{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T17:50:19Z","timestamp":1785865819704,"version":"3.56.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62422204"],"award-info":[{"award-number":["62422204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125201"],"award-info":[{"award-number":["62125201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B20174"],"award-info":[{"award-number":["U24B20174"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072147"],"award-info":[{"award-number":["62072147"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LR22F020001"],"award-info":[{"award-number":["LR22F020001"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F02025F02"],"award-info":[{"award-number":["LDT23F02025F02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tpami.2025.3562422","type":"journal-article","created":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T17:37:49Z","timestamp":1744997869000},"page":"6797-6808","source":"Crossref","is-referenced-by-count":10,"title":["Prophet: Prompting Large Language Models With Complementary Answer Heuristics for Knowledge-Based Visual Question Answering"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-1137","authenticated-orcid":false,"given":"Zhou","family":"Yu","sequence":"first","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science, Hangzhou Dianzi University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuecheng","family":"Ouyang","sequence":"additional","affiliation":[{"name":"HDU-ITMO Joint Institute, Hangzhou Dianzi University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3069-9347","authenticated-orcid":false,"given":"Zhenwei","family":"Shao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science, Hangzhou Dianzi University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3023438"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref7","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref11","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref12","first-page":"21218","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref23","first-page":"10560","article-title":"REVIVE: Regional visual representation matters in knowledge-based visual question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref25","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref28","article-title":"How much can clip benefit vision-and-language tasks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref30","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref31","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475251"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00277"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref41","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref42","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref49","article-title":"LLAMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref50","article-title":"Mistral 7B","year":"2023"},{"key":"ref51","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref52","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022"},{"key":"ref53","article-title":"PALI: A jointly-scaled multilingual language-image model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547870"},{"key":"ref56","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai","year":"2023"},{"key":"ref57","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.734"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11068886\/10970423.pdf?arnumber=10970423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:56:54Z","timestamp":1751929014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10970423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":59,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3562422","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}