@article{bb178800,
        AUTHOR = "Xie, Z. and Wu, K.W. and Zhang, X.Y. and Yang, X.M. and Hou, J.K.",
        TITLE = "Learning continuous temporal embedding of videos using pattern theory",
        JOURNAL = PRL,
        VOLUME = "146",
        YEAR = "2021",
        PAGES = "222-229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174136"}

@article{bb178801,
        AUTHOR = "Sharma, H. and Jalal, A.S.",
        TITLE = "Visual question answering model based on graph neural network and
contextual attention",
        JOURNAL = IVC,
        VOLUME = "110",
        YEAR = "2021",
        PAGES = "104165",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174137"}

@article{bb178802,
        AUTHOR = "Yuan, Z. and Sun, S.Y. and Duan, L.X. and Li, C.S. and Wu, X. and Xu, C.S.",
        TITLE = "Adversarial Multimodal Network for Movie Story Question Answering",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "1744-1756",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174138"}

@article{bb178803,
        AUTHOR = "Wu, Y. and Ma, Y.T. and Wan, S.H.",
        TITLE = "Multi-scale relation reasoning for multi-modal Visual Question
Answering",
        JOURNAL = SP:IC,
        VOLUME = "96",
        YEAR = "2021",
        PAGES = "116319",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174139"}

@inproceedings{bb178804,
        AUTHOR = "Ma, Y.T. and Lu, T. and Wu, Y.",
        TITLE = "Multi-scale Relational Reasoning with Regional Attention for Visual
Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "5642-5649",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174140"}

@article{bb178805,
        AUTHOR = "dos S Silva, F.H. and Bezerra, G.M. and Holanda, G.B. and de Souza, J.W.M. and Rego, P.A.L. and Lira Neto, A.V. and de Albuquerque, V.H.C. and Reboucas Filho, P.P.",
        TITLE = "A novel feature extractor for human action recognition in visual
question answering",
        JOURNAL = PRL,
        VOLUME = "147",
        YEAR = "2021",
        PAGES = "41-47",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174141"}

@article{bb178806,
        AUTHOR = "Liu, Y. and Zhang, X.M. and Zhang, Q.Y. and Li, C.Z. and Huang, F. and Tang, X.H. and Li, Z.J.",
        TITLE = "Dual self-attention with co-attention networks for visual question
answering",
        JOURNAL = PR,
        VOLUME = "117",
        YEAR = "2021",
        PAGES = "107956",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174142"}

@article{bb178807,
        AUTHOR = "Jin, W. and Zhao, Z. and Cao, X.C. and Zhu, J.M. and He, X.Q. and Zhuang, Y.T.",
        TITLE = "Adaptive Spatio-Temporal Graph Enhanced Vision-Language
Representation for Video QA",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "5477-5489",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174143"}

@article{bb178808,
        AUTHOR = "He, F.J. and Wang, Y.X. and Miao, X.L. and Sun, X.",
        TITLE = "Interpretable visual reasoning: A survey",
        JOURNAL = IVC,
        VOLUME = "112",
        YEAR = "2021",
        PAGES = "104194",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174144"}

@article{bb178809,
        AUTHOR = "Guo, W. and Zhang, Y. and Yang, J.F. and Yuan, X.J.",
        TITLE = "Re-Attention for Visual Question Answering",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "6730-6743",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174145"}

@article{bb178810,
        AUTHOR = "Hu, J. and Qian, S. and Fang, Q. and Xu, C.S.",
        TITLE = "Heterogeneous Community Question Answering via Social-Aware
Multi-Modal Co-Attention Convolutional Matching",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "2321-2334",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174146"}

@article{bb178811,
        AUTHOR = "Gao, L. and Chen, T.M. and Li, X.P. and Zeng, P.P. and Zhao, L. and Li, Y.F.",
        TITLE = "Generalized pyramid co-attention with learnable aggregation net for
video question answering",
        JOURNAL = PR,
        VOLUME = "120",
        YEAR = "2021",
        PAGES = "108145",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174147"}

@article{bb178812,
        AUTHOR = "Farazi, M. and Khan, S. and Barnes, N.",
        TITLE = "Accuracy vs. complexity: A trade-off in visual question answering
models",
        JOURNAL = PR,
        VOLUME = "120",
        YEAR = "2021",
        PAGES = "108106",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174148"}

@article{bb178813,
        AUTHOR = "Zheng, W.F. and Yin, L.R. and Chen, X.B. and Ma, Z. and Liu, S. and Yang, B.",
        TITLE = "Knowledge base graph embedding module design for Visual question
answering model",
        JOURNAL = PR,
        VOLUME = "120",
        YEAR = "2021",
        PAGES = "108153",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174149"}

@article{bb178814,
        AUTHOR = "Al Sadi, A. and Al Ayyoub, M. and Jararweh, Y. and Costen, F.",
        TITLE = "Visual question answering in the medical domain based on deep
learning approaches: A comprehensive study",
        JOURNAL = PRL,
        VOLUME = "150",
        YEAR = "2021",
        PAGES = "57-75",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174150"}

@article{bb178815,
        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#TT174151"}

@article{bb178816,
        AUTHOR = "Le, T.M. and Le, V. and Venkatesh, S. and Tran, T.",
        TITLE = "Hierarchical Conditional Relation Networks for Multimodal Video
Question Answering",
        JOURNAL = IJCV,
        VOLUME = "129",
        YEAR = "2021",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "3027-3050",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174152"}

@inproceedings{bb178817,
        AUTHOR = "Le, T.M. and Le, V. and Venkatesh, S. and Tran, T.",
        TITLE = "Hierarchical Conditional Relation Networks for Video Question
Answering",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "9969-9978",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174153"}

@article{bb178818,
        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#TT174154"}

@article{bb178819,
        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#TT174155"}

@article{bb178820,
        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#TT174156"}

@article{bb178821,
        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#TT174157"}

@inproceedings{bb178822,
        AUTHOR = "Zhang, M.X. and Yang, Y. and Chen, X. and Ji, Y.L. and Xu, X. and Li, J.J. and Shen, H.T.",
        TITLE = "Multi-stage Aggregated Transformer Network for Temporal Language
Localization in Videos",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "12664-12673",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174158"}

@inproceedings{bb178823,
        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#TT174159"}

@inproceedings{bb178824,
        AUTHOR = "Lei, J. and Li, L.J. and Zhou, L. and Gan, Z. and Berg, T.L. and Bansal, M. and Liu, J.J.",
        TITLE = "Less is More:
CLIPBERT for Video-and-Language Learning via Sparse Sampling",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "7327-7337",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174160"}

@inproceedings{bb178825,
        AUTHOR = "Yang, X. and Zhang, H. and Qi, G.J. and Cai, J.F.",
        TITLE = "Causal Attention for Vision-Language Tasks",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "9842-9852",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174161"}

@inproceedings{bb178826,
        AUTHOR = "Tu, T. and Ping, Q. and Thattai, G. and Tur, G. and Natarajan, P.",
        TITLE = "Learning Better Visual Dialog Agents with Pretrained
Visual-Linguistic Representation",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "5618-5627",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174162"}

@inproceedings{bb178827,
        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#TT174163"}

@inproceedings{bb178828,
        AUTHOR = "Xu, L. and Huang, H. and Liu, J.",
        TITLE = "SUTD-TrafficQA: A Question Answering Benchmark and an Efficient
Network for Video Reasoning over Traffic Events",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "9873-9883",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174164"}

@inproceedings{bb178829,
        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#TT174165"}

@inproceedings{bb178830,
        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#TT174166"}

@inproceedings{bb178831,
        AUTHOR = "Park, J. and Lee, J.Y. and Sohn, K.H.",
        TITLE = "Bridge to Answer: Structure-aware Graph Interaction Network for Video
Question Answering",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "15521-15530",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174167"}

@inproceedings{bb178832,
        AUTHOR = "Yuan, Y.Y. and Wang, S. and Jiang, M. 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#TT174168"}

@inproceedings{bb178833,
        AUTHOR = "Marino, K. and Chen, X. 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#TT174169"}

@inproceedings{bb178834,
        AUTHOR = "Niu, Y. and Tang, K. and Zhang, H. 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#TT174170"}

@inproceedings{bb178835,
        AUTHOR = "Yang, Z.Y. and Lu, Y. and Wang, J.F. and Yin, X. and Florencio, D. and Wang, L. 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#TT174171"}

@inproceedings{bb178836,
        AUTHOR = "Zhang, M. and Maidment, T. and Diab, A. and Kovashka, A. and Hwa, R.",
        TITLE = "Domain-robust VQA with diverse datasets and methods but no target
labels",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "7042-7052",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174172"}

@inproceedings{bb178837,
        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#TT174173"}

@inproceedings{bb178838,
        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#TT174174"}

@inproceedings{bb178839,
        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#TT174175"}

@inproceedings{bb178840,
        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#TT174176"}

@inproceedings{bb178841,
        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#TT174177"}

@inproceedings{bb178842,
        AUTHOR = "Mathew, M. and Karatzas, D. and Jawahar, C.V.",
        TITLE = "DocVQA: A Dataset for VQA on Document Images",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "2199-2208",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174178"}

@inproceedings{bb178843,
        AUTHOR = "Chen, X.W. and Liu, R. and Song, X.M. and Han, Y.H.",
        TITLE = "Locating Visual Explanations for Video Question Answering",
        BOOKTITLE = MMMod21,
        YEAR = "2021",
        PAGES = "I:290-302",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174179"}

@inproceedings{bb178844,
        AUTHOR = "Jiang, T.L. and Ji, Y. and Liu, C.P.",
        TITLE = "Integrating Historical States and Co-attention Mechanism for Visual
Dialog",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "2041-2048",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174180"}

@inproceedings{bb178845,
        AUTHOR = "Stefanini, M. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "A Novel Attention-based Aggregation Function to Combine Vision and
Language",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "1212-1219",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174181"}

@inproceedings{bb178846,
        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#TT174182"}

@inproceedings{bb178847,
        AUTHOR = "Liang, Y.Y. and Wang, X. and Duan, X.G. and Zhu, W.W.",
        TITLE = "Multi-modal Contextual Graph Neural Network for Text Visual Question
Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "3491-3498",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174183"}

@inproceedings{bb178848,
        AUTHOR = "Farazi, M. and Khan, S. and Barnes, N.",
        TITLE = "Question-Agnostic Attention for Visual Question Answering",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "3542-3549",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174184"}

@inproceedings{bb178849,
        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#TT174185"}

@inproceedings{bb178850,
        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#TT174186"}

@inproceedings{bb178851,
        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#TT174187"}

@inproceedings{bb178852,
        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#TT174188"}

@inproceedings{bb178853,
        AUTHOR = "Kocaman, V. and Talby, D.",
        TITLE = "Biomedical Named Entity Recognition at Scale",
        BOOKTITLE = "CADL20",
        YEAR = "2020",
        PAGES = "635-646",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174189"}

@inproceedings{bb178854,
        AUTHOR = "Sun, Q. and Xie, B. 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#TT174190"}

@inproceedings{bb178855,
        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#TT174191"}

@inproceedings{bb178856,
        AUTHOR = "Patel, D. and Parikh, R. and Shastri, Y.",
        TITLE = "Recent Advances in Video Question Answering:
A Review of Datasets and Methods",
        BOOKTITLE = VTIUR20,
        YEAR = "2020",
        PAGES = "339-356",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174192"}

@inproceedings{bb178857,
        AUTHOR = "Nguyen, V.Q. and Suganuma, M. and Okatani, T.",
        TITLE = "Efficient Attention Mechanism for Visual Dialog that Can Handle All the
Interactions Between Multiple Inputs",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXIV:223-240",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174193"}

@inproceedings{bb178858,
        AUTHOR = "Murahari, V. and Batra, D. and Parikh, D. and Das, A.",
        TITLE = "Large-scale Pretraining for Visual Dialog:
A Simple State-of-the-art Baseline",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVIII:336-352",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174194"}

@inproceedings{bb178859,
        AUTHOR = "Garcia, N. and Nakashima, Y.",
        TITLE = "Knowledge-based Video Question Answering with Unsupervised Scene
Descriptions",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVIII:581-598",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174195"}

@inproceedings{bb178860,
        AUTHOR = "Tan, S. and Xiang, W. 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#TT174196"}

@inproceedings{bb178861,
        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#TT174197"}

@inproceedings{bb178862,
        AUTHOR = "Jain, V. and Lodhavia, J.",
        TITLE = "Automatic Question Tagging using k-Nearest Neighbors and Random
Forest",
        BOOKTITLE = ISCV20,
        YEAR = "2020",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174198"}

@inproceedings{bb178863,
        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#TT174199"}

@inproceedings{bb178864,
        AUTHOR = "Zhu, Y. and Wu, Y. and Yang, Y. and Yan, Y.",
        TITLE = "Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXIII:153-169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174200"}

@inproceedings{bb178865,
        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#TT174201"}

@inproceedings{bb178866,
        AUTHOR = "Yang, X.F. and Lin, G.S. and Lv, F.M. and Liu, F.",
        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#TT174202"}

@inproceedings{bb178867,
        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#TT174203"}

@inproceedings{bb178868,
        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#TT174204"}

@inproceedings{bb178869,
        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#TT174205"}

@inproceedings{bb178870,
        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#TT174206"}

@inproceedings{bb178871,
        AUTHOR = "Zheng, W.B. and Yan, L. and Gou, C. and Wang, F.Y.",
        TITLE = "Webly Supervised Knowledge Embedding Model for Visual Reasoning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "12442-12451",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174207"}

@inproceedings{bb178872,
        AUTHOR = "Qi, J. and Niu, Y. and Huang, J. and Zhang, H.",
        TITLE = "Two Causal Principles for Improving Visual Dialog",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10857-10866",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174208"}

@inproceedings{bb178873,
        AUTHOR = "Abbasnejad, E. and Teney, D. and Parvaneh, A. and Shi, J. and van den Hengel, A.J.",
        TITLE = "Counterfactual Vision and Language Learning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10041-10051",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174209"}

@inproceedings{bb178874,
        AUTHOR = "Wang, P. and Wu, Q. and Cao, J. and Shen, C.H. and Gao, L.L. and van den Hengel, A.J.",
        TITLE = "Neighbourhood Watch: Referring Expression Comprehension via
Language-Guided Graph Attention Networks",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1960-1968",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174210"}

@inproceedings{bb178875,
        AUTHOR = "Guo, D. and Wang, H. and Zhang, H. and Zha, Z. and Wang, M.",
        TITLE = "Iterative Context-Aware Graph Inference for Visual Dialog",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10052-10061",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174211"}

@inproceedings{bb178876,
        AUTHOR = "Zhu, Y. and Zhu, F. and Zhan, Z. and Lin, B. and Jiao, J. and Chang, X. and Liang, X.",
        TITLE = "Vision-Dialog Navigation by Exploring Cross-Modal Memory",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10727-10736",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174212"}

@inproceedings{bb178877,
        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#TT174213"}

@inproceedings{bb178878,
        AUTHOR = "Chen, L. and Yan, X. and Xiao, J. and Zhang, H. 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#TT174214"}

@inproceedings{bb178879,
        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#TT174215"}

@inproceedings{bb178880,
        AUTHOR = "Jiang, H. and Misra, I. and Rohrbach, M. and Learned Miller, E. 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#TT174216"}

@inproceedings{bb178881,
        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#TT174217"}

@inproceedings{bb178882,
        AUTHOR = "Kim, J. and Ma, M. and Pham, T. and Kim, K. and Yoo, C.D.",
        TITLE = "Modality Shifting Attention Network for Multi-Modal Video Question
Answering",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10103-10112",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174218"}

@inproceedings{bb178883,
        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#TT174219"}

@inproceedings{bb178884,
        AUTHOR = "Jiang, M. and Chen, S. and Yang, J. and Zhao, Q.",
        TITLE = "Fantastic Answers and Where to Find Them: Immersive Question-Directed
Visual Attention",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "2977-2986",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174220"}

@inproceedings{bb178885,
        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#TT174221"}

@inproceedings{bb178886,
        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#TT174222"}

@inproceedings{bb178887,
        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#TT174223"}

@inproceedings{bb178888,
        AUTHOR = "Yang, Z. and Garcia, N. and Chu, C. and Otani, M. and Nakashima, Y. and Takemura, H.",
        TITLE = "BERT Representations for Video Question Answering",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1545-1554",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174224"}

@inproceedings{bb178889,
        AUTHOR = "Patro, B.N. and Kurmi, V.K. and Kumar, S. and Namboodiri, V.P.",
        TITLE = "Deep Bayesian Network for Visual Question Generation",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1555-1565",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174225"}

@inproceedings{bb178890,
        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#TT174226"}

@inproceedings{bb178891,
        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#TT174227"}

@inproceedings{bb178892,
        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#TT174228"}

@inproceedings{bb178893,
        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#TT174229"}

@inproceedings{bb178894,
        AUTHOR = "Singh, A.K. and Mishra, A. and Shekhar, S. and Chakraborty, A.",
        TITLE = "From Strings to Things: Knowledge-Enabled VQA Model That Can Read and
Reason",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4601-4611",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174230"}

@inproceedings{bb178895,
        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#TT174231"}

@inproceedings{bb178896,
        AUTHOR = "Luo, H. and Lin, G. and Liu, Z. and Liu, F. and Tang, Z. and Yao, Y.",
        TITLE = "SegEQA: Video Segmentation Based Visual Attention for Embodied
Question Answering",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "9666-9675",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174232"}

@inproceedings{bb178897,
        AUTHOR = "Li, L. and Gan, Z. and Cheng, Y. and Liu, 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#TT174233"}

@inproceedings{bb178898,
        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#TT174234"}

@inproceedings{bb178899,
        AUTHOR = "Fan, C.",
        TITLE = "EgoVQA: An Egocentric Video Question Answering Benchmark Dataset",
        BOOKTITLE = EPIC19,
        YEAR = "2019",
        PAGES = "4359-4366",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqa1.html#TT174235"}

Last update:Nov 30, 2021 at 22:19:38