@article{bb240900,
AUTHOR = "Chen, J. and Shao, J. and He, C.K.",
TITLE = "Movie fill in the blank by joint learning from video and text with
adaptive temporal attention",
JOURNAL = PRL,
VOLUME = "132",
YEAR = "2020",
PAGES = "62-68",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235815"}
@article{bb240901,
AUTHOR = "Wang, A. and Luu, A.T. and Foo, C. and Zhu, H. and Tay, Y. and Chandrasekhar, V.",
TITLE = "Holistic Multi-Modal Memory Network for Movie Question Answering",
JOURNAL = IP,
VOLUME = "29",
YEAR = "2020",
NUMBER = "1",
PAGES = "489-499",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235816"}
@article{bb240902,
AUTHOR = "Yuan, Z.Q. 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/applicat803vidq2.html#TT235817"}
@article{bb240903,
AUTHOR = "Gu, M. and Zhao, Z. and Jin, W. and Hong, R. and Wu, F.",
TITLE = "Graph-Based Multi-Interaction Network for Video Question Answering",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "2758-2770",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235818"}
@article{bb240904,
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/applicat803vidq2.html#TT235819"}
@article{bb240905,
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/applicat803vidq2.html#TT235820"}
@article{bb240906,
AUTHOR = "Liu, Y. and Zhang, X.M. and Huang, F. and Shen, S.X. and Tian, P. and Li, L. and Li, Z.J.",
TITLE = "Dynamic Self-Attention with Vision Synchronization Networks for Video
Question Answering",
JOURNAL = PR,
VOLUME = "132",
YEAR = "2022",
PAGES = "108959",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235821"}
@article{bb240907,
AUTHOR = "Liu, Y. and Zhang, X.M. and Huang, F. and Zhang, B. and Li, Z.J.",
TITLE = "Cross-Attentional Spatio-Temporal Semantic Graph Networks for Video
Question Answering",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "1684-1696",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235822"}
@article{bb240908,
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/applicat803vidq2.html#TT235823"}
@article{bb240909,
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/applicat803vidq2.html#TT235824"}
@article{bb240910,
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/applicat803vidq2.html#TT235825"}
@inproceedings{bb240911,
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/applicat803vidq2.html#TT235826"}
@article{bb240912,
AUTHOR = "Su, H.T. and Chang, C.H. and Shen, P.W. and Wang, Y.S. and Chang, Y.L. and Chang, Y.C. and Cheng, P.J. and Hsu, W.H.",
TITLE = "End-to-End Video Question-Answer Generation With Generator-Pretester
Network",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "11",
MONTH = "November",
PAGES = "4497-4507",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235827"}
@article{bb240913,
AUTHOR = "Gao, L.L. and Lei, Y. and Zeng, P.P. and Song, J.K. and Wang, M. and Shen, H.T.",
TITLE = "Hierarchical Representation Network With Auxiliary Tasks for Video
Captioning and Video Question Answering",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "202-215",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235828"}
@article{bb240914,
AUTHOR = "Zhang, J.P. and Shao, J. and Cao, R. and Gao, L.L. and Xu, X. and Shen, H.T.",
TITLE = "Action-Centric Relation Transformer Network for Video Question
Answering",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "1",
MONTH = "January",
PAGES = "63-74",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235829"}
@article{bb240915,
AUTHOR = "Zhang, H. and Sun, A. and Jing, W. and Zhen, L.L. and Zhou, J.T.Y. and Goh, R.S.M.",
TITLE = "Natural Language Video Localization: A Revisit in Span-Based Question
Answering Framework",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "8",
MONTH = "August",
PAGES = "4252-4266",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235830"}
@article{bb240916,
AUTHOR = "Wang, J.Y. and Bao, B.K. and Xu, C.S.",
TITLE = "DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question
Answering",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "3369-3380",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235831"}
@article{bb240917,
AUTHOR = "Zeng, P.P. and Zhang, H.N. and Gao, L. and Song, J.K. and Shen, H.T.",
TITLE = "Video Question Answering With Prior Knowledge and Object-Sensitive
Learning",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "5936-5948",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235832"}
@article{bb240918,
AUTHOR = "Gan, Z. and Li, L.J. and Li, C.Y. and Wang, L.J. and Liu, Z.C. and Gao, J.F.",
TITLE = "Vision-Language Pre-Training:
Basics, Recent Advances, and Future Trends",
JOURNAL = FTCGV,
VOLUME = "14",
YEAR = "2022",
NUMBER = "3-4",
PAGES = "163-352",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235833"}
@article{bb240919,
AUTHOR = "Zhang, F. and Wang, R.M. and Zhou, F. and Luo, Y.M.",
TITLE = "ERM: Energy-Based Refined-Attention Mechanism for Video Question
Answering",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "3",
MONTH = "March",
PAGES = "1454-1467",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235834"}
@article{bb240920,
AUTHOR = "Yang, J. and Jang, H. and Yu, K.",
TITLE = "Analyzing Geographic Questions Using Embedding-based Topic Modeling",
JOURNAL = IJGI,
VOLUME = "12",
YEAR = "2023",
NUMBER = "2",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235835"}
@inproceedings{bb240921,
AUTHOR = "Zhao, S.W. and Liu, Y.Y. and Du, S.Y. and Tian, Z.Q. and Qu, T. and Xu, L.H.",
TITLE = "CMFG: Cross-model Fine-grained Feature Interaction for Text-video
Retrieval",
BOOKTITLE = MMMod23,
YEAR = "2023",
PAGES = "II: 435-445",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235836"}
@article{bb240922,
AUTHOR = "Luo, H.N. and Lin, G.S. and Yao, Y.Z. and Liu, F.Y. and Liu, Z.C. and Tang, Z.M.",
TITLE = "Depth and Video Segmentation Based Visual Attention for Embodied
Question Answering",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "6807-6819",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235837"}
@inproceedings{bb240923,
AUTHOR = "Luo, H.N. and Lin, G.S. and Liu, Z.C. and Liu, F.Y. and Tang, Z.M. and Yao, Y.Z.",
TITLE = "SegEQA: Video Segmentation Based Visual Attention for Embodied
Question Answering",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "9666-9675",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235838"}
@article{bb240924,
AUTHOR = "Zhang, X. and Zhang, F.F. and Xu, C.S.",
TITLE = "Reducing Vision-Answer Biases for Multiple-Choice VQA",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "4621-4634",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235839"}
@article{bb240925,
AUTHOR = "Xiao, J.B. and Zhou, P. and Yao, A. and Li, Y.C. and Hong, R.C. and Yan, S.C. and Chua, T.S.",
TITLE = "Contrastive Video Question Answering via Video Graph Transformer",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "11",
MONTH = "November",
PAGES = "13265-13280",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235840"}
@inproceedings{bb240926,
AUTHOR = "Xiao, J.B. and Zhou, P. and Chua, T.S. and Yan, S.C.",
TITLE = "Video Graph Transformer for Video Question Answering",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:39-58",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235841"}
@article{bb240927,
AUTHOR = "Shen, W.X. and Song, J.K. and Zhu, X.S. and Li, G.F. and Shen, H.T.",
TITLE = "End-to-End Pre-Training With Hierarchical Matching and Momentum
Contrast for Text-Video Retrieval",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "5017-5030",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235842"}
@article{bb240928,
AUTHOR = "Jiang, J.J. and Liu, Z. and Zheng, N.N.",
TITLE = "LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video
Question Answering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "5002-5013",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235843"}
@article{bb240929,
AUTHOR = "Xu, F.F. and Zhu, Y. and Wang, C. and Cao, Y.Z. and Zhong, Z. and Li, X.M.",
TITLE = "Spatio-Temporal Two-stage Fusion for video question answering",
JOURNAL = CVIU,
VOLUME = "237",
YEAR = "2023",
PAGES = "103821",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235844"}
@article{bb240930,
AUTHOR = "Wang, Y.Y. and Liu, M. and Wu, J.L. and Nie, L.Q.",
TITLE = "Multi-Granularity Interaction and Integration Network for Video
Question Answering",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "12",
MONTH = "December",
PAGES = "7684-7695",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235845"}
@article{bb240931,
AUTHOR = "Bai, Z. and Wang, R.P. and Gao, D.F. and Chen, X.L.",
TITLE = "Event Graph Guided Compositional Spatial-Temporal Reasoning for Video
Question Answering",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "1109-1121",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235846"}
@article{bb240932,
AUTHOR = "Qian, T.W. and Cui, R. and Chen, J.J. and Peng, P. and Guo, X.W. and Jiang, Y.G.",
TITLE = "Locate Before Answering: Answer Guided Question Localization for
Video Question Answering",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "4554-4563",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235847"}
@article{bb240933,
AUTHOR = "Cheng, Y. and Fan, H. and Lin, D.Y. and Sun, Y. and Kankanhalli, M. and Lim, J.H.",
TITLE = "Keyword-Aware Relative Spatio-Temporal Graph Networks for Video
Question Answering",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "6131-6141",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235848"}
@article{bb240934,
AUTHOR = "Jiang, Y.M. and Yan, T.F. and Yao, M.Z. and Wang, H.B. and Liu, W.Z.",
TITLE = "Cascade transformers with dynamic attention for video question
answering",
JOURNAL = CVIU,
VOLUME = "242",
YEAR = "2024",
PAGES = "103983",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235849"}
@article{bb240935,
AUTHOR = "Yu, T. and Fu, K. and Zhang, J. and Huang, Q.M. and Yu, J.",
TITLE = "Multi-Granularity Contrastive Cross-Modal Collaborative Generation
for End-to-End Long-Term Video Question Answering",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "3115-3129",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235850"}
@article{bb240936,
AUTHOR = "Liu, J. and Wang, G.X. and Xie, J.L. and Zhou, F.Y. and Xu, H.J.",
TITLE = "Video Question Answering with Semantic Disentanglement and Reasoning",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "3663-3673",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235851"}
@article{bb240937,
AUTHOR = "Nie, J. and Wang, X. and Hou, R.Z. and Li, G.H. and Chen, H. and Zhu, W.W.",
TITLE = "Dynamic Spatio-Temporal Graph Reasoning for VideoQA With
Self-Supervised Event Recognition",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "4145-4158",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235852"}
@article{bb240938,
AUTHOR = "Lee, S. and Kim, H.I. and Ro, Y.M.",
TITLE = "Text-guided distillation learning to diversify video embeddings for
text-video retrieval",
JOURNAL = PR,
VOLUME = "156",
YEAR = "2024",
PAGES = "110754",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235853"}
@article{bb240939,
AUTHOR = "Fei, H. and Wu, S.Q. and Zhang, M. and Zhang, M. and Chua, T.S. and Yan, S.C.",
TITLE = "Enhancing Video-Language Representations With Structural
Spatio-Temporal Alignment",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "7701-7719",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235854"}
@article{bb240940,
AUTHOR = "Wang, R.M. and Luo, Y.M. and Zhang, F. and Liu, M.Y. and Luo, X.N.",
TITLE = "HSSHG: Heuristic Semantics-Constrained Spatio-Temporal Heterogeneous
Graph for VideoQA",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "11176-11190",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235855"}
@article{bb240941,
AUTHOR = "Jeshmol, P.J. and Kovoor, B.C.",
TITLE = "Video Question Answering: A survey of the state-of-the-art",
JOURNAL = JVCIR,
VOLUME = "105",
YEAR = "2024",
PAGES = "104320",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235856"}
@article{bb240942,
AUTHOR = "Wu, X.Z. and Wu, J. and Zhu, L. and Senhadji, L. and Shu, H.Z.",
TITLE = "Collaborative Aware Bidirectional Semantic Reasoning for Video
Question Answering",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "3",
MONTH = "March",
PAGES = "2074-2086",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235857"}
@article{bb240943,
AUTHOR = "Yang, A. and Miech, A. and Sivic, J. and Laptev, I. and Schmid, C.",
TITLE = "Learning to Answer Visual Questions From Web Videos",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "3202-3218",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235858"}
@inproceedings{bb240944,
AUTHOR = "Yang, A. and Miech, A. and Sivic, J. and Laptev, I. and Schmid, C.",
TITLE = "Just Ask:
Learning to Answer Questions from Millions of Narrated Videos",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1666-1677",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235859"}
@article{bb240945,
AUTHOR = "Jiang, Y.Y. and Yin, J.Q.",
TITLE = "CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual
Question Answering",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "2581-2598",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235860"}
@article{bb240946,
AUTHOR = "Wang, Y.Y. and Liu, M. and Song, X.M. and Nie, L.Q.",
TITLE = "TR-Adapter: Parameter-Efficient Transfer Learning for Video Question
Answering",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "2232-2242",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235861"}
@article{bb240947,
AUTHOR = "Xiao, J.B. and Huang, N.X. and Qin, H.Y. and Li, D.Y. and Li, Y.C. and Zhu, F.B. and Tao, Z. and Yu, J.X. and Lin, L. and Chua, T.S. and Yao, A.",
TITLE = "VideoQA in the Era of LLMs: An Empirical Study",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "3970-3993",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235862"}
@article{bb240948,
AUTHOR = "Liang, T.M. and Li, L.H. and Hu, J.F. and Yu, X.Y. and Zheng, W.S. and Lai, J.H.",
TITLE = "Rethinking Temporal Context in Video-QA:
A Comprehensive Study of Single-Frame Static Bias",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "5077-5091",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235863"}
@article{bb240949,
AUTHOR = "Qin, Y.X. and Zhao, L. and Gao, L. and Zhang, H.N. and Zeng, P.P. and Shen, H.T.",
TITLE = "Temporal-Guided Mixture-of-Experts for Zero-Shot Video Question
Answering",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "9",
MONTH = "September",
PAGES = "9003-9016",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235864"}
@article{bb240950,
AUTHOR = "Wang, H.B. and Lai, C.H. and Ge, W.F.",
TITLE = "Adapting Multimodal Large Language Models for Video Question
Answering by Capturing Question-Critical and Coherent Moments",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "8737-8747",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235865"}
@inproceedings{bb240951,
AUTHOR = "Gia, B.T. and Le, K. and Do, T. and Mai, T.D. and Ngo, T.D. and Le, D.D. and Satoh, S.",
TITLE = "VRAG: Retrieval-Augmented Video Question Answering for Long-Form
Videos",
BOOKTITLE = IntVidSea25,
YEAR = "2025",
PAGES = "3689-3698",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235866"}
@article{bb240952,
AUTHOR = "Song, E. and Chai, W.H. and Ye, T. and Hwang, J.N. and Li, X. and Wang, G.A.",
TITLE = "MovieChat+: Question-Aware Sparse Memory for Long Video Question
Answering",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "374-389",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235867"}
@article{bb240953,
AUTHOR = "Zhou, S. and Xiao, J.B. and Yang, X. and Song, P.P. and Guo, D. and Yao, A. and Wang, M. and Chua, T.S.",
TITLE = "Scene-Text Grounding for Text-Based Video Question Answering",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "1417-1430",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235868"}
@inproceedings{bb240954,
AUTHOR = "Zhou, S. and Xiao, J.B. and Li, Q.Y. and Li, Y.C. and Yang, X. and Guo, D. and Wang, M. and Chua, T.S. and Yao, A.",
TITLE = "EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question
Answering",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3363-3373",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235869"}
@article{bb240955,
AUTHOR = "Gong, H.B. and Yan, C.G. and Zhang, J. and Sun, Y.Q. and Gao, Y.H. and Li, L.",
TITLE = "Spatial-Temporal Clue Reasoning Chain for Long Video Question
Answering",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "2757-2770",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235870"}
@inproceedings{bb240956,
AUTHOR = "Chowdhury, M.I. and Aukkapinyo, K. and Fujimura, H. and Woo, J.A. and Wasusatein, W. and Ghourabi, F.",
TITLE = "Grid-Logat: Grid Based Local And Global Area Transcription For Video
Question Answering",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "1247-1252",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235871"}
@inproceedings{bb240957,
AUTHOR = "Parikh, C. and Rawat, D. and Rakshitha, R.T. and Ghosh, T. and Sarvadevabhatla, R.K.",
TITLE = "RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event
Understanding from Social Video Narratives",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19002-19011",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235872"}
@inproceedings{bb240958,
AUTHOR = "Azad, S. and Vineet, V. and Rawat, Y.S.",
TITLE = "HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video
Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8545-8556",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235873"}
@inproceedings{bb240959,
AUTHOR = "Chen, W.X. and Liu, Y. and Chen, B.L. and Su, J. and Zheng, Y. and Lin, L.",
TITLE = "Cross-modal Causal Relation Alignment for Video Question Grounding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24087-24096",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235874"}
@inproceedings{bb240960,
AUTHOR = "Yi, J.H. and Wasim, S.T. and Luo, Y. and Naseer, M. and Gall, J.",
TITLE = "Video-Panda: Parameter-efficient Alignment for Encoder-free
Video-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24119-24128",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235875"}
@inproceedings{bb240961,
AUTHOR = "Islam, M.M. and Nagarajan, T. and Wang, H.Y. and Bertasius, G. and Torresani, L.",
TITLE = "BIMBA: Selective-Scan Compression for Long-Range Video Question
Answering",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29096-29107",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235876"}
@inproceedings{bb240962,
AUTHOR = "Cheng, F. and Wang, Z.Y. and Sung, Y.L. and Lin, Y.B. and Bansal, M. and Bertasius, G.",
TITLE = "Dam: Dynamic Adapter Merging for Continual Video QA Learning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6805-6817",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235877"}
@inproceedings{bb240963,
AUTHOR = "Chen, X.Y. and Lin, Y. and Zhang, Y.C. and Huang, W.R.",
TITLE = "Autoeval-video: An Automatic Benchmark for Assessing Large Vision
Language Models in Open-ended Video Question Answering",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXVIII: 179-195",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235878"}
@inproceedings{bb240964,
AUTHOR = "Wang, X. and Liang, J. and Wang, C.K. and Deng, K. and Lou, Y. and Lin, M.C. and Yang, S.",
TITLE = "Vila: Efficient Video-language Alignment for Video Question Answering",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXII: 186-204",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235879"}
@inproceedings{bb240965,
AUTHOR = "Choudhury, R. and Niinuma, K. and Kitani, K.M. and Jeni, L.A.",
TITLE = "Video Question Answering with Procedural Programs",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXVIII: 315-332",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235880"}
@inproceedings{bb240966,
AUTHOR = "Xiao, J.B. and Yao, A. and Li, Y.C. and Chua, T.S.",
TITLE = "Can I Trust Your Answer? Visually Grounded Video Question Answering",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13204-13214",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235881"}
@inproceedings{bb240967,
AUTHOR = "Min, J. and Buch, S. and Nagrani, A. and Cho, M. and Schmid, C.",
TITLE = "MoReVQA: Exploring Modular Reasoning Models for Video Question
Answering",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13235-13245",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235882"}
@inproceedings{bb240968,
AUTHOR = "Zou, B. and Yang, C. and Qiao, Y. and Quan, C.B. and Zhao, Y.J.",
TITLE = "Language-aware Visual Semantic Distillation for Video Question
Answering",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27103-27113",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235883"}
@inproceedings{bb240969,
AUTHOR = "Liang, T.M. and Tan, C.L. and Xia, B.H. and Zheng, W.S. and Hu, J.F.",
TITLE = "Ranking Distillation for Open-Ended Video Question Answering with
Insufficient Labels",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13161-13170",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235884"}
@inproceedings{bb240970,
AUTHOR = "Wu, J.M. and Shu, P.C. and Hong, H.Y. and Ma, L. and Zhu, Y. and Wang, L.",
TITLE = "Pre-trained Bidirectional Dynamic Memory Network For Long Video
Question Answering",
BOOKTITLE = Crowded24,
YEAR = "2024",
PAGES = "5550-5557",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235885"}
@inproceedings{bb240971,
AUTHOR = "Inoue, Y. and Yada, Y. and Tanahashi, K. and Yamaguchi, Y.",
TITLE = "NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous
Driving Datasets using Markup Annotations",
BOOKTITLE = LLVMCrive24,
YEAR = "2024",
PAGES = "930-938",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235886"}
@inproceedings{bb240972,
AUTHOR = "Park, S.Y. and Lee, M.J. and Kang, J.H. and Choi, H. and Park, Y. and Cho, J. and Lee, A. and Kim, D.K.",
TITLE = "VLAAD: Vision and Language Assistant for Autonomous Driving",
BOOKTITLE = LLVMCrive24,
YEAR = "2024",
PAGES = "980-987",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235887"}
@inproceedings{bb240973,
AUTHOR = "Fang, J.Z.Y. and Zheng, S. and Sharma, V. and Piramuthu, R.",
TITLE = "epislon-ViLM: Efficient Video-Language Model via Masked Video Modeling
with Semantic Vector-Quantized Tokenizer",
BOOKTITLE = Pretrain24,
YEAR = "2024",
PAGES = "529-540",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235888"}
@inproceedings{bb240974,
AUTHOR = "Zonneveld, A. and Gatt, A. and Calixto, I.",
TITLE = "Video-and-Language (VidL) models and their cognitive relevance",
BOOKTITLE = MMFM23,
YEAR = "2023",
PAGES = "325-338",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235889"}
@inproceedings{bb240975,
AUTHOR = "Momeni, L. and Caron, M. and Nagrani, A. and Zisserman, A. and Schmid, C.",
TITLE = "Verbs in Action: Improving verb understanding in video-language
models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15533-15545",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235890"}
@inproceedings{bb240976,
AUTHOR = "Jin, P. and Li, H. and Cheng, Z. and Li, K. and Ji, X.Y. and Liu, C. and Yuan, L. and Chen, J.",
TITLE = "DiffusionRet: Generative Text-Video Retrieval with Diffusion Model",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2470-2481",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235891"}
@inproceedings{bb240977,
AUTHOR = "Li, P.D. and Xie, C.W. and Zhao, L.M. and Xie, H.T. and Ge, J.N. and Zheng, Y. and Zhao, D.L. and Zhang, Y.D.",
TITLE = "Progressive Spatio-Temporal Prototype Matching for Text-Video
Retrieval",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "4077-4087",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235892"}
@inproceedings{bb240978,
AUTHOR = "Guan, P.Y. and Pei, R.J. and Shao, B. and Liu, J.Z. and Li, W.M. and Gu, J.X. and Xu, H. and Xu, S.C. and Yan, Y. and Lam, E.Y.",
TITLE = "PIDRo: Parallel Isomeric Attention with Dynamic Routing for
Text-Video Retrieval",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "11130-11139",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235893"}
@inproceedings{bb240979,
AUTHOR = "Deng, C.R. and Chen, Q. and Qin, P. and Chen, D. and Wu, Q.",
TITLE = "Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15602-15612",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT235894"}
@inproceedings{bb240980,
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#TT235895"}
@inproceedings{bb240981,
AUTHOR = "Ahmad, M. and Park, G. and Park, D. 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#TT235896"}
@inproceedings{bb240982,
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#TT235897"}
@inproceedings{bb240983,
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#TT235898"}
@inproceedings{bb240984,
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#TT235899"}
@inproceedings{bb240985,
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#TT235900"}
@inproceedings{bb240986,
AUTHOR = "Li, J. 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#TT235901"}
@inproceedings{bb240987,
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#TT235902"}
@inproceedings{bb240988,
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#TT235903"}
@inproceedings{bb240989,
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#TT235904"}
@inproceedings{bb240990,
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#TT235905"}
@inproceedings{bb240991,
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#TT235906"}
@inproceedings{bb240992,
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#TT235907"}
@inproceedings{bb240993,
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#TT235908"}
@inproceedings{bb240994,
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#TT235909"}
@inproceedings{bb240995,
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#TT235910"}
@inproceedings{bb240996,
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#TT235911"}
@inproceedings{bb240997,
AUTHOR = "Zhang, M. 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#TT235912"}
@inproceedings{bb240998,
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#TT235913"}
@inproceedings{bb240999,
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#TT235914"}
Last update:Mar 28, 2026 at 17:09:41