{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T14:20:22Z","timestamp":1778768422935,"version":"3.51.4"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neucom.2026.133353","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T16:30:04Z","timestamp":1773419404000},"page":"133353","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Say it better: RL-based prompt tuning for enhancing open-vocabulary recognition"],"prefix":"10.1016","volume":"681","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2424-3260","authenticated-orcid":false,"given":"Mikhail","family":"Avshalumov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zoya","family":"Volovikova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1407-2633","authenticated-orcid":false,"given":"Dmitry","family":"Yudin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9747-3837","authenticated-orcid":false,"given":"Aleksandr","family":"Panov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.neucom.2026.133353_bib0005","doi-asserted-by":"crossref","first-page":"285","DOI":"10.3103\/S1060992X25700092","article-title":"M3DMap: object-aware multimodal 3D mapping for dynamic environments","volume":"34","author":"Yudin","year":"2025","journal-title":"Opt. Mem. Neural Netw."},{"key":"10.1016\/j.neucom.2026.133353_bib0010","author":"Zemskova"},{"key":"10.1016\/j.neucom.2026.133353_bib0015","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133353_bib0020","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","article-title":"Yolo-world: real-time open-vocabulary object detection","author":"Cheng","year":"2024"},{"key":"10.1016\/j.neucom.2026.133353_bib0025","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"11","article-title":"Generation and comprehension of unambiguous object descriptions","author":"Mao","year":"2016"},{"key":"10.1016\/j.neucom.2026.133353_bib0030","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.133353_bib0035","series-title":"European Conference on Computer Vision","first-page":"106","article-title":"Open-vocabulary DETR with conditional matching","author":"Zang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133353_bib0040","author":"Gu"},{"key":"10.1016\/j.neucom.2026.133353_bib0045","author":"Liu"},{"key":"10.1016\/j.neucom.2026.133353_bib0050","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.neucom.2026.133353_bib0055","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27\u201330, 2016","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.neucom.2026.133353_bib0060","author":"Wang"},{"key":"10.1016\/j.neucom.2026.133353_bib0065","doi-asserted-by":"crossref","first-page":"19769","DOI":"10.52202\/075280-0868","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133353_bib0070","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133353_bib0075","author":"Ziegler"},{"key":"10.1016\/j.neucom.2026.133353_bib0080","series-title":"Advances in Neural Information Processing Systems","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"vol. 33","author":"Stiennon","year":"2020"},{"key":"10.1016\/j.neucom.2026.133353_bib0085","author":"Gulcehre"},{"key":"10.1016\/j.neucom.2026.133353_bib0090","series-title":"International Conference on Machine Learning","article-title":"Aligning language models with preferences through f-divergence minimization","author":"Go","year":"2023"},{"key":"10.1016\/j.neucom.2026.133353_bib0095","author":"Khalifa"},{"key":"10.1016\/j.neucom.2026.133353_bib0100","author":"Shao"},{"key":"10.1016\/j.neucom.2026.133353_bib0105","author":"Shin"},{"key":"10.1016\/j.neucom.2026.133353_bib0110","author":"Deng"},{"key":"10.1016\/j.neucom.2026.133353_bib0115","author":"Lester"},{"key":"10.1016\/j.neucom.2026.133353_bib0120","author":"Li"},{"key":"10.1016\/j.neucom.2026.133353_bib0125","author":"Liu"},{"issue":"9","key":"10.1016\/j.neucom.2026.133353_bib0130","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.133353_bib0135","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14084","article-title":"Learning to prompt for open-vocabulary object detection with vision-language model","author":"Du","year":"2022"},{"key":"10.1016\/j.neucom.2026.133353_bib0140","series-title":"International Conference on Hybrid Artificial Intelligence Systems","first-page":"128","article-title":"Reframing: detector-specific prompt tuning for enhancing open-vocabulary object detection","author":"Avshalumov","year":"2024"},{"key":"10.1016\/j.neucom.2026.133353_bib0145","author":"Touvron"},{"key":"10.1016\/j.neucom.2026.133353_bib0150","author":"Yang"},{"key":"10.1016\/j.neucom.2026.133353_bib0155","series-title":"Trl: Transformer Reinforcement Learning","author":"von Werra","year":"2020"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226007502?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226007502?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T13:53:38Z","timestamp":1778766818000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226007502"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":31,"alternative-id":["S0925231226007502"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133353","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Say it better: RL-based prompt tuning for enhancing open-vocabulary recognition","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133353","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133353"}}