{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T23:48:58Z","timestamp":1769557738584,"version":"3.49.0"},"reference-count":48,"publisher":"Tsinghua University Press","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271125"],"award-info":[{"award-number":["62271125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Big Data Min. Anal."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.26599\/bdma.2025.9020032","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:39:39Z","timestamp":1757957979000},"page":"1418-1431","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Knowledge-Based Visual Question Answering with Frozen Language Models"],"prefix":"10.26599","volume":"8","author":[{"given":"Jing","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"}]},{"given":"Lizong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"}]},{"given":"Chenpeng","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"}]},{"given":"Yinong","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"}]},{"given":"Chong","family":"Mu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"}]},{"given":"Jiaxin","family":"Li","sequence":"additional","affiliation":[{"name":"Miaozhendida (Beijing) Network Technology Co. Ltd.,Beijing,China,100085"}]}],"member":"11138","reference":[{"key":"ref1","first-page":"1","article-title":"An explanation of in-context learning as implicit Bayesian inference","volume-title":"Proc. 10th Int. Conf. Learning Representations, Virtual Event","author":"Xie","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2024.9020046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"ref6","article-title":"Enhancing aspect-based sentiment analysis in tourism using large language models and positional information","author":"Xu","journal-title":"Tsinghua Science and Technology."},{"key":"ref7","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. 35th Int. Conf. Neural Information Processing Systems, Virtual Event","author":"Tsimpoukelli","year":"2021"},{"key":"ref8","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. 36th Int. Conf. Neural Information Processing Systems","author":"Alayrac"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2024.9020026"},{"key":"ref12","first-page":"2472","article-title":"Exploring question decomposition for zero-shot VQA","volume-title":"Proc. 37th Int. Conf. Neural Information Processing Systems","author":"Khan"},{"key":"ref13","first-page":"533","article-title":"Knowledge generation for zero-shot knowledge-based VQA","volume-title":"Proc. Findings of the Association for Computational Linguistics: EACL 2024","author":"Cao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.256"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnlest.2022.100159"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124561"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2023.100190"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2023.9010060"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462987"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.772"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110368"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.590"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.67"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.171"},{"key":"ref38","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref41","first-page":"12888","article-title":"BLIP: Bootstrappinglanguage-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Machine Learning","author":"Li"},{"key":"ref42","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127505"},{"key":"ref44","article-title":"ClipCap: Clip prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"PromptCap: Prompt-guided task-aware image captioning","author":"Hu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. 38th Int. Conf. Machine Learning, Virtual Event","author":"Cho","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.187"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.197"}],"container-title":["Big Data Mining and Analytics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8254253\/11164402\/11164407.pdf?arnumber=11164407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:36:14Z","timestamp":1758044174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.26599\/bdma.2025.9020032","relation":{},"ISSN":["2096-0654","2097-406X"],"issn-type":[{"value":"2096-0654","type":"print"},{"value":"2097-406X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}