@inproceedings{bb240600,
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#TT235515"}
@inproceedings{bb240601,
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#TT235516"}
@inproceedings{bb240602,
AUTHOR = "Li, G.Y. and Wei, Y. and Tian, Y.P. and Xu, C.L. and Wen, J.R. and Hu, D.",
TITLE = "Learning to Answer Questions in Dynamic Audio-Visual Scenarios",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19086-19096",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235517"}
@inproceedings{bb240603,
AUTHOR = "Chen, C.Y. and Anjum, S. and Gurari, D.",
TITLE = "Grounding Answers for Visual Questions Asked by Visually Impaired
People",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19076-19085",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235518"}
@inproceedings{bb240604,
AUTHOR = "Li, C.H. and Li, Z. and Jing, C.C. and Wu, Y.W. and Zhai, M.L. and Jia, Y.D.",
TITLE = "Compositional Substitutivity of Visual Reasoning for Visual Question
Answering",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLVIII: 143-160",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235519"}
@inproceedings{bb240605,
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#TT235520"}
@inproceedings{bb240606,
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#TT235521"}
@inproceedings{bb240607,
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#TT235522"}
@inproceedings{bb240608,
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#TT235523"}
@inproceedings{bb240609,
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#TT235524"}
@inproceedings{bb240610,
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#TT235525"}
@inproceedings{bb240611,
AUTHOR = "Zhou, Y.Y. and Ren, T.H. and Zhu, C.Y. and Sun, X.S. and Liu, J.Z. and Ding, X.H. and Xu, M.L. and Ji, R.R.",
TITLE = "TRAR: Routing the Attention Spans in Transformer for Visual Question
Answering",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "2054-2064",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235526"}
@inproceedings{bb240612,
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#TT235527"}
@inproceedings{bb240613,
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#TT235528"}
@inproceedings{bb240614,
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#TT235529"}
@inproceedings{bb240615,
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#TT235530"}
@inproceedings{bb240616,
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#TT235531"}
@inproceedings{bb240617,
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#TT235532"}
@inproceedings{bb240618,
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#TT235533"}
@inproceedings{bb240619,
AUTHOR = "Jung, S.J. and Byun, J.Y. and Shim, K. and Hwang, S.Y. and Kim, C.",
TITLE = "Understanding VQA for Negative Answers Through Visual and Linguistic
Inference",
BOOKTITLE = ICIP21,
YEAR = "2021",
PAGES = "2873-2877",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235534"}
@inproceedings{bb240620,
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#TT235535"}
@inproceedings{bb240621,
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#TT235536"}
@inproceedings{bb240622,
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#TT235537"}
@inproceedings{bb240623,
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#TT235538"}
@inproceedings{bb240624,
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#TT235539"}
@inproceedings{bb240625,
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#TT235540"}
@inproceedings{bb240626,
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#TT235541"}
@inproceedings{bb240627,
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#TT235542"}
@inproceedings{bb240628,
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#TT235543"}
@inproceedings{bb240629,
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#TT235544"}
@inproceedings{bb240630,
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#TT235545"}
@inproceedings{bb240631,
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#TT235546"}
@inproceedings{bb240632,
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#TT235547"}
@inproceedings{bb240633,
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#TT235548"}
@inproceedings{bb240634,
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#TT235549"}
@inproceedings{bb240635,
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#TT235550"}
@inproceedings{bb240636,
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#TT235551"}
@inproceedings{bb240637,
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#TT235552"}
@inproceedings{bb240638,
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#TT235553"}
@inproceedings{bb240639,
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#TT235554"}
@inproceedings{bb240640,
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#TT235555"}
@inproceedings{bb240641,
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#TT235556"}
@inproceedings{bb240642,
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#TT235557"}
@inproceedings{bb240643,
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#TT235558"}
@inproceedings{bb240644,
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#TT235559"}
@inproceedings{bb240645,
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#TT235560"}
@inproceedings{bb240646,
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#TT235561"}
@inproceedings{bb240647,
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#TT235562"}
@inproceedings{bb240648,
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#TT235563"}
@inproceedings{bb240649,
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#TT235564"}
@inproceedings{bb240650,
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#TT235565"}
@inproceedings{bb240651,
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#TT235566"}
@inproceedings{bb240652,
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#TT235567"}
@inproceedings{bb240653,
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#TT235568"}
@inproceedings{bb240654,
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#TT235569"}
@inproceedings{bb240655,
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#TT235570"}
@inproceedings{bb240656,
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#TT235571"}
@inproceedings{bb240657,
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#TT235572"}
@inproceedings{bb240658,
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#TT235573"}
@inproceedings{bb240659,
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#TT235574"}
@inproceedings{bb240660,
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#TT235575"}
@inproceedings{bb240661,
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#TT235576"}
@inproceedings{bb240662,
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#TT235577"}
@inproceedings{bb240663,
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#TT235578"}
@inproceedings{bb240664,
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#TT235579"}
@inproceedings{bb240665,
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#TT235580"}
@inproceedings{bb240666,
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#TT235581"}
@inproceedings{bb240667,
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#TT235582"}
@inproceedings{bb240668,
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#TT235583"}
@inproceedings{bb240669,
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#TT235584"}
@inproceedings{bb240670,
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#TT235585"}
@inproceedings{bb240671,
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#TT235586"}
@inproceedings{bb240672,
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#TT235587"}
@inproceedings{bb240673,
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#TT235588"}
@inproceedings{bb240674,
AUTHOR = "Yu, Z. and Yu, J. and Cui, Y.H. and Tao, D.C. and Tian, Q.",
TITLE = "Deep Modular Co-Attention Networks for Visual Question Answering",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6274-6283",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235589"}
@inproceedings{bb240675,
AUTHOR = "Abbasnejad, E. and Wu, Q. and Shi, Q.F. and van den Hengel, A.",
TITLE = "What's to Know? Uncertainty as a Guide to Asking Goal-Oriented
Questions",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "4150-4159",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235590"}
@inproceedings{bb240676,
AUTHOR = "Schwenk, D. and Khandelwal, A. and Clark, C. and Marino, K. and Mottaghi, R.",
TITLE = "A-OKVQA: A Benchmark for Visual Question Answering Using World
Knowledge",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "VIII:146-162",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235591"}
@inproceedings{bb240677,
AUTHOR = "Marino, K. and Rastegari, M. and Farhadi, A. and Mottaghi, R.",
TITLE = "OK-VQA: A Visual Question Answering Benchmark Requiring External
Knowledge",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "3190-3199",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235592"}
@inproceedings{bb240678,
AUTHOR = "Krishna, R. and Bernstein, M. and Fei Fei, L.",
TITLE = "Information Maximizing Visual Question Generation",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "2008-2018",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235593"}
@inproceedings{bb240679,
AUTHOR = "Haurilet, M. and Roitberg, A. and Stiefelhagen, R.",
TITLE = "It's Not About the Journey; It's About the Destination: Following Soft
Paths Under Question-Guidance for Visual Reasoning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "1930-1939",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235594"}
@inproceedings{bb240680,
AUTHOR = "Qiu, Y. and Satoh, Y. and Suzuki, R. and Kataoka, H.",
TITLE = "Incorporating 3D Information Into Visual Question Answering",
BOOKTITLE = "3DV19",
YEAR = "2019",
PAGES = "756-765",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235595"}
@inproceedings{bb240681,
AUTHOR = "Liu, F. and Liu, J. and Fang, Z. and Lu, H.",
TITLE = "Language and Visual Relations Encoding for Visual Question Answering",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "3307-3311",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235596"}
@inproceedings{bb240682,
AUTHOR = "Fang, Z.W. and Liu, J. and Tang, Q. and Li, Y. and Lu, H.Q.",
TITLE = "Answer Distillation for Visual Question Answering",
BOOKTITLE = ACCV18,
YEAR = "2018",
PAGES = "I:72-87",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235597"}
@inproceedings{bb240683,
AUTHOR = "Kuhnle, A. and Xie, H.Y. and Copestake, A.",
TITLE = "How Clever Is the FiLM Model, and How Clever Can it Be?",
BOOKTITLE = VL18,
YEAR = "2018",
PAGES = "IV:162-172",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235598"}
@inproceedings{bb240684,
AUTHOR = "Li, W. and Yuan, Z.H. and Fang, X.Z. and Wang, C.",
TITLE = "Knowing Where to Look? Analysis on Attention of Visual Question
Answering System",
BOOKTITLE = VL18,
YEAR = "2018",
PAGES = "IV:145-152",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235599"}
@inproceedings{bb240685,
AUTHOR = "Wagner, M. and Basevi, H. and Shetty, R. and Li, W.B. and Malinowski, M. and Fritz, M. and Leonardis, A.",
TITLE = "Answering Visual What-If Questions: From Actions to Predicted Scene
Descriptions",
BOOKTITLE = VLEASE18,
YEAR = "2018",
PAGES = "I:521-537",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235600"}
@inproceedings{bb240686,
AUTHOR = "Duke, B. and Taylor, G.W.",
TITLE = "Generalized Hadamard-Product Fusion Operators for Visual Question
Answering",
BOOKTITLE = CRV18,
YEAR = "2018",
PAGES = "39-46",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235601"}
@inproceedings{bb240687,
AUTHOR = "Das, A. and Datta, S. and Gkioxari, G. and Lee, S. and Parikh, D. and Batra, D.",
TITLE = "Embodied Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "1-10",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235602"}
@inproceedings{bb240688,
AUTHOR = "Misra, I. and Girshick, R. and Fergus, R. and Hebert, M. and Gupta, A. and van der Maaten, L.",
TITLE = "Learning by Asking Questions",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "11-20",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235603"}
@inproceedings{bb240689,
AUTHOR = "Gurari, D. and Li, Q. and Stangl, A.J. and Guo, A. and Lin, C. and Grauman, K. and Luo, J. and Bigham, J.P.",
TITLE = "VizWiz Grand Challenge: Answering Visual Questions from Blind People",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "3608-3617",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235604"}
@inproceedings{bb240690,
AUTHOR = "Li, J. and Su, H. and Zhu, J. and Wang, S. and Zhang, B.",
TITLE = "Textbook Question Answering Under Instructor Guidance with Memory
Networks",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "3655-3663",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235605"}
@inproceedings{bb240691,
AUTHOR = "Gordon, D. and Kembhavi, A. and Rastegari, M. and Redmon, J. and Fox, D. and Farhadi, A.",
TITLE = "IQA: Visual Question Answering in Interactive Environments",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "4089-4098",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235606"}
@inproceedings{bb240692,
AUTHOR = "Agrawal, A. and Batra, D. and Parikh, D. and Kembhavi, A.",
TITLE = "Don't Just Assume; Look and Answer: Overcoming Priors for Visual
Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "4971-4980",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235607"}
@inproceedings{bb240693,
AUTHOR = "Sha, F. and Chao, W. and Hu, H.",
TITLE = "Learning Answer Embeddings for Visual Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "5428-5436",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235608"}
@inproceedings{bb240694,
AUTHOR = "Kafle, K. and Price, B. and Cohen, S. and Kanan, C.",
TITLE = "DVQA: Understanding Data Visualizations via Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "5648-5656",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235609"}
@inproceedings{bb240695,
AUTHOR = "Sha, F. and Hu, H. and Chao, W.",
TITLE = "Cross-Dataset Adaptation for Visual Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "5716-5725",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235610"}
@inproceedings{bb240696,
AUTHOR = "Anderson, P. and He, X. and Buehler, C. and Teney, D. and Johnson, M. and Gould, S. and Zhang, L.",
TITLE = "Bottom-Up and Top-Down Attention for Image Captioning and Visual
Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "6077-6086",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235611"}
@inproceedings{bb240697,
AUTHOR = "Nguyen, D. and Okatani, T.",
TITLE = "Improved Fusion of Visual and Language Representations by Dense
Symmetric Co-attention for Visual Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "6087-6096",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235612"}
@inproceedings{bb240698,
AUTHOR = "Patro, B. and Namboodiri, V.P.",
TITLE = "Differential Attention for Visual Question Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7680-7688",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235613"}
@inproceedings{bb240699,
AUTHOR = "Su, Z. and Zhu, C. and Dong, Y.P. and Cai, D.Q. and Chen, Y.R. and Li, J.G.",
TITLE = "Learning Visual Knowledge Memory Networks for Visual Question
Answering",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7736-7745",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT235614"}
Last update:Apr 6, 2026 at 11:28:57