@article{bb247000,
AUTHOR = "Liu, Y. and Zhang, X.M. and Zhao, Z.Y. and Zhang, B. and Cheng, L. and Li, Z.J.",
TITLE = "ALSA: Adversarial Learning of Supervised Attentions for Visual
Question Answering",
JOURNAL = Cyber,
VOLUME = "52",
YEAR = "2022",
NUMBER = "6",
MONTH = "June",
PAGES = "4520-4533",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241889"}
@article{bb247001,
AUTHOR = "Ouyang, N.L. and Huang, Q.B. and Li, P.J. and Cai, Y. and Liu, B. and Leung, H.F. and Li, Q.",
TITLE = "Suppressing Biased Samples for Robust VQA",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "3405-3415",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241890"}
@article{bb247002,
AUTHOR = "Gouthaman, K.V. and Mittal, A.",
TITLE = "On the role of question encoder sequence model in robust visual
question answering",
JOURNAL = PR,
VOLUME = "131",
YEAR = "2022",
PAGES = "108883",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241891"}
@article{bb247003,
AUTHOR = "Chen, C.Q. and Han, D.Z. and Chang, C.C.",
TITLE = "CAAN: Context-Aware attention network for visual question answering",
JOURNAL = PR,
VOLUME = "132",
YEAR = "2022",
PAGES = "108980",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241892"}
@article{bb247004,
AUTHOR = "Jin, Z.X. and Wu, H. and Yang, C. and Zhou, F. and Qin, J.Y. and Xiao, L. and Yin, X.C.",
TITLE = "RUArt: A Novel Text-Centered Solution for Text-Based Visual Question
Answering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "1-12",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241893"}
@article{bb247005,
AUTHOR = "Beckham, C. and Weiss, M. and Golemo, F. and Honari, S. and Nowrouzezahrai, D. and Pal, C.",
TITLE = "Visual question answering from another perspective: CLEVR mental
rotation tests",
JOURNAL = PR,
VOLUME = "136",
YEAR = "2023",
PAGES = "109209",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241894"}
@article{bb247006,
AUTHOR = "Zhang, H.N. and Zeng, P.P. and Hu, Y.X. and Qian, J. and Song, J.K. and Gao, L.",
TITLE = "Learning visual question answering on controlled semantic noisy
labels",
JOURNAL = PR,
VOLUME = "138",
YEAR = "2023",
PAGES = "109339",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241895"}
@article{bb247007,
AUTHOR = "Zeng, G.Y. and Zhang, Y. and Zhou, Y. and Yang, X.M. and Jiang, N. and Zhao, G.Q. and Wang, W.P. and Yin, X.C.",
TITLE = "Beyond OCR + VQA: Towards end-to-end reading and reasoning for robust
and accurate textvqa",
JOURNAL = PR,
VOLUME = "138",
YEAR = "2023",
PAGES = "109337",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241896"}
@article{bb247008,
AUTHOR = "Gao, D.F. and Wang, R.P. and Shan, S.G. and Chen, X.L.",
TITLE = "CRIC: A VQA Dataset for Compositional Reasoning on Vision and
Commonsense",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "5",
MONTH = "May",
PAGES = "5561-5578",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241897"}
@article{bb247009,
AUTHOR = "Li, P.J. and Tan, Z.Y. and Bao, B.K.",
TITLE = "Multiview Language Bias Reduction for Visual Question Answering",
JOURNAL = MultMedMag,
VOLUME = "30",
YEAR = "2023",
NUMBER = "1",
MONTH = "January",
PAGES = "91-99",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241898"}
@article{bb247010,
AUTHOR = "Li, H.M. and Han, D.Z. and Chen, C.Q. and Chang, C.C. and Li, K.C. and Li, D.",
TITLE = "A Visual Question Answering Network Merging High- and Low-Level
Semantic Information",
JOURNAL = IEICE,
VOLUME = "E106-D",
YEAR = "2023",
NUMBER = "5",
MONTH = "May",
PAGES = "581-589",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241899"}
@article{bb247011,
AUTHOR = "Liu, B. and Zhan, L.M. and Xu, L. and Wu, X.M.",
TITLE = "Medical Visual Question Answering via Conditional Reasoning and
Contrastive Learning",
JOURNAL = MedImg,
VOLUME = "42",
YEAR = "2023",
NUMBER = "5",
MONTH = "May",
PAGES = "1532-1545",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241900"}
@article{bb247012,
AUTHOR = "Wu, J.M. and Ge, F. and Hong, H.Y. and Shi, Y. and Hao, Y.B. and Ma, L.",
TITLE = "Question-aware dynamic scene graph of local semantic representation
learning for visual question answering",
JOURNAL = PRL,
VOLUME = "170",
YEAR = "2023",
PAGES = "93-99",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241901"}
@article{bb247013,
AUTHOR = "Li, H. and Huang, J. and Jin, P. and Song, G. and Wu, Q. and Chen, J.",
TITLE = "Weakly-Supervised 3D Spatial Reasoning for Text-Based Visual Question
Answering",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "3367-3382",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241902"}
@article{bb247014,
AUTHOR = "Li, Z.Y. and Guo, Y.Y. and Wang, K. and Wei, Y.W. and Nie, L.Q. and Kankanhalli, M.",
TITLE = "Joint Answering and Explanation for Visual Commonsense Reasoning",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "3836-3846",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241903"}
@article{bb247015,
AUTHOR = "Yang, X.F. and Lv, F.M. and Liu, F. and Lin, G.S.",
TITLE = "Self-Training Vision Language BERTs With a Unified Conditional Model",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "8",
MONTH = "August",
PAGES = "3560-3569",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241904"}
@article{bb247016,
AUTHOR = "Chen, L. and Zheng, Y.H. and Niu, Y. and Zhang, H.W. and Xiao, J.",
TITLE = "Counterfactual Samples Synthesizing and Training for Robust Visual
Question Answering",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "11",
MONTH = "November",
PAGES = "13218-13234",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241905"}
@inproceedings{bb247017,
AUTHOR = "Chen, L. and Yan, X. and Xiao, J. and Zhang, H.W. and Pu, S. and Zhuang, Y.",
TITLE = "Counterfactual Samples Synthesizing for Robust Visual Question
Answering",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10797-10806",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241906"}
@article{bb247018,
AUTHOR = "Wang, B.Y. and Ma, Y.J. and Li, X.Y. and Liu, H. and Hu, Y.L. and Yin, B.C.",
TITLE = "DSGEM: Dual scene graph enhancement module-based visual question
answering",
JOURNAL = IET-CV,
VOLUME = "17",
YEAR = "2023",
NUMBER = "6",
PAGES = "638-651",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241907"}
@article{bb247019,
AUTHOR = "Bi, Y.D. and Jiang, H. and Zhang, H. and Hu, Y.L. and Yin, B.C.",
TITLE = "Self-supervised knowledge distillation in counterfactual learning for
VQA",
JOURNAL = PRL,
VOLUME = "177",
YEAR = "2024",
PAGES = "33-39",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241908"}
@article{bb247020,
AUTHOR = "Tan, S. and Ge, M.M. and Guo, D. and Liu, H.P. and Sun, F.C.",
TITLE = "Knowledge-Based Embodied Question Answering",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "11948-11960",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241909"}
@inproceedings{bb247021,
AUTHOR = "Tan, S. and Xiang, W.L. and Liu, H.P. and Guo, D. and Sun, F.C.",
TITLE = "Multi-agent Embodied Question Answering in Interactive Environments",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XIII:663-678",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241910"}
@article{bb247022,
AUTHOR = "Wang, Y.X. and Wei, B. and Liu, J. and Zhang, L.L. and Wang, J.X. and Wang, Q.Y.",
TITLE = "DisAVR: Disentangled Adaptive Visual Reasoning Network for Diagram
Question Answering",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "4812-4827",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241911"}
@article{bb247023,
AUTHOR = "Han, Y.D. and Yin, J.H. and Wu, J.L. and Wei, Y.W. and Nie, L.Q.",
TITLE = "Semantic-Aware Modular Capsule Routing for Visual Question Answering",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "5537-5549",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241912"}
@article{bb247024,
AUTHOR = "Qian, T.W. and Chen, J.J. and Chen, S.X. and Wu, B. and Jiang, Y.G.",
TITLE = "Scene Graph Refinement Network for Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "3950-3961",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241913"}
@article{bb247025,
AUTHOR = "Qin, B.S. and Hu, H.J. and Zhuang, Y.T.",
TITLE = "Deep Residual Weight-Sharing Attention Network With Low-Rank
Attention for Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "4282-4295",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241914"}
@article{bb247026,
AUTHOR = "Zhou, S. and Guo, D. and Li, J. and Yang, X. and Wang, M.",
TITLE = "Exploring Sparse Spatial Relation in Graph Inference for Text-Based
VQA",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "5060-5074",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241915"}
@article{bb247027,
AUTHOR = "Liu, Y.H. and Wei, W. and Peng, D. and Mao, X.L. and He, Z.Y. and Zhou, P.",
TITLE = "Depth-Aware and Semantic Guided Relational Attention Network for
Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "5344-5357",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241916"}
@article{bb247028,
AUTHOR = "Mao, A. and Yang, Z. and Lin, K. and Xuan, J. and Liu, Y.J.",
TITLE = "Positional Attention Guided Transformer-Like Architecture for Visual
Question Answering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "6997-7009",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241917"}
@article{bb247029,
AUTHOR = "Sun, H. and Wang, S. and Zhu, Y.Q. and Yuan, W. and Zou, Z.Q.",
TITLE = "Question Classification for Intelligent Question Answering:
A Comprehensive Survey",
JOURNAL = IJGI,
VOLUME = "12",
YEAR = "2023",
NUMBER = "10",
PAGES = "415",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241918"}
@article{bb247030,
AUTHOR = "Cao, B.W. and Cao, J.X. and Gui, J. and Shen, J.Y. and Liu, B. and He, L. and Tang, Y.Y. and Kwok, J.T.Y.",
TITLE = "AlignVE: Visual Entailment Recognition Based on Alignment Relations",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "7378-7387",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241919"}
@article{bb247031,
AUTHOR = "Yu, Z. and Jin, Z. and Yu, J. and Xu, M.L. and Wang, H.B. and Fan, J.P.",
TITLE = "Bilaterally Slimmable Transformer for Elastic and Efficient Visual
Question Answering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "9543-9556",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241920"}
@article{bb247032,
AUTHOR = "Huang, X.F. and Gong, H.F.",
TITLE = "A Dual-Attention Learning Network With Word and Sentence Embedding
for Medical Visual Question Answering",
JOURNAL = MedImg,
VOLUME = "43",
YEAR = "2024",
NUMBER = "2",
MONTH = "February",
PAGES = "832-845",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241921"}
@article{bb247033,
AUTHOR = "Song, Y.G. and Yang, X.S. and Wang, Y.W. and Xu, C.S.",
TITLE = "Recovering Generalization via Pre-Training-Like Knowledge
Distillation for Out-of-Distribution Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "837-851",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241922"}
@article{bb247034,
AUTHOR = "Wu, S. and Zhao, G.S. and Qian, X.M.",
TITLE = "Resolving Zero-Shot and Fact-Based Visual Question Answering via
Enhanced Fact Retrieval",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "1790-1800",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241923"}
@article{bb247035,
AUTHOR = "Wen, Z.Q. and Niu, S.C. and Li, G. and Wu, Q.Y. and Tan, M.K. and Wu, Q.",
TITLE = "Test-Time Model Adaptation for Visual Question Answering With
Debiased Self-Supervisions",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "2137-2147",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241924"}
@article{bb247036,
AUTHOR = "Huai, T.Y. and Yang, S.W. and Zhang, J.H. and Zhao, J.B. and He, L.",
TITLE = "Debiased Visual Question Answering via the perspective of question
types",
JOURNAL = PRL,
VOLUME = "178",
YEAR = "2024",
PAGES = "181-187",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241925"}
@article{bb247037,
AUTHOR = "Xu, N. and Lu, Z. and Tian, H.S. and Kang, R.B. and Cao, J. and Zhang, Y.D. and Liu, A.A.",
TITLE = "Learning to Supervise Knowledge Retrieval Over a Tree Structure for
Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "6689-6700",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241926"}
@article{bb247038,
AUTHOR = "Pan, Y.H. and Liu, J. and Jin, L. and Li, Z.C.",
TITLE = "Unbiased Visual Question Answering by Leveraging Instrumental
Variable",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "6648-6662",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241927"}
@article{bb247039,
AUTHOR = "Wang, Q. and Liu, J. and Wu, W.J.",
TITLE = "Coordinating explicit and implicit knowledge for knowledge-based VQA",
JOURNAL = PR,
VOLUME = "151",
YEAR = "2024",
PAGES = "110368",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241928"}
@article{bb247040,
AUTHOR = "Wei, M. and Chen, L. and Ji, W. and Yue, X.Y. and Zimmermann, R.",
TITLE = "In Defense of Clip-Based Video Relation Detection",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "2759-2769",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241929"}
@article{bb247041,
AUTHOR = "Ma, J. and Liu, J. and Chai, Q. and Wang, P.H. and Tao, J.",
TITLE = "Diagram Perception Networks for Textbook Question Answering via Joint
Optimization",
JOURNAL = IJCV,
VOLUME = "132",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "1578-1591",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241930"}
@article{bb247042,
AUTHOR = "Li, L.J. and Jin, T. and Lin, W. and Jiang, H. and Pan, W.W. and Wang, J. and Xiao, S.W. and Xia, Y. and Jiang, W.H. and Zhao, Z.",
TITLE = "Multi-Granularity Relational Attention Network for Audio-Visual
Question Answering",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "8",
MONTH = "August",
PAGES = "7080-7094",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241931"}
@article{bb247043,
AUTHOR = "Bi, Y.D. and Jiang, H.J. and Hu, Y.L. and Sun, Y.F. and Yin, B.C.",
TITLE = "Fair Attention Network for Robust Visual Question Answering",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "9",
MONTH = "September",
PAGES = "7870-7881",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241932"}
@article{bb247044,
AUTHOR = "Xue, D. and Qian, S.S. and Xu, C.S.",
TITLE = "Integrating Neural-Symbolic Reasoning With Variational Causal
Inference Network for Explanatory Visual Question Answering",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "7893-7908",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241933"}
@inproceedings{bb247045,
AUTHOR = "Xue, D. and Qian, S.S. and Xu, C.S.",
TITLE = "Variational Causal Inference Network for Explanatory Visual Question
Answering",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2515-2525",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241934"}
@article{bb247046,
AUTHOR = "Xue, D. and Qian, S.S. and Fang, Q. and Xu, C.S.",
TITLE = "LININ: Logic Integrated Neural Inference Network for Explanatory
Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "16-27",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241935"}
@article{bb247047,
AUTHOR = "Shen, K. and Wu, L.F. and Tang, S.L. and Xu, F.L. and Long, B. and Zhuang, Y.T. and Pei, J.",
TITLE = "Ask Questions With Double Hints: Visual Question Generation With
Answer-Awareness and Region-Reference",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "9648-9660",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241936"}
@article{bb247048,
AUTHOR = "Yamada, M. and d'Amario, V. and Takemoto, K. and Boix, X. and Sasaki, T.",
TITLE = "Transformer Module Networks for Systematic Generalization in Visual
Question Answering",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "10096-10105",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241937"}
@article{bb247049,
AUTHOR = "Liu, J. and Xie, J.L. and Zhou, F.Y. and He, S.F.",
TITLE = "Question Type-Aware Debiasing for Test-Time Visual Question Answering
Model Adaptation",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "11",
MONTH = "November",
PAGES = "10805-10816",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241938"}
@article{bb247050,
AUTHOR = "Cao, R.L. and Li, Z.X. and Tang, Z.J. and Zhang, C.L. and Ma, H.F.",
TITLE = "Enhancing robust VQA via contrastive and self-supervised learning",
JOURNAL = PR,
VOLUME = "159",
YEAR = "2025",
PAGES = "111129",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241939"}
@article{bb247051,
AUTHOR = "Liu, F. and Dai, W.W. and Zhang, C.Y. and Zhu, J. and Yao, L. and Li, X.",
TITLE = "Co-LLaVA: Efficient Remote Sensing Visual Question Answering via
Model Collaboration",
JOURNAL = RS,
VOLUME = "17",
YEAR = "2025",
NUMBER = "3",
PAGES = "466",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241940"}
@article{bb247052,
AUTHOR = "Gao, Y.Q. and Bai, Z.W. and Zhou, M.L. and Jia, B.L. and Gao, P.Q. and Zhu, R.",
TITLE = "Adaptive Conditional Reasoning for Remote Sensing Visual Question
Answering",
JOURNAL = RS,
VOLUME = "17",
YEAR = "2025",
NUMBER = "8",
PAGES = "1338",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241941"}
@article{bb247053,
AUTHOR = "Lan, N. and Ou, B.S. and Xie, X.M. and Shi, G.M.",
TITLE = "Visual Environment-Interactive Planning for Embodied Complex-Question
Answering",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "6481-6493",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241942"}
@article{bb247054,
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#TT241943"}
@article{bb247055,
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#TT241944"}
@article{bb247056,
AUTHOR = "Zhao, Z.C. and Zhou, C.F. and Zhang, Y. and Li, C.L. and Ma, X.L. and Tang, J.",
TITLE = "Text-Guided Coarse-to-Fine Fusion Network for robust remote sensing
visual question answering",
JOURNAL = PandRS,
VOLUME = "230",
YEAR = "2025",
PAGES = "1-17",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241945"}
@article{bb247057,
AUTHOR = "Lu, Z.L. and Zeng, Q.J. and Lu, M.K. and Chen, G. and Xia, Y.",
TITLE = "Bridging the Semantic Gap in Medical Visual Question Answering with
Prompt Learning",
JOURNAL = MedImg,
VOLUME = "44",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "4605-4616",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241946"}
@article{bb247058,
AUTHOR = "Du, Z. and Yuan, Z.Q. and Wu, X. and Xu, C.S.",
TITLE = "Disentanglement-Based Equivariant Learning for Compositional VQA",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "8160-8173",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241947"}
@article{bb247059,
AUTHOR = "Jin, Z.X. and Qin, P. and Lin, S. and Qin, J. and Zhai, S.J. and Zeng, J.C. and Yin, X.C.",
TITLE = "Robust scene text understanding with OCR token and word alignment for
Text-VQA and text-caption",
JOURNAL = PR,
VOLUME = "172",
YEAR = "2026",
PAGES = "112362",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241948"}
@article{bb247060,
AUTHOR = "Mao, A. and Wen, S.Y. and Chen, F. and Yi, R. and Liu, Y.J.",
TITLE = "Robust 3D Visual Question Answering via Bias Learning",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "12",
MONTH = "December",
PAGES = "12492-12507",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241949"}
@article{bb247061,
AUTHOR = "Liu, J. and Zhang, L.Z. and Mu, C. and Lu, G.X. and Zhang, B. and Li, J.S.",
TITLE = "Question-Guided Multigranular Visual Augmentation for Knowledge-Based
Visual Question Answering",
JOURNAL = CVIU,
VOLUME = "263",
YEAR = "2026",
PAGES = "104569",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241950"}
@article{bb247062,
AUTHOR = "Zhang, X.Y. and Zhang, L.L. and Wu, Y.R. and Wang, S.W. and Wu, W.J. and Huang, M. and Wang, Q.Y. and Liu, J.",
TITLE = "Memory-enriched thought-by-thought framework for complex Diagram
Question Answering",
JOURNAL = CVIU,
VOLUME = "264",
YEAR = "2026",
PAGES = "104608",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241951"}
@article{bb247063,
AUTHOR = "Chen, T.Y. and Liu, H.B. and Wang, Y. and Chen, Y.H. and He, T.Y. and Gan, C.F. and He, H.Y. and Lin, W.Y.",
TITLE = "MECD+: Unlocking Event-Level Causal Graph Discovery for Video
Reasoning",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "2628-2645",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241952"}
@article{bb247064,
AUTHOR = "Liang, J.F. and Jiang, S.X. and Tang, W. and Wang, N. and Wang, Z.K. and Mao, X. and Lv, K. and Liu, M. and Qin, B.",
TITLE = "APSam: An Aggregating-Then-Pruning Sampler for Question-Conditional
Denoising",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "1754-1765",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241953"}
@article{bb247065,
AUTHOR = "Wang, F.J. and Liu, J.Y. and Zhang, R.N. and Li, Z.X. and Zhang, F. and An, G.Y.",
TITLE = "CKCR: Context-aware knowledge construction and retrieval for
knowledge-based visual question answering",
JOURNAL = JVCIR,
VOLUME = "116",
YEAR = "2026",
PAGES = "104711",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241954"}
@article{bb247066,
AUTHOR = "Lu, J.H. and You, S. and Bao, B.K.",
TITLE = "Question Understanding and Temporality Guiding for Video Question
Answering",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "2772-2783",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241955"}
@article{bb247067,
AUTHOR = "Li, Z.F. and Qiu, F. and Wang, Y.R. and Xia, Y.J. and Xiao, K. and Zhang, M. and Zhang, Y.",
TITLE = "Integrating Object Interaction Self-Attention and GAN-Based Debiasing
for Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "3228-3241",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241956"}
@article{bb247068,
AUTHOR = "Xu, Q.X. and Zhou, L. and Zhong, X. and Zhang, F.F. and Tian, J. and Yu, X.H. and Huang, R.",
TITLE = "Refined generation-based framework for consistent and reliable visual
question answering",
JOURNAL = PR,
VOLUME = "178",
YEAR = "2026",
PAGES = "113421",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241957"}
@article{bb247069,
AUTHOR = "Xu, P.F. and Yan, F.",
TITLE = "RSSR: Efficient knowledge transfer and deep spatial modeling for
remote sensing visual question answering",
JOURNAL = CVIU,
VOLUME = "268",
YEAR = "2026",
PAGES = "104753",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241958"}
@article{bb247070,
AUTHOR = "Zhu, L. and Ying, M.X. and Zhang, C.Y. and Liu, D. and Wu, L.Y.B. and Zhang, S.C. and Li, X.L.",
TITLE = "Multi-Modal Refined Prompting for Advancing Knowledge-Based Visual
Question Answering",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "3444-3457",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241959"}
@article{bb247071,
AUTHOR = "Suo, W. and Ma, J. and Sun, M.Y. and Zhang, H.W. and Wang, P. and Zhang, Y.N. and Wu, Q.",
TITLE = "Semi-Supervised VQA Multi-Modal Explanation via Self-Critical
Learning",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "7",
MONTH = "July",
PAGES = "8361-8377",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241960"}
@inproceedings{bb247072,
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#TT241961"}
@article{bb247073,
AUTHOR = "Fang, C.Y. and Wan, X. and Jiang, W.H. and Fang, Y.M. and Tang, Z.",
TITLE = "DSRAS: Dual-Stage Reasoning and Answer Selection for Video-Text
Visual Question Answering",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2270-2274",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241962"}
@article{bb247074,
AUTHOR = "Huang, Q. and He, P.H. and Li, P. and Lu, X.C. and Tian, Y. and Cai, Y. and Li, Q.",
TITLE = "Metaphorical Visual Question Answering: Benchmark and
Knowledge-Enhanced Metaphor Understanding Method",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "4904-4916",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241963"}
@article{bb247075,
AUTHOR = "Zhang, C.L. and Deng, J.Q. and Zhang, H. and Li, L.B. and Sun, L. and Ma, X.",
TITLE = "GeoIR-Compiler: A Geospatial Intermediate Representation and
Compilation Framework for Chinese Urban Spatial Question Answering",
JOURNAL = IJGI,
VOLUME = "15",
YEAR = "2026",
NUMBER = "7",
PAGES = "310",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241964"}
@inproceedings{bb247076,
AUTHOR = "Vardi, B. and Nir, O. and Shamir, A.",
TITLE = "CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual
Question Answering",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "5898-5908",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241965"}
@article{bb247077,
AUTHOR = "Zhang, L.X. and Huang, B.Q.",
TITLE = "Leveraging frequency information and feature disentanglement for
debiased Visual Question Answering",
JOURNAL = CVIU,
VOLUME = "271",
YEAR = "2026",
PAGES = "104880",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241966"}
@article{bb247078,
AUTHOR = "Wang, J. and Nian, X.D. and Li, Y. and Zhu, Y. and Wang, H.S. and Zheng, J.B. and Wang, Z.Y.",
TITLE = "RGS: A Unified Representation-Generation-Selection Framework for
Knowledge-Based Visual Question Answering",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "9503-9512",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241967"}
@article{bb247079,
AUTHOR = "Chang, J.M. and Zhang, Y.B. and Wang, K. and Jia, Z.H. and Ye, H.",
TITLE = "A consensus-aware visual question answering method for remote sensing
images",
JOURNAL = PRL,
VOLUME = "209",
YEAR = "2026",
PAGES = "160-165",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241968"}
@article{bb247080,
AUTHOR = "Almodovar, A. and Elizo, M. and Apellaniz, P.A. and Zazo, S. and Parras, J.",
TITLE = "Kolmogorov-Arnold Causal Generative Models",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "11",
MONTH = "November",
PAGES = "15301-15311",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241969"}
@inproceedings{bb247081,
AUTHOR = "Moradi, M.M. and Mudur, S.",
TITLE = "Crafting Descriptive Information for a Zero-shot Method to Improve
Knowledge-Based Visual Question Answering Performance",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "3120-3128",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241970"}
@inproceedings{bb247082,
AUTHOR = "Xue, J.T. and Zhao, G.N. and Yao, J.E. and Chen, H.E. and Hu, Y. and Chen, M. and You, S. and Kuo, C.C.J.",
TITLE = "Descrip3D: Enhancing Large Language Model-based 3D Scene
Understanding with Object-Level Text Descriptions",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "1746-1756",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241971"}
@inproceedings{bb247083,
AUTHOR = "Zhang, H.C. and Savaliya, N. and Siddiqui, F. and Sachdeva, E.",
TITLE = "FAST-EQA: Efficient Embodied Question Answering with Global and Local
Region Relevancy",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "1664-1673",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241972"}
@inproceedings{bb247084,
AUTHOR = "Ren, H.Y. and Chen, W. and Liu, C.P. and Ji, Y. and Li, Y.",
TITLE = "MedKI: Knowledge Dual Injections for Medical Visual Question
Answering",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "79-84",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241973"}
@inproceedings{bb247085,
AUTHOR = "Shah, K. and J, S. and Bhutani, G. and Singh, K. and Singh, S.",
TITLE = "Visual Prompting Through Image Mines",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "713-718",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241974"}
@inproceedings{bb247086,
AUTHOR = "He, Z.L. and Pan, Y.J. and Li, H. and Ma, F.P. and Peng, Y.S. and Wu, S.Y. and Sun, X.Y.",
TITLE = "Enhancing Visual Question Answering Via Clustered In-Context Sequence
Configuration",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "935-940",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241975"}
@inproceedings{bb247087,
AUTHOR = "Mijiyawa, A. and Sadat, F.",
TITLE = "Visual Question Answering Using Multimodal Data Augmentation for
Hausa",
BOOKTITLE = IVCNZ25,
YEAR = "2025",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241976"}
@inproceedings{bb247088,
AUTHOR = "Cheng, Y. and Goel, A. and Bilen, H.",
TITLE = "Visually Interpretable Subtask Reasoning for Visual Question
Answering",
BOOKTITLE = XAI4CV25,
YEAR = "2025",
PAGES = "2751-2771",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241977"}
@inproceedings{bb247089,
AUTHOR = "Jang, Y. and Kong, H. and Kim, G. and Lee, Y. and Choi, J. and Bae, K.",
TITLE = "ICT-QA: Question Answering Over Multi-Modal Contexts Including Image,
Chart, and Text Modalities",
BOOKTITLE = "MULA25",
YEAR = "2025",
PAGES = "138-148",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241978"}
@inproceedings{bb247090,
AUTHOR = "Li, K. and Vosselman, G. and Yang, M.Y.",
TITLE = "Multimodal Rationales for Explainable Visual Question Answering",
BOOKTITLE = "MULA25",
YEAR = "2025",
PAGES = "191-201",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241979"}
@inproceedings{bb247091,
AUTHOR = "Zou, Y.H. and Yin, Z.Z.",
TITLE = "MVCM: Enhancing Multi-View and Cross-Modality Alignment for Medical
Visual Question Answering and Medical Image-Text Retrieval",
BOOKTITLE = "MULA25",
YEAR = "2025",
PAGES = "180-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT241980"}
@inproceedings{bb247092,
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#TT241981"}
@inproceedings{bb247093,
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#TT241982"}
@inproceedings{bb247094,
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#TT241983"}
@inproceedings{bb247095,
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#TT241984"}
@inproceedings{bb247096,
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#TT241985"}
@inproceedings{bb247097,
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#TT241986"}
@inproceedings{bb247098,
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#TT241987"}
@inproceedings{bb247099,
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#TT241988"}
Last update: