@inproceedings{bb212800, 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#TT207876"} @inproceedings{bb212801, AUTHOR = "Chai, Z. and Wan, X.J. and Han, S.C. and Poon, J.", TITLE = "Visual Question Generation Under Multi-granularity Cross-Modal Interaction", BOOKTITLE = MMMod23, YEAR = "2023", PAGES = "I: 255-266", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207877"} @inproceedings{bb212802, AUTHOR = "Wang, J.H. and Hu, M.H. and Song, Y.G. and Yang, X.S.", TITLE = "Health-Oriented Multimodal Food Question Answering", BOOKTITLE = MMMod23, YEAR = "2023", PAGES = "I: 191-203", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207878"} @inproceedings{bb212803, 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#TT207879"} @inproceedings{bb212804, 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#TT207880"} @inproceedings{bb212805, 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#TT207881"} @inproceedings{bb212806, AUTHOR = "Uehara, K. and Harada, T.", TITLE = "K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition", BOOKTITLE = WACV23, YEAR = "2023", PAGES = "4390-4398", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207882"} @inproceedings{bb212807, 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#TT207883"} @inproceedings{bb212808, 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#TT207884"} @inproceedings{bb212809, AUTHOR = "Zhang, H.T. and Wu, W.", TITLE = "CAT: Re-Conv Attention in Transformer for Visual Question Answering", BOOKTITLE = "ICPR22", YEAR = "2022", PAGES = "1471-1477", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207885"} @inproceedings{bb212810, 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#TT207886"} @inproceedings{bb212811, 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#TT207887"} @inproceedings{bb212812, 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#TT207888"} @inproceedings{bb212813, 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#TT207889"} @inproceedings{bb212814, 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#TT207890"} @inproceedings{bb212815, 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#TT207891"} @inproceedings{bb212816, 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#TT207892"} @inproceedings{bb212817, 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#TT207893"} @inproceedings{bb212818, 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#TT207894"} @inproceedings{bb212819, 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#TT207895"} @inproceedings{bb212820, AUTHOR = "Li, G.Y. and Wei, Y. and Tian, Y. 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#TT207896"} @inproceedings{bb212821, AUTHOR = "Chen, C. 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#TT207897"} @inproceedings{bb212822, 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#TT207898"} @inproceedings{bb212823, 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#TT207899"} @inproceedings{bb212824, 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#TT207900"} @inproceedings{bb212825, 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#TT207901"} @inproceedings{bb212826, 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#TT207902"} @inproceedings{bb212827, 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#TT207903"} @inproceedings{bb212828, AUTHOR = "Dancette, C. and Cadene, R. and Teney, D. and Cord, M.", TITLE = "Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "1554-1563", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207904"} @inproceedings{bb212829, AUTHOR = "Zhou, Y. and Ren, T. 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#TT207905"} @inproceedings{bb212830, 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#TT207906"} @inproceedings{bb212831, 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#TT207907"} @inproceedings{bb212832, 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#TT207908"} @inproceedings{bb212833, 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#TT207909"} @inproceedings{bb212834, 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#TT207910"} @inproceedings{bb212835, 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#TT207911"} @inproceedings{bb212836, 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#TT207912"} @inproceedings{bb212837, AUTHOR = "Jung, S.J. and Byun, J. 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#TT207913"} @inproceedings{bb212838, AUTHOR = "Felix, R. and Repasky, B. and Hodge, S. and Zolfaghari, R. and Abbasnejad, E. and Sherrah, J.", TITLE = "Cross-Modal Visual Question Answering for Remote Sensing Data: the International Conference on Digital Image Computing: Techniques and Applications (DICTA 2021)", BOOKTITLE = DICTA21, YEAR = "2021", PAGES = "1-9", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207914"} @inproceedings{bb212839, 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#TT207915"} @inproceedings{bb212840, 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#TT207916"} @inproceedings{bb212841, AUTHOR = "Chen, H.Y. and Liu, R.F. and Peng, B.", TITLE = "Cross-modal Relational Reasoning Network for Visual Question Answering", BOOKTITLE = MAIR2-21, YEAR = "2021", PAGES = "3939-3948", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207917"} @inproceedings{bb212842, 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#TT207918"} @inproceedings{bb212843, 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#TT207919"} @inproceedings{bb212844, 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#TT207920"} @inproceedings{bb212845, 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#TT207921"} @inproceedings{bb212846, 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#TT207922"} @inproceedings{bb212847, 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#TT207923"} @inproceedings{bb212848, 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#TT207924"} @inproceedings{bb212849, 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#TT207925"} @inproceedings{bb212850, 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#TT207926"} @inproceedings{bb212851, 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#TT207927"} @inproceedings{bb212852, 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#TT207928"} @inproceedings{bb212853, 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#TT207929"} @inproceedings{bb212854, 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#TT207930"} @inproceedings{bb212855, 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#TT207931"} @inproceedings{bb212856, 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#TT207932"} @inproceedings{bb212857, AUTHOR = "Farazi, M. and Khan, S. and Barnes, N.M.", TITLE = "Question-Agnostic Attention for Visual Question Answering", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "3542-3549", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207933"} @inproceedings{bb212858, AUTHOR = "Li, Y. and Lin, Y. and Zhao, H.H. and Wang, D.H.", TITLE = "Dual Path Multi-Modal High-Order Features for Textual Content based Visual Question Answering", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "4324-4331", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207934"} @inproceedings{bb212859, 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#TT207935"} @inproceedings{bb212860, 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#TT207936"} @inproceedings{bb212861, AUTHOR = "Huang, H.T. and Han, T. and Han, W. and Yap, D. and Chiang, C.M.", TITLE = "Answer-checking in Context: A Multi-modal Fully Attention Network for Visual Question Answering", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "1173-1180", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207937"} @inproceedings{bb212862, 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#TT207938"} @inproceedings{bb212863, 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#TT207939"} @inproceedings{bb212864, 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#TT207940"} @inproceedings{bb212865, 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#TT207941"} @inproceedings{bb212866, 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#TT207942"} @inproceedings{bb212867, 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#TT207943"} @inproceedings{bb212868, 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#TT207944"} @inproceedings{bb212869, 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#TT207945"} @inproceedings{bb212870, AUTHOR = "Kant, Y. and Batra, D. and Anderson, P. and Schwing, A. and Parikh, D. and Lu, J. and Agrawal, H.", TITLE = "Spatially Aware Multimodal Transformers for TextVQA", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "IX:715-732", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207946"} @inproceedings{bb212871, 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#TT207947"} @inproceedings{bb212872, 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#TT207948"} @inproceedings{bb212873, 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#TT207949"} @inproceedings{bb212874, AUTHOR = "Jiang, H. and Misra, I. and Rohrbach, M. and Learned Miller, E.G. and Chen, X.", TITLE = "In Defense of Grid Features for Visual Question Answering", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "10264-10273", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207950"} @inproceedings{bb212875, AUTHOR = "Wang, X. and Liu, Y. and Shen, C. and Ng, C.C. and Luo, C. and Jin, L. and Chan, C.S. and van den Hengel, A. and Wang, L.", TITLE = "On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "10123-10132", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207951"} @inproceedings{bb212876, AUTHOR = "Xiong, P. and Wu, Y.", TITLE = "TA-Student VQA: Multi-Agents Training by Self-Questioning", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "10062-10072", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207952"} @inproceedings{bb212877, AUTHOR = "Agarwal, V. and Shetty, R. and Fritz, M.", TITLE = "Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "9687-9695", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207953"} @inproceedings{bb212878, AUTHOR = "Hu, R. and Singh, A. and Darrell, T.J. and Rohrbach, M.", TITLE = "Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "9989-9999", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207954"} @inproceedings{bb212879, AUTHOR = "Kafle, K. and Shrestha, R. and Price, B. and Cohen, S. and Kanan, C.", TITLE = "Answering Questions about Data Visualizations using Efficient Bimodal Fusion", BOOKTITLE = WACV20, YEAR = "2020", PAGES = "1487-1496", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207955"} @inproceedings{bb212880, AUTHOR = "Patro, B.N. and Patel, S. and Namboodiri, V.P.", TITLE = "Robust Explanations for Visual Question Answering", BOOKTITLE = WACV20, YEAR = "2020", PAGES = "1566-1575", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207956"} @inproceedings{bb212881, AUTHOR = "Chou, S. and Chao, W. and Lai, W. and Sun, M. and Yang, M.", TITLE = "Visual Question Answering on 360° Images", BOOKTITLE = WACV20, YEAR = "2020", PAGES = "1596-1605", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207957"} @inproceedings{bb212882, AUTHOR = "Chaudhry, R. and Shekhar, S. and Gupta, U. and Maneriker, P. and Bansal, P. and Joshi, A.", TITLE = "LEAF-QA: Locate, Encode Attend for Figure Question Answering", BOOKTITLE = WACV20, YEAR = "2020", PAGES = "3501-3510", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207958"} @inproceedings{bb212883, AUTHOR = "Liang, Y.Z. and Bai, Y.L. and Zhang, W. and Qian, X.M. and Zhu, L. and Mei, T.", TITLE = "VrR-VG: Refocusing Visually-Relevant Relationships", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "10402-10411", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207959"} @inproceedings{bb212884, AUTHOR = "Bhattacharya, N. and Li, Q. and Gurari, D.", TITLE = "Why Does a Visual Question Have Different Answers?", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "4270-4279", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207960"} @inproceedings{bb212885, AUTHOR = "Li, L.J. and Gan, Z. and Cheng, Y. and Liu, J.J.", TITLE = "Relation-Aware Graph Attention Network for Visual Question Answering", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "10312-10321", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207961"} @inproceedings{bb212886, AUTHOR = "Peng, G. and You, H.X. and Zhang, Z.P. and Wang, X.G. and Li, H.S.", TITLE = "Multi-Modality Latent Interaction Network for Visual Question Answering", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "5824-5834", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207962"} @inproceedings{bb212887, AUTHOR = "Do, T. and Tran, H. and Do, T. and Tjiputra, E. and Tran, Q.", TITLE = "Compact Trilinear Interaction for Visual Question Answering", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "392-401", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207963"} @inproceedings{bb212888, AUTHOR = "Schwartz, I. and Yu, S. and Hazan, T. and Schwing, A.G.", TITLE = "Factor Graph Attention", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "2039-2048", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207964"} @inproceedings{bb212889, AUTHOR = "Kolesnikov, A. and Beyer, L. and Zhai, X.H. and Puigcerver, J. and Yung, J. and Gelly, S. and Houlsby, N.", TITLE = "Big Transfer (BIT): General Visual Representation Learning", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "V:491-507", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207965"} @inproceedings{bb212890, AUTHOR = "Kolesnikov, A. and Zhai, X.H. and Beyer, L.", TITLE = "Revisiting Self-Supervised Visual Representation Learning", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "1920-1929", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207966"} @inproceedings{bb212891, AUTHOR = "Xiong, P.X. and Zhan, H.Y. and Wang, X. and Sinha, B. and Wu, Y.", TITLE = "Visual Query Answering by Entity-Attribute Graph Matching and Reasoning", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "8349-8358", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207967"} @inproceedings{bb212892, AUTHOR = "Singh, A. and Natarajan, V. and Shah, M. and Jiang, Y. and Chen, X.L. and Batra, D. and Parikh, D. and Rohrbach, M.", TITLE = "Towards VQA Models That Can Read", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "8309-8318", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207968"} @inproceedings{bb212893, AUTHOR = "Manjunatha, V. and Saini, N. and Davis, L.S.", TITLE = "Explicit Bias Discovery in Visual Question Answering Models", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "9554-9563", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207969"} @inproceedings{bb212894, AUTHOR = "Shrestha, R. and Kafle, K. and Kanan, C.", TITLE = "Answer Them All! Toward Universal Visual Question Answering Models", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "10464-10473", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207970"} @inproceedings{bb212895, AUTHOR = "Noh, H. and Kim, T. and Mun, J. and Han, B.H.", TITLE = "Transfer Learning via Unsupervised Task Discovery for Visual Question Answering", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "8377-8386", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207971"} @inproceedings{bb212896, AUTHOR = "Wijmans, E. and Datta, S. and Maksymets, O. and Das, A. and Gkioxari, G. and Lee, S. and Essa, I. and Parikh, D. and Batra, D.", TITLE = "Embodied Question Answering in Photorealistic Environments With Point Cloud Perception", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "6652-6661", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207972"} @inproceedings{bb212897, AUTHOR = "Shah, M. and Chen, X.L. and Rohrbach, M. and Parikh, D.", TITLE = "Cycle-Consistency for Robust Visual Question Answering", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "6642-6651", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207973"} @inproceedings{bb212898, AUTHOR = "Li, H. and Wang, P. and Shen, C.H. and van den Hengel, A.", TITLE = "Visual Question Answering as Reading Comprehension", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "6312-6321", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207974"} @inproceedings{bb212899, AUTHOR = "Yu, L.C. and Chen, X.L. and Gkioxari, G. and Bansal, M. and Berg, T.L. and Batra, D.", TITLE = "Multi-Target Embodied Question Answering", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "6302-6311", BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT207975"}