D. and Chandak, A. and Mahajan, H. and Khurana, V. and Kumar, Y.",
TITLE = "AdQuestA: Knowledge-Guided Visual Question Answer Framework for
Advertisements",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5812-5821",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239207"}
@inproceedings{bb244302,
AUTHOR = "Ge, J.X. and Subramanian, S. and Shi, B.F. and Herzig, R. and Darrell, T.J.",
TITLE = "Recursive Visual Programming",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIII: 1-18",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239208"}
@inproceedings{bb244303,
AUTHOR = "Lu, C. and Lu, Q. and Luo, J.",
TITLE = "An Explainable Vision Question Answer Model via Diffusion
Chain-of-thought",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXVII: 146-162",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239209"}
@inproceedings{bb244304,
AUTHOR = "Wang, H.B. and Ge, W.F.",
TITLE = "Q&A Prompts: Discovering Rich Visual Clues through Mining
Question-answer Prompts for VQA requiring Diverse World Knowledge",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLII: 274-292",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239210"}
@inproceedings{bb244305,
AUTHOR = "Liu, H. and Ma, X. and Zhong, C. and Zhang, Y. and Lin, W.Y.",
TITLE = "Timecraft: Navigate Weakly-supervised Temporal Grounded Video Question
Answering via Bi-directional Reasoning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "V: 92-107",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239211"}
@inproceedings{bb244306,
AUTHOR = "Zhang, Y.F. and Jiang, M. and Zhao, Q.",
TITLE = "Grace: Graph-based Contextual Debiasing for Fair Visual Question
Answering",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVII: 176-194",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239212"}
@inproceedings{bb244307,
AUTHOR = "Liu, X.L. and Dong, Z.K. and Zhang, P.",
TITLE = "Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for
Unbiased Question-Answering",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4466-4475",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239213"}
@inproceedings{bb244308,
AUTHOR = "Shi, X.X. and Lee, S.",
TITLE = "Benchmarking Out-of-Distribution Detection in Visual Question
Answering",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5473-5483",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239214"}
@inproceedings{bb244309,
AUTHOR = "Venkataraman, S.R. and Rao, R.S. and Balasubramanian, S. and Sarma, R.R. and Vorugunti, C.S.",
TITLE = "Can you even tell left from right? Presenting a new challenge for VQA",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4486-4495",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT239215"}
@inproceedings{bb244310,
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#TT239216"}
@inproceedings{bb244311,
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#TT239217"}
@inproceedings{bb244312,
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#TT239218"}
@inproceedings{bb244313,
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#TT239219"}
@inproceedings{bb244314,
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#TT239220"}
@inproceedings{bb244315,
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#TT239221"}
@inproceedings{bb244316,
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#TT239222"}
@inproceedings{bb244317,
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#TT239223"}
@inproceedings{bb244318,
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#TT239224"}
@inproceedings{bb244319,
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#TT239225"}
@inproceedings{bb244320,
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#TT239226"}
@inproceedings{bb244321,
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#TT239227"}
@inproceedings{bb244322,
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#TT239228"}
@inproceedings{bb244323,
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#TT239229"}
@inproceedings{bb244324,
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#TT239230"}
@inproceedings{bb244325,
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#TT239231"}
@inproceedings{bb244326,
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#TT239232"}
@inproceedings{bb244327,
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#TT239233"}
@inproceedings{bb244328,
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#TT239234"}
@inproceedings{bb244329,
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#TT239235"}
@inproceedings{bb244330,
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#TT239236"}
@inproceedings{bb244331,
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#TT239237"}
@inproceedings{bb244332,
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#TT239238"}
@inproceedings{bb244333,
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#TT239239"}
@inproceedings{bb244334,
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#TT239240"}
@inproceedings{bb244335,
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#TT239241"}
@inproceedings{bb244336,
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#TT239242"}
@inproceedings{bb244337,
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#TT239243"}
@inproceedings{bb244338,
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#TT239244"}
@inproceedings{bb244339,
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#TT239245"}
@inproceedings{bb244340,
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#TT239246"}
@inproceedings{bb244341,
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#TT239247"}
@inproceedings{bb244342,
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#TT239248"}
@inproceedings{bb244343,
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#TT239249"}
@inproceedings{bb244344,
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#TT239250"}
@inproceedings{bb244345,
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#TT239251"}
@inproceedings{bb244346,
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#TT239252"}
@inproceedings{bb244347,
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#TT239253"}
@inproceedings{bb244348,
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#TT239254"}
@inproceedings{bb244349,
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#TT239255"}
@inproceedings{bb244350,
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#TT239256"}
@inproceedings{bb244351,
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#TT239257"}
@inproceedings{bb244352,
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#TT239258"}
@inproceedings{bb244353,
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#TT239259"}
@inproceedings{bb244354,
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#TT239260"}
@inproceedings{bb244355,
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#TT239261"}
@inproceedings{bb244356,
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#TT239262"}
@inproceedings{bb244357,
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#TT239263"}
@inproceedings{bb244358,
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#TT239264"}
@inproceedings{bb244359,
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#TT239265"}
@inproceedings{bb244360,
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#TT239266"}
@inproceedings{bb244361,
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#TT239267"}
@inproceedings{bb244362,
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#TT239268"}
@inproceedings{bb244363,
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#TT239269"}
@inproceedings{bb244364,
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#TT239270"}
@inproceedings{bb244365,
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#TT239271"}
@inproceedings{bb244366,
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#TT239272"}
@inproceedings{bb244367,
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#TT239273"}
@inproceedings{bb244368,
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#TT239274"}
@inproceedings{bb244369,
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#TT239275"}
@inproceedings{bb244370,
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#TT239276"}
@inproceedings{bb244371,
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#TT239277"}
@inproceedings{bb244372,
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#TT239278"}
@inproceedings{bb244373,
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#TT239279"}
@inproceedings{bb244374,
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#TT239280"}
@inproceedings{bb244375,
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#TT239281"}
@inproceedings{bb244376,
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#TT239282"}
@inproceedings{bb244377,
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#TT239283"}
@inproceedings{bb244378,
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#TT239284"}
@inproceedings{bb244379,
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#TT239285"}
@inproceedings{bb244380,
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#TT239286"}
@inproceedings{bb244381,
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#TT239287"}
@inproceedings{bb244382,
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#TT239288"}
@inproceedings{bb244383,
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#TT239289"}
@inproceedings{bb244384,
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#TT239290"}
@inproceedings{bb244385,
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#TT239291"}
@inproceedings{bb244386,
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#TT239292"}
@inproceedings{bb244387,
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#TT239293"}
@inproceedings{bb244388,
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#TT239294"}
@inproceedings{bb244389,
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#TT239295"}
@inproceedings{bb244390,
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#TT239296"}
@inproceedings{bb244391,
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#TT239297"}
@inproceedings{bb244392,
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#TT239298"}
@inproceedings{bb244393,
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#TT239299"}
@inproceedings{bb244394,
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#TT239300"}
@inproceedings{bb244395,
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#TT239301"}
@inproceedings{bb244396,
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#TT239302"}
@inproceedings{bb244397,
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#TT239303"}
@inproceedings{bb244398,
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#TT239304"}
@inproceedings{bb244399,
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#TT239305"}
Last update:Aug 19, 2026 at 13:26:35