{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T01:29:33Z","timestamp":1790731773247,"version":"4.1.0"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["62431020"],"award-info":[{"award-number":["62431020"]}],"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":["62406231"],"award-info":[{"award-number":["62406231"]}],"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":["62231027"],"award-info":[{"award-number":["62231027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Fund Project of National Natural Science Foundation of China","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}]},{"name":"Postdoctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZC20232033"],"award-info":[{"award-number":["GZC20232033"]}]},{"name":"Fund for Foreign Scholars in University Research and Teaching Programs","award":["B07048"],"award-info":[{"award-number":["B07048"]}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT_15R53"],"award-info":[{"award-number":["IRT_15R53"]}]},{"name":"Key Scientific Technological Innovation Research Project by the Ministry of Education"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["YJSJ25004"],"award-info":[{"award-number":["YJSJ25004"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYTS25211"],"award-info":[{"award-number":["ZYTS25211"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Fund of Xidian University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tpami.2025.3581174","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T13:38:41Z","timestamp":1750340321000},"page":"8725-8739","source":"Crossref","is-referenced-by-count":10,"title":["Visual-Language Scene-Relation-Aware Zero-Shot Captioner"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-3881","authenticated-orcid":false,"given":"Qianyue","family":"Bao","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2604-4381","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2002-3894","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-1426","authenticated-orcid":false,"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3335859"},{"key":"ref4","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/c2019-0-00628-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3135248"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3194869"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3289293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3401711"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3389454"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939201"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3102098"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3395844"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185638"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3174873"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328298"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3408684"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402242"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2385695"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR55827.2022.00037"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132229"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548199"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111452"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3386339"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107110"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2994057"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185320"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2813306"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3144984"},{"key":"ref45","article-title":"DeCap: Decoding CLIP latents for zero-shot captioning via text-only training","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Li"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00291"},{"issue":"8","key":"ref47","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref48","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02247"},{"key":"ref51","article-title":"Language models can see: Plugging visual controls in text generation","author":"Su","year":"2022"},{"key":"ref52","article-title":"Zero-shot video captioning with evolving pseudo-tokens","author":"Tewel","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3371376"},{"key":"ref56","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00252"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339628"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159811"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612388"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3365104"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894139"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_13"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3042192"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119754"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3387724"},{"key":"ref72","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref73","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":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3467229"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521729"},{"key":"ref76","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref77","article-title":"RLAIF: Scaling reinforcement learning from human feedback with AI feedback","author":"Lee","year":"2023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10061-9"},{"key":"ref79","first-page":"33229","article-title":"Tuning computer vision models with task rewards","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.705"},{"key":"ref81","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","author":"Zhao","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref84","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref87","article-title":"Diagnosing and rectifying vision models using language","author":"Zhang","year":"2023"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref91","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref93","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref101","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.681"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11163533\/11045221.pdf?arnumber=11045221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:10:53Z","timestamp":1758028253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":104,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3581174","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":[[2025,10]]}}}