@article{bb212700, AUTHOR = "Barra, S. and Bisogni, C. and de Marsico, M. and Ricciardi, S.", TITLE = "Visual question answering: Which investigated applications?", JOURNAL = PRL, VOLUME = "151", YEAR = "2021", PAGES = "325-331", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207776"} @article{bb212701, AUTHOR = "Manmadhan, S. and Kovoor, B.C.", TITLE = "Multi-Tier Attention Network using Term-weighted Question Features for Visual Question Answering", JOURNAL = IVC, VOLUME = "115", YEAR = "2021", PAGES = "104291", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207777"} @article{bb212702, AUTHOR = "Liu, A.A. and Lu, Z. and Xu, N. and Nie, W.Z. and Li, W.H.", TITLE = "Multi-type decision fusion network for visual Q&A", JOURNAL = IVC, VOLUME = "115", YEAR = "2021", PAGES = "104281", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207778"} @article{bb212703, AUTHOR = "Patro, B.N. and Kurmi, V.K. and Kumar, S. and Namboodiri, V.P.", TITLE = "MUMC: Minimizing uncertainty of mixture of cues", JOURNAL = IVC, VOLUME = "115", YEAR = "2021", PAGES = "104280", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207779"} @article{bb212704, AUTHOR = "Liu, F. and Liu, J. and Fang, Z.W. and Hong, R.C. and Lu, H.Q.", TITLE = "Visual Question Answering With Dense Inter- and Intra-Modality Interactions", JOURNAL = MultMed, VOLUME = "23", YEAR = "2021", PAGES = "3518-3529", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207780"} @article{bb212705, AUTHOR = "Wu, J.J. and Du, J. and Wang, F. and Yang, C. and Jiang, X.Z. and Hu, J. and Yin, B. and Zhang, J.S. and Dai, L.R.", TITLE = "A multimodal attention fusion network with a dynamic vocabulary for TextVQA", JOURNAL = PR, VOLUME = "122", YEAR = "2022", PAGES = "108214", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207781"} @article{bb212706, AUTHOR = "Narayanan, A. and Rao, A. and Prasad, A. and Natarajan, S.", TITLE = "VQA as a factoid question answering problem: A novel approach for knowledge-aware and explainable visual question answering", JOURNAL = IVC, VOLUME = "116", YEAR = "2021", PAGES = "104328", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207782"} @article{bb212707, AUTHOR = "Guo, Y.Y. and Nie, L.Q. and Cheng, Z.Y. and Tian, Q. and Zhang, M.", TITLE = "Loss Re-Scaling VQA: Revisiting the Language Prior Problem From a Class-Imbalance View", JOURNAL = IP, VOLUME = "31", YEAR = "2022", PAGES = "227-238", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207783"} @article{bb212708, AUTHOR = "Peng, L. and Yang, Y. and Wang, Z. and Huang, Z. and Shen, H.T.", TITLE = "MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network", JOURNAL = PAMI, VOLUME = "44", YEAR = "2022", NUMBER = "1", MONTH = "January", PAGES = "318-329", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207784"} @article{bb212709, AUTHOR = "Manogaran, G. and Shakeel, P.M. and Burhanuddin, M.A. and Baskar, S. and Saravanan, V. and Crespo, R.G. and Martinez, O.S.", TITLE = "ADCCF: Adaptive deep concatenation coder framework for visual question answering", JOURNAL = PRL, VOLUME = "152", YEAR = "2021", PAGES = "348-355", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207785"} @article{bb212710, AUTHOR = "Zhou, Y. and Ji, R.R. and Sun, X.S. and Su, J.S. and Meng, D.Y. and Gao, Y. and Shen, C.H.", TITLE = "Plenty is Plague: Fine-Grained Learning for Visual Question Answering", JOURNAL = PAMI, VOLUME = "44", YEAR = "2022", NUMBER = "2", MONTH = "February", PAGES = "697-709", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207786"} @article{bb212711, AUTHOR = "E, W.N. and Zhou, Y.J.", TITLE = "A Mathematical Model for Universal Semantics", JOURNAL = PAMI, VOLUME = "44", YEAR = "2022", NUMBER = "3", MONTH = "March", PAGES = "1124-1132", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207787"} @article{bb212712, AUTHOR = "Li, X.P. and Wu, B. and Song, J.K. and Gao, L.L. and Zeng, P.P. and Gan, C.", TITLE = "Text-instance graph: Exploring the relational semantics for text-based visual question answering", JOURNAL = PR, VOLUME = "124", YEAR = "2022", PAGES = "108455", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207788"} @article{bb212713, AUTHOR = "Shao, X.J. and Xiang, Z.L. and Li, Y.X.", TITLE = "Visual question answering with gated relation-aware auxiliary", JOURNAL = IET-IPR, VOLUME = "16", YEAR = "2022", NUMBER = "5", PAGES = "1424-1432", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207789"} @article{bb212714, 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#TT207790"} @article{bb212715, 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#TT207791"} @article{bb212716, AUTHOR = "Shuang, K. and Guo, J. and Wang, Z.", TITLE = "Comprehensive-perception dynamic reasoning for visual question answering", JOURNAL = PR, VOLUME = "131", YEAR = "2022", PAGES = "108878", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207792"} @article{bb212717, 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#TT207793"} @article{bb212718, 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#TT207794"} @article{bb212719, AUTHOR = "Xie, J.Y. and Fang, W.H. and Cai, Y. and Huang, Q.B. and Li, Q.", TITLE = "Knowledge-Based Visual Question Generation", JOURNAL = CirSysVideo, VOLUME = "32", YEAR = "2022", NUMBER = "11", MONTH = "November", PAGES = "7547-7558", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207795"} @article{bb212720, AUTHOR = "Gao, C.Y. and Zhu, Q. and Wang, P. and Li, H. and Liu, Y.L. and van den Hengel, A.J. and Wu, Q.", TITLE = "Structured Multimodal Attentions for TextVQA", JOURNAL = PAMI, VOLUME = "44", YEAR = "2022", NUMBER = "12", MONTH = "December", PAGES = "9603-9614", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207796"} @article{bb212721, 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#TT207797"} @article{bb212722, 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#TT207798"} @article{bb212723, 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#TT207799"} @article{bb212724, AUTHOR = "Zeng, G. 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#TT207800"} @article{bb212725, 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#TT207801"} @article{bb212726, AUTHOR = "Xu, F.Z. and Lin, Q. and Liu, J. and Zhang, L.L. and Zhao, T.Z. and Chai, Q. and Pan, Y. and Huang, Y. and Wang, Q.", TITLE = "MoCA: Incorporating domain pretraining and cross attention for textbook question answering", JOURNAL = PR, VOLUME = "140", YEAR = "2023", PAGES = "109588", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207802"} @article{bb212727, AUTHOR = "Li, P. and Tan, Z. 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#TT207803"} @article{bb212728, 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#TT207804"} @article{bb212729, 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#TT207805"} @article{bb212730, 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#TT207806"} @article{bb212731, 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#TT207807"} @article{bb212732, 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#TT207808"} @article{bb212733, AUTHOR = "Yang, X.F. and Lv, F. 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#TT207809"} @article{bb212734, 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#TT207810"} @inproceedings{bb212735, 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#TT207811"} @article{bb212736, 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#TT207812"} @article{bb212737, 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#TT207813"} @article{bb212738, 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#TT207814"} @inproceedings{bb212739, 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#TT207815"} @article{bb212740, AUTHOR = "Mohamud, S.A.M. and Jalali, A. and Lee, M.H.", TITLE = "Encoder-decoder cycle for visual question answering based on perception-action cycle", JOURNAL = PR, VOLUME = "144", YEAR = "2023", PAGES = "109848", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207816"} @article{bb212741, AUTHOR = "Tito, R. and Karatzas, D. and Valveny, E.", TITLE = "Hierarchical multimodal transformers for Multipage DocVQA", JOURNAL = PR, VOLUME = "144", YEAR = "2023", PAGES = "109834", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207817"} @article{bb212742, 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#TT207818"} @article{bb212743, 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#TT207819"} @article{bb212744, 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#TT207820"} @article{bb212745, 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#TT207821"} @article{bb212746, 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#TT207822"} @article{bb212747, AUTHOR = "Biswas, K. and Shivakumara, P. and Pal, U. and Liu, C.L. and Lu, Y.", TITLE = "VQAPT: A New visual question answering model for personality traits in social media images", JOURNAL = PRL, VOLUME = "175", YEAR = "2023", PAGES = "66-73", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207823"} @article{bb212748, AUTHOR = "Cho, J.W. and Argaw, D.M. and Oh, Y. and Kim, D.J. and Kweon, I.S.", TITLE = "Empirical study on using adapters for debiased Visual Question Answering", JOURNAL = CVIU, VOLUME = "237", YEAR = "2023", PAGES = "103842", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207824"} @inproceedings{bb212749, AUTHOR = "Cho, J.W. and Kim, D.J. and Choi, J. and Jung, Y. and Kweon, I.S.", TITLE = "Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation", BOOKTITLE = MULA21, YEAR = "2021", PAGES = "1592-1601", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207825"} @inproceedings{bb212750, AUTHOR = "Cho, J.W. and Kim, D.J. and Ryu, H. and Kweon, I.S.", TITLE = "Generative Bias for Robust Visual Question Answering", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "11681-11690", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207826"} @article{bb212751, 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#TT207827"} @article{bb212752, 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#TT207828"} @article{bb212753, 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#TT207829"} @article{bb212754, AUTHOR = "Cao, B.W. and Cao, J.X. and Gui, J. and Shen, J. 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#TT207830"} @article{bb212755, AUTHOR = "Mashrur, A. and Luo, W. and Zaidi, N.A. and Robles Kelly, A.", TITLE = "Robust visual question answering via semantic cross modal augmentation", JOURNAL = CVIU, VOLUME = "238", YEAR = "2024", PAGES = "103862", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207831"} @article{bb212756, 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#TT207832"} @article{bb212757, AUTHOR = "Yao, H.B. and Wang, L.P. and Cai, C.T. and Sun, Y.X. and Zhang, Z. and Luo, Y.K.", TITLE = "Multi-modal spatial relational attention networks for visual question answering", JOURNAL = IVC, VOLUME = "140", YEAR = "2023", PAGES = "104840", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207833"} @article{bb212758, 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#TT207834"} @article{bb212759, AUTHOR = "Zheng, W.B. and Yan, L. and Wang, F.Y.", TITLE = "So Many Heads, So Many Wits: Multimodal Graph Reasoning for Text-Based Visual Question Answering", JOURNAL = SMCS, VOLUME = "54", YEAR = "2024", NUMBER = "2", MONTH = "February", PAGES = "854-865", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207835"} @article{bb212760, AUTHOR = "Bi, Y.D. and Jiang, H. and Hu, Y.L. and Sun, Y.F. and Yin, B.C.", TITLE = "See and Learn More: Dense Caption-Aware Representation for Visual Question Answering", JOURNAL = CirSysVideo, VOLUME = "34", YEAR = "2024", NUMBER = "2", MONTH = "February", PAGES = "1135-1146", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207836"} @article{bb212761, AUTHOR = "Song, Y. and Yang, X.S. and Wang, Y. 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#TT207837"} @article{bb212762, AUTHOR = "Wu, S. and Zhao, G. 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#TT207838"} @article{bb212763, 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#TT207839"} @article{bb212764, 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#TT207840"} @article{bb212765, AUTHOR = "Jiang, J.J. and Liu, Z.Y. and Zheng, N.N.", TITLE = "Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering", JOURNAL = IJCV, VOLUME = "132", YEAR = "2024", NUMBER = "1", MONTH = "January", PAGES = "185-207", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207841"} @article{bb212766, AUTHOR = "Xu, N. and Lu, Z. and Tian, H. and Kang, R. 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#TT207842"} @article{bb212767, 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#TT207843"} @article{bb212768, AUTHOR = "Zhang, S. and Chen, Y. and Sun, Y. and Wang, F. and Shi, H.B. and Wang, H.R.", TITLE = "LOIS: Looking Out of Instance Semantics for Visual Question Answering", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "6202-6214", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207844"} @article{bb212769, AUTHOR = "Xie, J.Y. and Cai, Y. and Chen, J.L. and Xu, R. and Wang, J. and Li, Q.", TITLE = "Knowledge-Augmented Visual Question Answering With Natural Language Explanation", JOURNAL = IP, VOLUME = "33", YEAR = "2024", PAGES = "2652-2664", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207845"} @article{bb212770, AUTHOR = "Hu, Z.J. and Yang, P. and Jiang, Y.S. and Bai, Z.J.", TITLE = "Prompting large language model with context and pre-answer for knowledge-based VQA", JOURNAL = PR, VOLUME = "151", YEAR = "2024", PAGES = "110399", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207846"} @article{bb212771, 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#TT207847"} @article{bb212772, 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#TT207848"} @inproceedings{bb212773, 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#TT207849"} @inproceedings{bb212774, 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#TT207850"} @inproceedings{bb212775, AUTHOR = "Reichman, B. and Heck, L.", TITLE = "Cross-Modal Dense Passage Retrieval for Outside Knowledge Visual Question Answering", BOOKTITLE = CLVL23, YEAR = "2023", PAGES = "2829-2834", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207851"} @inproceedings{bb212776, 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#TT207852"} @inproceedings{bb212777, 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#TT207853"} @inproceedings{bb212778, 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#TT207854"} @inproceedings{bb212779, 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#TT207855"} @inproceedings{bb212780, 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#TT207856"} @inproceedings{bb212781, AUTHOR = "Qian, Z. and Wang, X. and Duan, X.G. and Qin, P. and Li, Y.H. and Zhu, W.W.", TITLE = "Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "2941-2950", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207857"} @inproceedings{bb212782, 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#TT207858"} @inproceedings{bb212783, 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#TT207859"} @inproceedings{bb212784, 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#TT207860"} @inproceedings{bb212785, AUTHOR = "Wu, Z.H. and Shu, X. and Yan, S. 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#TT207861"} @inproceedings{bb212786, 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#TT207862"} @inproceedings{bb212787, 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#TT207863"} @inproceedings{bb212788, 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#TT207864"} @inproceedings{bb212789, 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#TT207865"} @inproceedings{bb212790, 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#TT207866"} @inproceedings{bb212791, 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#TT207867"} @inproceedings{bb212792, 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#TT207868"} @inproceedings{bb212793, 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#TT207869"} @inproceedings{bb212794, AUTHOR = "Shao, Z.W. and Yu, Z. and Wang, M. and Yu, J.", TITLE = "Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "14974-14983", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207870"} @inproceedings{bb212795, 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#TT207871"} @inproceedings{bb212796, 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#TT207872"} @inproceedings{bb212797, AUTHOR = "Guo, J.X. and Li, J. and Li, D.X. and Tiong, A.M.H. and Li, B.Y. and Tao, D.C. and Hoi, S.", TITLE = "From Images to Textual Prompts: Zero-shot Visual Question Answering with Frozen Large Language Models", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "10867-10877", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207873"} @inproceedings{bb212798, 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#TT207874"} @inproceedings{bb212799, AUTHOR = "Li, B.J. and Wang, J. and Zhao, M. and Zhou, S.", TITLE = "Two-stage Multimodality Fusion for High-performance Text-based Visual Question Answering", BOOKTITLE = ACCV22, YEAR = "2022", PAGES = "IV:658-674", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207875"}