@inproceedings{bb248300,
        AUTHOR = "Pirhadi, M.J. and Mirzaei, M. and Eetemadi, S.",
        TITLE = "Just Ask Plus: Using Transcripts for VideoQA",
        BOOKTITLE = ASI23,
        YEAR = "2023",
        PAGES = "3074-3077",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243189"}

@inproceedings{bb248301,
        AUTHOR = "Ahmad, M. and Park, G. and Park, D.C. and Park, S.",
        TITLE = "MMTF: Multi-Modal Temporal Fusion for Commonsense Video Question
Answering",
        BOOKTITLE = VLAR23,
        YEAR = "2023",
        PAGES = "4659-4664",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243190"}

@inproceedings{bb248302,
        AUTHOR = "Engin, D. and Avrithis, Y.",
        TITLE = "Zero-Shot and Few-Shot Video Question Answering with Multi-Modal
Prompts",
        BOOKTITLE = CLVL23,
        YEAR = "2023",
        PAGES = "2797-2802",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243191"}

@inproceedings{bb248303,
        AUTHOR = "Nuthalapati, S.V. and Tunga, A.",
        TITLE = "Coarse to Fine Frame Selection for Online Open-ended Video Question
Answering",
        BOOKTITLE = MMFM23,
        YEAR = "2023",
        PAGES = "353-361",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243192"}

@inproceedings{bb248304,
        AUTHOR = "Li, Y.C. and Xiao, J.B. and Feng, C. and Wang, X. and Chua, T.S.",
        TITLE = "Discovering Spatio-Temporal Rationales for Video Question Answering",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "13823-13832",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243193"}

@inproceedings{bb248305,
        AUTHOR = "Ko, D. and Lee, J.S. and Choi, M. and Chu, J.W. and Park, J. and Kim, H.W.J.",
        TITLE = "Open-Vocabulary Video Question Answering: A New Benchmark for
Evaluating the Generalizability of Video Question Answering Models",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "3078-3089",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243194"}

@inproceedings{bb248306,
        AUTHOR = "Li, J.T. and Niu, L. and Zhang, L.Q.",
        TITLE = "Knowledge Proxy Intervention for Deconfounded Video Question
Answering",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "2770-2781",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243195"}

@inproceedings{bb248307,
        AUTHOR = "Chen, G.Y. and Liu, X. and Wang, G. and Zhang, K. and Torr, P.H.S. and Zhang, X.P. and Tang, Y.S.",
        TITLE = "Tem-adapter:
Adapting Image-Text Pretraining for Video Question Answer",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "13899-13909",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243196"}

@inproceedings{bb248308,
        AUTHOR = "Jahagirdar, S. and Mathew, M. and Karatzas, D. and Jawahar, C.V.",
        TITLE = "Understanding Video Scenes through Text:
Insights from Text-based Video Question Answering",
        BOOKTITLE = VLAR23,
        YEAR = "2023",
        PAGES = "4648-4652",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243197"}

@inproceedings{bb248309,
        AUTHOR = "Peng, M. and Liu, L.C. and Li, Z.H. and Shi, Y. and Zhou, X.D.",
        TITLE = "Multi-Semantic Alignment Co-Reasoning Network for Video Question
Answering",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "2090-2094",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243198"}

@inproceedings{bb248310,
        AUTHOR = "Ye, S.H. and Kong, W.K. and Yao, C.L. and Ren, J.F. and Jiang, X.D.",
        TITLE = "Video Question Answering Using Clip-Guided Visual-Text Attention",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "81-85",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243199"}

@inproceedings{bb248311,
        AUTHOR = "Khan, Z. and Kumar, B.V. and Schulter, S. and Yu, X. and Fu, Y. and Chandraker, M.",
        TITLE = "Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA
Tasks? A: Self-Train on Unlabeled Images!",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "15005-15015",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243200"}

@inproceedings{bb248312,
        AUTHOR = "Su, H.T. and Niu, Y. and Lin, X.D. and Hsu, W.H. and Chang, S.F.",
        TITLE = "Language Models are Causal Knowledge Extractors for Zero-shot Video
Question Answering",
        BOOKTITLE = L3D-IVU23,
        YEAR = "2023",
        PAGES = "4951-4960",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243201"}

@inproceedings{bb248313,
        AUTHOR = "Zang, C.Q. and Wang, H.Q. and Pei, M.T. and Liang, W.",
        TITLE = "Discovering the Real Association: Multimodal Causal Reasoning in
Video Question Answering",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "19027-19036",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243202"}

@inproceedings{bb248314,
        AUTHOR = "Gao, D.F. and Zhou, L. and Ji, L. and Zhu, L.C. and Yang, Y. and Shou, M.Z.",
        TITLE = "MIST: Multi-modal Iterative Spatial-Temporal Transformer for
Long-form Video Question Answering",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "14773-14783",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243203"}

@inproceedings{bb248315,
        AUTHOR = "Khan, A.U. and Kuehne, H. and Wu, B. and Chheu, K. and Bousselham, W. and Gan, C. and Lobo, N. and Shah, M.",
        TITLE = "Learning Situation Hyper-Graphs for Video Question Answering",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "14879-14889",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243204"}

@inproceedings{bb248316,
        AUTHOR = "Jahagirdar, S. and Mathew, M. and Karatzas, D. and Jawahar, C.V.",
        TITLE = "Watching the News: Towards VideoQA Models that can Read",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "4430-4439",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243205"}

@inproceedings{bb248317,
        AUTHOR = "Zhang, M.D. and Hwa, R. and Kovashka, A.",
        TITLE = "How to Practice VQA on a Resource-limited Target Domain",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "4440-4449",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243206"}

@inproceedings{bb248318,
        AUTHOR = "Lee, J. and Kang, W. and Kim, E.S.",
        TITLE = "Dense but Efficient VideoQA for Intricate Compositional Reasoning",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "1114-1123",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243207"}

@inproceedings{bb248319,
        AUTHOR = "Shen, R. and Inoue, N. and Shinoda, K.",
        TITLE = "Text-Guided Object Detector for Multi-modal Video Question Answering",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "1032-1042",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243208"}

@inproceedings{bb248320,
        AUTHOR = "Fang, S. and Wang, S.H. and Zhuo, J. and Han, X.Z. and Huang, Q.M.",
        TITLE = "Learning Linguistic Association Towards Efficient Text-Video Retrieval",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXVI:254-270",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243209"}

@inproceedings{bb248321,
        AUTHOR = "Piergiovanni, A.J. and Morton, K. and Kuo, W.C. and Ryoo, M.S. and Angelova, A.",
        TITLE = "Video Question Answering with Iterative Video-Text Co-tokenization",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXVI:76-94",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243210"}

@inproceedings{bb248322,
        AUTHOR = "Barmann, L. and Waibel, A.",
        TITLE = "Where did I leave my keys?: Episodic-Memory-Based Question Answering
on Egocentric Videos",
        BOOKTITLE = Ego4D-EPIC22,
        YEAR = "2022",
        PAGES = "1559-1567",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243211"}

@inproceedings{bb248323,
        AUTHOR = "Li, J.T. and Niu, L. and Zhang, L.Q.",
        TITLE = "From Representation to Reasoning: Towards both Evidence and
Commonsense Reasoning for Video Question-Answering",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "21241-21250",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243212"}

@inproceedings{bb248324,
        AUTHOR = "Datta, S. and Dharur, S. and Cartillier, V. and Desai, R. and Khanna, M. and Batra, D. and Parikh, D.",
        TITLE = "Episodic Memory Question Answering",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "19097-19106",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243213"}

@inproceedings{bb248325,
        AUTHOR = "Gandhi, M. and Gul, M.O. and Prakash, E. and Grunde McLaughlin, M. and Krishna, R. and Agrawala, M.",
        TITLE = "Measuring Compositional Consistency for Video Question Answering",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "5036-5045",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243214"}

@inproceedings{bb248326,
        AUTHOR = "Gorti, S.K. and Vouitsis, N. and Ma, J.W. and Golestan, K. and Volkovs, M. and Garg, A. and Yu, G.W.",
        TITLE = "X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "4996-5005",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243215"}

@inproceedings{bb248327,
        AUTHOR = "Li, J.C. and Tang, S.L. and Zhu, L.C. and Shi, H. and Huang, X.W. and Wu, F. and Yang, Y. and Zhuang, Y.T.",
        TITLE = "Adaptive Hierarchical Graph Reasoning with Semantic Coherence for
Video-and-Language Inference",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1847-1857",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243216"}

@inproceedings{bb248328,
        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/applicat803vidq2.html#TT243217"}

@inproceedings{bb248329,
        AUTHOR = "Kim, N. and Ha, S.J. and Kang, J.W.",
        TITLE = "Video Question Answering Using Language-Guided Deep Compressed-Domain
Video Feature",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1688-1697",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243218"}

@inproceedings{bb248330,
        AUTHOR = "Liu, F. and Liu, J. and Wang, W.N. and Lu, H.Q.",
        TITLE = "HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video
Question Answering",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1678-1687",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243219"}

@inproceedings{bb248331,
        AUTHOR = "Gao, D.F. and Wang, R.P. and Bai, Z. and Chen, X.L.",
        TITLE = "Env-QA: A Video Question Answering Benchmark for Comprehensive
Understanding of Dynamic Environments",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1655-1665",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243220"}

@inproceedings{bb248332,
        AUTHOR = "Yun, H. and Yu, Y. and Yang, W. and Lee, K. and Kim, G.",
        TITLE = "Pano-AVQA: Grounded Audio-Visual Question Answering on 360° Videos",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2011-2021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243221"}

@inproceedings{bb248333,
        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/applicat803vidq2.html#TT243222"}

@inproceedings{bb248334,
        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/applicat803vidq2.html#TT243223"}

@inproceedings{bb248335,
        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/applicat803vidq2.html#TT243224"}

@inproceedings{bb248336,
        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/applicat803vidq2.html#TT243225"}

@inproceedings{bb248337,
        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/applicat803vidq2.html#TT243226"}

@inproceedings{bb248338,
        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/applicat803vidq2.html#TT243227"}

@inproceedings{bb248339,
        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/applicat803vidq2.html#TT243228"}

@inproceedings{bb248340,
        AUTHOR = "Fan, C.Y. and Zhang, X.F. and Zhang, S. and Wang, W.S. and Zhang, C. and Huang, H.",
        TITLE = "Heterogeneous Memory Enhanced Multimodal Attention Model for Video
Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1999-2007",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243229"}

@inproceedings{bb248341,
        AUTHOR = "Kim, J.Y. and Ma, M. and Kim, K. and Kim, S.J. and Yoo, C.D.",
        TITLE = "Progressive Attention Memory Network for Movie Story Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8329-8338",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243230"}

@inproceedings{bb248342,
        AUTHOR = "Liu, C.N. and Chen, D.J. and Chen, H.T. and Liu, T.L.",
        TITLE = "A2A: Attention to Attention Reasoning for Movie Question Answering",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "VI:404-419",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243231"}

@inproceedings{bb248343,
        AUTHOR = "Gao, J. and Ge, R. and Chen, K. and Nevatia, R.",
        TITLE = "Motion-Appearance Co-memory Networks for Video Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6576-6585",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243232"}

@inproceedings{bb248344,
        AUTHOR = "Kim, K.M. and Choi, S.H. and Kim, J.H. and Zhang, B.T.",
        TITLE = "Multimodal Dual Attention Memory for Video Story Question Answering",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XV: 698-713",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243233"}

@inproceedings{bb248345,
        AUTHOR = "Yu, Y.J. and Kim, J.S. and Kim, G.",
        TITLE = "A Joint Sequence Fusion Model for Video Question Answering and
Retrieval",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VII: 487-503",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243234"}

@inproceedings{bb248346,
        AUTHOR = "Hasan Chowdhury, M.I. and Nguyen, K. and Sridharan, S. and Fookes, C.",
        TITLE = "Hierarchical Relational Attention for Video Question Answering",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "599-603",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243235"}

@inproceedings{bb248347,
        AUTHOR = "Mun, J. and Seo, P.H. and Jung, I. and Han, B.H.",
        TITLE = "MarioQA: Answering Questions by Watching Gameplay Videos",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2886-2894",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243236"}

@inproceedings{bb248348,
        AUTHOR = "Yu, Y. and Ko, H. and Choi, J. and Kim, G.",
        TITLE = "End-to-End Concept Word Detection for Video Captioning, Retrieval,
and Question Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3261-3269",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT243237"}

@article{bb248349,
        AUTHOR = "Kafle, K. and Kanan, C.",
        TITLE = "Visual question answering:
Datasets, algorithms, and future challenges",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "3-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243240"}

@article{bb248350,
        AUTHOR = "Wu, Q. and Teney, D. and Wang, P. and Shen, C.H. and Dick, A. and van den Hengel, A.J.",
        TITLE = "Visual question answering: A survey of methods and datasets",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "21-40",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243241"}

@article{bb248351,
        AUTHOR = "Teney, D. and Wu, Q. and van den Hengel, A.J.",
        TITLE = "Visual Question Answering: A Tutorial",
        JOURNAL = SPMag,
        VOLUME = "34",
        YEAR = "2017",
        NUMBER = "6",
        MONTH = "November",
        PAGES = "63-75",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243242"}

@inproceedings{bb248352,
        AUTHOR = "Teney, D. and Liu, L. and van den Hengel, A.J.",
        TITLE = "Graph-Structured Representations for Visual Question Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3233-3241",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243243"}

@inproceedings{bb248353,
        AUTHOR = "Teney, D. and van den Hengel, A.J.",
        TITLE = "Visual Question Answering as a Meta Learning Task",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XV: 229-245",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243244"}

@inproceedings{bb248354,
        AUTHOR = "Teney, D. and Abbasnejad, E. and van den Hengel, A.J.",
        TITLE = "Unshuffling Data for Improved Generalization in Visual Question
Answering",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1397-1407",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243245"}

@article{bb248355,
        AUTHOR = "Wu, Q. and Shen, C.H. and Wang, P. and Dick, A. and van den Hengel, A.J.",
        TITLE = "Image Captioning and Visual Question Answering Based on Attributes
and External Knowledge",
        JOURNAL = PAMI,
        VOLUME = "40",
        YEAR = "2018",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "1367-1381",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243246"}

@inproceedings{bb248356,
        AUTHOR = "Wu, Q. and Wang, P. and Shen, C.H. and Dick, A. and van den Hengel, A.J.",
        TITLE = "Ask Me Anything: Free-Form Visual Question Answering Based on
Knowledge from External Sources",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4622-4630",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243247"}

@article{bb248357,
        AUTHOR = "Tommasi, T. and Mallya, A. and Plummer, B.A. and Lazebnik, S. and Berg, A.C. and Berg, T.L.",
        TITLE = "Combining Multiple Cues for Visual Madlibs Question Answering",
        JOURNAL = IJCV,
        VOLUME = "127",
        YEAR = "2019",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "38-60",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243248"}

@inproceedings{bb248358,
        AUTHOR = "Tommasi, T. and Mallya, A. and Plummer, B.A. and Lazebnik, S. and Berg, A.C. and Berg, T.L.",
        TITLE = "Solving Visual Madlibs with Multiple Cues",
        BOOKTITLE = BMVC16,
        YEAR = "2016",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243249"}

@inproceedings{bb248359,
        AUTHOR = "Yu, L.C. and Park, E. and Berg, A.C. and Berg, T.L.",
        TITLE = "Visual Madlibs:
Fill in the Blank Description Generation and Question Answering",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "2461-2469",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243250"}

@article{bb248360,
        AUTHOR = "Liu, F. and Xiang, T. and Hospedales, T.M. and Yang, W.K. and Sun, C.Y.",
        TITLE = "Inverse Visual Question Answering:
A New Benchmark and VQA Diagnosis Tool",
        JOURNAL = PAMI,
        VOLUME = "42",
        YEAR = "2020",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "460-474",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243251"}

@inproceedings{bb248361,
        AUTHOR = "Liu, F. and Xiang, T. and Hospedales, T.M. and Yang, W.K. and Sun, C.Y.",
        TITLE = "iVQA: Inverse Visual Question Answering",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "8611-8619",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243252"}

@article{bb248362,
        AUTHOR = "Patil, C. and Patwardhan, M.",
        TITLE = "Visual Question Generation: The State of the Art",
        JOURNAL = Surveys,
        VOLUME = "53",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "May",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243253"}

@article{bb248363,
        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/applicat803vqds43.html#TT243254"}

@article{bb248364,
        AUTHOR = "Sharma, H. and Jalal, A.S.",
        TITLE = "A survey of methods, datasets and evaluation metrics for visual
question answering",
        JOURNAL = IVC,
        VOLUME = "116",
        YEAR = "2021",
        PAGES = "104327",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243255"}

@article{bb248365,
        AUTHOR = "Yang, L. and Jiang, H. and Song, Q. and Guo, J.",
        TITLE = "A Survey on Long-Tailed Visual Recognition",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1837-1872",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243256"}

@article{bb248366,
        AUTHOR = "Zhao, W.L. and Rao, Y.M. and Tang, Y.S. and Zhou, J. and Lu, J.W.",
        TITLE = "VideoABC: A Real-World Video Dataset for Abductive Visual Reasoning",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "6048-6061",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243257"}

@article{bb248367,
        AUTHOR = "Lahouti, F. and Kostina, V. and Hassibi, B.",
        TITLE = "How to Query an Oracle? Efficient Strategies to Label Data",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "7597-7609",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243258"}

@article{bb248368,
        AUTHOR = "Ma, J. and Wang, P.H. and Kong, D.C. and Wang, Z.W. and Liu, J. and Pei, H.B. and Zhao, J.Z.",
        TITLE = "Robust Visual Question Answering: Datasets, Methods, and Future
Challenges",
        JOURNAL = PAMI,
        VOLUME = "46",
        YEAR = "2024",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "5575-5594",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243259"}

@article{bb248369,
        AUTHOR = "Li, K. and Vosselman, G. and Yang, M.Y.",
        TITLE = "HRVQA: A Visual Question Answering benchmark for high-resolution
aerial images",
        JOURNAL = PandRS,
        VOLUME = "214",
        YEAR = "2024",
        PAGES = "65-81",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243260"}

@inproceedings{bb248370,
        AUTHOR = "Chen, C.Y. and Liu, M.C. and Codella, N. and Li, Y.S. and Yuan, L. and Gurari, D.",
        TITLE = "Fully Authentic Visual Question Answering Dataset from Online
Communities",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XLVIII: 252-269",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243261"}

@inproceedings{bb248371,
        AUTHOR = "Singh, M. and Patvardhan, C. and Lakshmi, C.V.",
        TITLE = "Does ChatGPT Spell the End of Automatic Question Generation Research?",
        BOOKTITLE = ICCVMI23,
        YEAR = "2023",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243262"}

@inproceedings{bb248372,
        AUTHOR = "Zhu, L. and Ning, R. and Li, J. and Xin, C.S. and Wu, H.Y.",
        TITLE = "Most and Least Retrievable Images in Visual-Language Query Systems",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXVII:1-18",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243263"}

@inproceedings{bb248373,
        AUTHOR = "Salewski, L. and Emde, C. and Do, V. and Akata, Z. and Lukasiewicz, T.",
        TITLE = "e-ViL: A Dataset and Benchmark for Natural Language Explanations in
Vision-Language Tasks",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1224-1234",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243264"}

@inproceedings{bb248374,
        AUTHOR = "Gupta, V. and Patro, B.N. and Parihar, H. and Namboodiri, V.P.",
        TITLE = "VQuAD: Video Question Answering Diagnostic Dataset",
        BOOKTITLE = Novelty22,
        YEAR = "2022",
        PAGES = "282-291",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243265"}

@inproceedings{bb248375,
        AUTHOR = "Nishimura, T. and Sakoda, K. and Hashimoto, A. and Ushiku, Y. and Tanaka, N. and Ono, F. and Kameko, H. and Mori, S.",
        TITLE = "Egocentric Biochemical Video-and-Language Dataset",
        BOOKTITLE = CLVL21,
        YEAR = "2021",
        PAGES = "3122-3126",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243266"}

@inproceedings{bb248376,
        AUTHOR = "Zhang, M.D. 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/applicat803vqds43.html#TT243267"}

@inproceedings{bb248377,
        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/applicat803vqds43.html#TT243268"}

@inproceedings{bb248378,
        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/applicat803vqds43.html#TT243269"}

@inproceedings{bb248379,
        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/applicat803vqds43.html#TT243270"}

@inproceedings{bb248380,
        AUTHOR = "Hudson, D.A. and Manning, C.D.",
        TITLE = "GQA: A New Dataset for Real-World Visual Reasoning and Compositional
Question Answering",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6693-6702",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243271"}

@inproceedings{bb248381,
        AUTHOR = "Yang, G.Y.R. and Ganichev, I. and Wang, X.J. and Shlens, J. and Sussillo, D.",
        TITLE = "A Dataset and Architecture for Visual Reasoning with a Working Memory",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "X: 729-745",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243272"}

@inproceedings{bb248382,
        AUTHOR = "Gan, C. and Li, Y. and Li, H. and Sun, C. and Gong, B.",
        TITLE = "VQS: Linking Segmentations to Questions and Answers for Supervised
Attention in VQA and Question-Focused Semantic Segmentation",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1829-1838",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243273"}

@inproceedings{bb248383,
        AUTHOR = "Maharaj, T. and Ballas, N. and Rohrbach, A. and Courville, A. and Pal, C.",
        TITLE = "A Dataset and Exploration of Models for Understanding Video Data
through Fill-in-the-Blank Question-Answering",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "7359-7368",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vqds43.html#TT243274"}

@article{bb248384,
        AUTHOR = "Das, A. and Kottur, S. and Gupta, K. and Singh, A. and Yadav, D. and Lee, S. and Moura, J.M.F. and Parikh, D. and Batra, D.",
        TITLE = "Visual Dialog",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1242-1256",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243275"}

@article{bb248385,
        AUTHOR = "Zhao, Z. and Zhang, Z. and Jiang, X.H. and Cai, D.",
        TITLE = "Multi-Turn Video Question Answering via Hierarchical Attention
Context Reinforced Networks",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "3860-3872",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243276"}

@article{bb248386,
        AUTHOR = "Gu, M. and Zhao, Z. and Jin, W. and Cai, D. and Wu, F.",
        TITLE = "Video Dialog via Multi-Grained Convolutional Self-Attention Context
Multi-Modal Networks",
        JOURNAL = CirSysVideo,
        VOLUME = "30",
        YEAR = "2020",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "4453-4466",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243277"}

@article{bb248387,
        AUTHOR = "Guo, D. and Wang, H. and Wang, S. and Wang, M.",
        TITLE = "Textual-Visual Reference-Aware Attention Network for Visual Dialog",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "6655-6666",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243278"}

@article{bb248388,
        AUTHOR = "Patro, B.N. and Anupriy and Namboodiri, V.P.",
        TITLE = "Probabilistic framework for solving visual dialog",
        JOURNAL = PR,
        VOLUME = "110",
        YEAR = "2021",
        PAGES = "107586",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243279"}

@article{bb248389,
        AUTHOR = "Zhao, L. and Lyu, X.Y. and Song, J.K. and Gao, L.L.",
        TITLE = "GuessWhich? Visual dialog with attentive memory network",
        JOURNAL = PR,
        VOLUME = "114",
        YEAR = "2021",
        PAGES = "107823",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243280"}

@article{bb248390,
        AUTHOR = "Jiang, T.L. and Shao, H.L. and Tian, X. and Ji, Y. and Liu, C.P.",
        TITLE = "Aligning vision-language for graph inference in visual dialog",
        JOURNAL = IVC,
        VOLUME = "116",
        YEAR = "2021",
        PAGES = "104316",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243281"}

@article{bb248391,
        AUTHOR = "Guo, D. and Wang, H. and Wang, M.",
        TITLE = "Context-Aware Graph Inference With Knowledge Distillation for Visual
Dialog",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "6056-6073",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243282"}

@inproceedings{bb248392,
        AUTHOR = "Guo, D. and Wang, H. and Zhang, H.W. and Zha, Z.J. 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/applicat803vdi3.html#TT243283"}

@article{bb248393,
        AUTHOR = "Patro, B.N. and Anupriy and Namboodiri, V.P.",
        TITLE = "Explanation vs. attention: A two-player game to obtain attention for
VQA and visual dialog",
        JOURNAL = PR,
        VOLUME = "132",
        YEAR = "2022",
        PAGES = "108898",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243284"}

@article{bb248394,
        AUTHOR = "Zhu, Y. and Wu, Y. and Yang, Y. and Yan, Y.",
        TITLE = "Saying the Unseen: Video Descriptions via Dialog Agents",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "7190-7204",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243285"}

@article{bb248395,
        AUTHOR = "Huang, Y. and Wang, Y.M. and Wang, L.",
        TITLE = "Efficient Image and Sentence Matching",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "2970-2983",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243286"}

@article{bb248396,
        AUTHOR = "Zhao, L. and Li, J.L. and Gao, L.L. and Rao, Y. and Song, J.K. and Shen, H.T.",
        TITLE = "Heterogeneous Knowledge Network for Visual Dialog",
        JOURNAL = CirSysVideo,
        VOLUME = "33",
        YEAR = "2023",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "861-871",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243287"}

@article{bb248397,
        AUTHOR = "Bucinca, Z. and Yemez, Y. and Erzin, E. and Sezgin, M.",
        TITLE = "AffectON: Incorporating Affect Into Dialog Generation",
        JOURNAL = AffCom,
        VOLUME = "14",
        YEAR = "2023",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "823-835",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243288"}

@article{bb248398,
        AUTHOR = "Yu, H. and Ko, Y.J.",
        TITLE = "Enriching the dialogue state tracking model with a asyntactic
discourse graph",
        JOURNAL = PRL,
        VOLUME = "169",
        YEAR = "2023",
        PAGES = "81-86",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243289"}

@article{bb248399,
        AUTHOR = "Wu, Y.X. and Liao, L. and Zhang, G.Y. and Lei, W.Q. and Zhao, G.S. and Qian, X.M. and Chua, T.S.",
        TITLE = "State Graph Reasoning for Multimodal Conversational Recommendation",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "3113-3124",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vdi3.html#TT243290"}

Last update:Nov 9, 2026 at 17:04:52