@article{bb234900,
AUTHOR = "Welde, T.M. and Liao, L.",
TITLE = "Counting in Visual Question Answering:
Methods, Datasets, and Future Work",
JOURNAL = IJIG,
VOLUME = "25",
YEAR = "2025",
NUMBER = "5",
MONTH = "September",
PAGES = "2550044",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT229868"}
@article{bb234901,
AUTHOR = "Bi, C. and Wang, S.H. and Li, N. and Huang, Q.M.",
TITLE = "Inferential and Commonsense Visual Question Generation",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "7796-7809",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT229869"}
@inproceedings{bb234902,
AUTHOR = "Luo, J.Z. and Liu, Y. and Chen, W.X. and Li, Z. and Wang, Y.W. and Li, G.B. and Lin, L.",
TITLE = "DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14169-14178",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT229870"}
@inproceedings{bb234903,
AUTHOR = "Zou, Y.H. and Yin, Z.Z.",
TITLE = "Alignment, Mining and Fusion: Representation Alignment with Hard
Negative Mining and Selective Knowledge Fusion for Medical Visual
Question Answering",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29623-29633",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT229871"}
@inproceedings{bb234904,
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#TT229872"}
@inproceedings{bb234905,
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#TT229873"}
@inproceedings{bb234906,
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#TT229874"}
@inproceedings{bb234907,
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#TT229875"}
@inproceedings{bb234908,
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#TT229876"}
@inproceedings{bb234909,
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#TT229877"}
@inproceedings{bb234910,
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#TT229878"}
@inproceedings{bb234911,
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#TT229879"}
@inproceedings{bb234912,
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#TT229880"}
@inproceedings{bb234913,
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#TT229881"}
@inproceedings{bb234914,
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#TT229882"}
@inproceedings{bb234915,
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#TT229883"}
@inproceedings{bb234916,
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#TT229884"}
@inproceedings{bb234917,
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#TT229885"}
@inproceedings{bb234918,
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#TT229886"}
@inproceedings{bb234919,
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#TT229887"}
@inproceedings{bb234920,
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#TT229888"}
@inproceedings{bb234921,
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#TT229889"}
@inproceedings{bb234922,
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#TT229890"}
@inproceedings{bb234923,
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#TT229891"}
@inproceedings{bb234924,
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#TT229892"}
@inproceedings{bb234925,
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#TT229893"}
@inproceedings{bb234926,
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#TT229894"}
@inproceedings{bb234927,
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#TT229895"}
@inproceedings{bb234928,
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#TT229896"}
@inproceedings{bb234929,
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#TT229897"}
@inproceedings{bb234930,
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#TT229898"}
@inproceedings{bb234931,
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#TT229899"}
@inproceedings{bb234932,
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#TT229900"}
@inproceedings{bb234933,
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#TT229901"}
@inproceedings{bb234934,
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#TT229902"}
@inproceedings{bb234935,
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#TT229903"}
@inproceedings{bb234936,
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#TT229904"}
@inproceedings{bb234937,
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#TT229905"}
@inproceedings{bb234938,
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#TT229906"}
@inproceedings{bb234939,
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#TT229907"}
@inproceedings{bb234940,
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#TT229908"}
@inproceedings{bb234941,
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#TT229909"}
@inproceedings{bb234942,
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#TT229910"}
@inproceedings{bb234943,
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#TT229911"}
@inproceedings{bb234944,
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#TT229912"}
@inproceedings{bb234945,
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#TT229913"}
@inproceedings{bb234946,
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#TT229914"}
@inproceedings{bb234947,
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#TT229915"}
@inproceedings{bb234948,
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#TT229916"}
@inproceedings{bb234949,
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#TT229917"}
@inproceedings{bb234950,
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#TT229918"}
@inproceedings{bb234951,
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#TT229919"}
@inproceedings{bb234952,
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#TT229920"}
@inproceedings{bb234953,
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#TT229921"}
@inproceedings{bb234954,
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#TT229922"}
@inproceedings{bb234955,
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#TT229923"}
@inproceedings{bb234956,
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#TT229924"}
@inproceedings{bb234957,
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#TT229925"}
@inproceedings{bb234958,
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#TT229926"}
@inproceedings{bb234959,
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#TT229927"}
@inproceedings{bb234960,
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#TT229928"}
@inproceedings{bb234961,
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#TT229929"}
@inproceedings{bb234962,
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#TT229930"}
@inproceedings{bb234963,
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#TT229931"}
@inproceedings{bb234964,
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#TT229932"}
@inproceedings{bb234965,
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#TT229933"}
@inproceedings{bb234966,
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#TT229934"}
@inproceedings{bb234967,
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#TT229935"}
@inproceedings{bb234968,
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#TT229936"}
@inproceedings{bb234969,
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#TT229937"}
@inproceedings{bb234970,
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#TT229938"}
@inproceedings{bb234971,
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#TT229939"}
@inproceedings{bb234972,
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#TT229940"}
@inproceedings{bb234973,
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#TT229941"}
@inproceedings{bb234974,
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#TT229942"}
@inproceedings{bb234975,
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#TT229943"}
@inproceedings{bb234976,
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#TT229944"}
@inproceedings{bb234977,
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#TT229945"}
@inproceedings{bb234978,
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#TT229946"}
@inproceedings{bb234979,
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#TT229947"}
@inproceedings{bb234980,
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#TT229948"}
@inproceedings{bb234981,
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#TT229949"}
@inproceedings{bb234982,
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#TT229950"}
@inproceedings{bb234983,
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#TT229951"}
@inproceedings{bb234984,
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#TT229952"}
@inproceedings{bb234985,
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#TT229953"}
@inproceedings{bb234986,
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#TT229954"}
@inproceedings{bb234987,
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#TT229955"}
@inproceedings{bb234988,
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#TT229956"}
@inproceedings{bb234989,
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#TT229957"}
@inproceedings{bb234990,
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#TT229958"}
@inproceedings{bb234991,
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#TT229959"}
@inproceedings{bb234992,
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#TT229960"}
@inproceedings{bb234993,
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#TT229961"}
@inproceedings{bb234994,
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#TT229962"}
@inproceedings{bb234995,
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#TT229963"}
@inproceedings{bb234996,
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#TT229964"}
@inproceedings{bb234997,
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#TT229965"}
@inproceedings{bb234998,
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#TT229966"}
@inproceedings{bb234999,
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#TT229967"}
Last update:Nov 2, 2025 at 14:03:07