@article{bb247600,
AUTHOR = "Sun, G.L. and Liang, L. and Qiu, J. and Zhang, L.Z. and Lang, F.",
TITLE = "Leveraging Static-Dynamic Scene Parsing to Enhance Progressive
Symbolic Reasoning for Video Question Answering",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "5328-5343",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242489"}
@article{bb247601,
AUTHOR = "Wu, X. and Wang, Z. and Wu, J. and Zhu, L. and Shen, H.T.",
TITLE = "SCL: Semantic Coherence Learning for Video Question Answering",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "5821-5834",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242490"}
@article{bb247602,
AUTHOR = "Ji, Z. and Lv, W.F. and Hu, J.L. and Zhang, C. and Qiu, Z.K. and Huang, J.",
TITLE = "MotionViLA: A motion-aware video understanding model for video
localization and question answering",
JOURNAL = JVCIR,
VOLUME = "119",
YEAR = "2026",
PAGES = "104886",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242491"}
@article{bb247603,
AUTHOR = "He, H.B. and Zhong, Q. and Liu, J. and Du, B. and Wang, P. and Zhang, J.",
TITLE = "SFA: Scan, Focus, and Amplify toward guidance-aware answering for
Video TextVQA",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114009",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242492"}
@article{bb247604,
AUTHOR = "Chen, T.Y. and Liu, H.B. and Wang, Y. and Gan, C.F. and Lv, M.X. and Qin, Z.R. and Li, S.J. and Shen, L.Q. and Hou, J.H. and Wang, Z. and Lin, W.Y.",
TITLE = "Looking Beyond Visible Cues: Implicit Video Question Answering via
Dual-Clue Reasoning",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "8",
MONTH = "August",
PAGES = "351",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242493"}
@article{bb247605,
AUTHOR = "Li, J.P. and Wei, P. and Han, W.J. and Zhu, S.C. and Fan, L.F.",
TITLE = "IntentQA: Intent Question Answering in Videos by Cognitive Context
Reasoning",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "9",
MONTH = "September",
PAGES = "11044-11061",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242494"}
@article{bb247606,
AUTHOR = "Wen, M.X. and Wang, Y.X. and Zhao, X. and Jin, P.Q. and Chen, H.Y. and Li, B. and Long, Y. and Ren, Z.W. and Li, X.F. and Yang, C.M. and Zhang, H.",
TITLE = "ASTRM: Adaptive Spatio-Temporal Reasoning for Audio-Visual Question
Answering",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114470",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242495"}
@article{bb247607,
AUTHOR = "Huang, C.L. and Zhu, J. and Li, Z.L. and Guo, H.H. and Liu, J.J. and de Meo, P. and Shi, W.J.",
TITLE = "Video-Seer: A Hierarchical Scene Selection and Multi-View Analysis
Approach for Zero-Shot Video Question Answering",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "7673-7684",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242496"}
@inproceedings{bb247608,
AUTHOR = "Shin, J. and Hur, C. and Cho, S. and Choi, J. and Park, H.",
TITLE = "ReFineVQA: Iterative Refinement of Video Description via Feedback
Generation for Video Question Answering",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "7647-7657",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242497"}
@inproceedings{bb247609,
AUTHOR = "Kim, J.H. and Ko, B. and Na, J. and Yoon, J. and Kim, H.W.J.",
TITLE = "Relevance-aware Multi-context Contrastive Decoding for
Retrieval-augmented Visual Question Answering",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "8596-8605",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242498"}
@inproceedings{bb247610,
AUTHOR = "Zhang, H. and Hashimoto, A. and Hirasawa, T.",
TITLE = "Evaluating the Capability of Video Question Generation for Expert
Knowledge Elicitation",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "3047-3056",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vidq2.html#TT242499"}
@inproceedings{bb247611,
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#TT242500"}
@inproceedings{bb247612,
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#TT242501"}
@inproceedings{bb247613,
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#TT242502"}
@inproceedings{bb247614,
AUTHOR = "Chen, W.X. and Liu, Y. and Chen, B.L. and Su, J.D. 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#TT242503"}
@inproceedings{bb247615,
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#TT242504"}
@inproceedings{bb247616,
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#TT242505"}
@inproceedings{bb247617,
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#TT242506"}
@inproceedings{bb247618,
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#TT242507"}
@inproceedings{bb247619,
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#TT242508"}
@inproceedings{bb247620,
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#TT242509"}
@inproceedings{bb247621,
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#TT242510"}
@inproceedings{bb247622,
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#TT242511"}
@inproceedings{bb247623,
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#TT242512"}
@inproceedings{bb247624,
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#TT242513"}
@inproceedings{bb247625,
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#TT242514"}
@inproceedings{bb247626,
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#TT242515"}
@inproceedings{bb247627,
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#TT242516"}
@inproceedings{bb247628,
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#TT242517"}
@inproceedings{bb247629,
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#TT242518"}
@inproceedings{bb247630,
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#TT242519"}
@inproceedings{bb247631,
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#TT242520"}
@inproceedings{bb247632,
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#TT242521"}
@inproceedings{bb247633,
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.L. 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#TT242522"}
@inproceedings{bb247634,
AUTHOR = "Deng, C.R. and Chen, Q. and Qin, P.D. 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#TT242523"}
@inproceedings{bb247635,
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#TT242524"}
@inproceedings{bb247636,
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#TT242525"}
@inproceedings{bb247637,
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#TT242526"}
@inproceedings{bb247638,
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#TT242527"}
@inproceedings{bb247639,
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#TT242528"}
@inproceedings{bb247640,
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#TT242529"}
@inproceedings{bb247641,
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#TT242530"}
@inproceedings{bb247642,
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#TT242531"}
@inproceedings{bb247643,
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#TT242532"}
@inproceedings{bb247644,
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#TT242533"}
@inproceedings{bb247645,
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#TT242534"}
@inproceedings{bb247646,
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#TT242535"}
@inproceedings{bb247647,
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#TT242536"}
@inproceedings{bb247648,
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#TT242537"}
@inproceedings{bb247649,
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#TT242538"}
@inproceedings{bb247650,
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#TT242539"}
@inproceedings{bb247651,
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#TT242540"}
@inproceedings{bb247652,
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#TT242541"}
@inproceedings{bb247653,
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#TT242542"}
@inproceedings{bb247654,
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#TT242543"}
@inproceedings{bb247655,
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#TT242544"}
@inproceedings{bb247656,
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#TT242545"}
@inproceedings{bb247657,
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#TT242546"}
@inproceedings{bb247658,
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#TT242547"}
@inproceedings{bb247659,
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#TT242548"}
@inproceedings{bb247660,
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#TT242549"}
@inproceedings{bb247661,
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#TT242550"}
@inproceedings{bb247662,
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#TT242551"}
@inproceedings{bb247663,
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#TT242552"}
@inproceedings{bb247664,
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#TT242553"}
@inproceedings{bb247665,
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#TT242554"}
@inproceedings{bb247666,
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#TT242555"}
@inproceedings{bb247667,
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#TT242556"}
@inproceedings{bb247668,
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#TT242557"}
@inproceedings{bb247669,
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#TT242558"}
@inproceedings{bb247670,
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#TT242559"}
@inproceedings{bb247671,
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#TT242560"}
@inproceedings{bb247672,
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#TT242561"}
@inproceedings{bb247673,
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#TT242562"}
@inproceedings{bb247674,
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#TT242563"}
@inproceedings{bb247675,
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#TT242564"}
@inproceedings{bb247676,
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#TT242565"}
@inproceedings{bb247677,
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#TT242566"}
@inproceedings{bb247678,
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#TT242567"}
@inproceedings{bb247679,
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#TT242568"}
@inproceedings{bb247680,
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#TT242569"}
@inproceedings{bb247681,
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#TT242570"}
@inproceedings{bb247682,
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#TT242571"}
@inproceedings{bb247683,
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#TT242572"}
@article{bb247684,
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#TT242575"}
@article{bb247685,
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#TT242576"}
@article{bb247686,
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#TT242577"}
@inproceedings{bb247687,
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#TT242578"}
@inproceedings{bb247688,
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#TT242579"}
@inproceedings{bb247689,
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#TT242580"}
@article{bb247690,
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#TT242581"}
@inproceedings{bb247691,
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#TT242582"}
@article{bb247692,
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#TT242583"}
@inproceedings{bb247693,
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#TT242584"}
@inproceedings{bb247694,
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#TT242585"}
@article{bb247695,
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#TT242586"}
@inproceedings{bb247696,
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#TT242587"}
@article{bb247697,
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#TT242588"}
@article{bb247698,
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#TT242589"}
@article{bb247699,
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#TT242590"}
Last update: