{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:24Z","timestamp":1764399084821,"version":"3.46.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249117","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"2430-2435","source":"Crossref","is-referenced-by-count":0,"title":["Zero-shot Artistic Text Recognition with Multimodal Language Models"],"prefix":"10.1109","author":[{"given":"Tien","family":"Do","sequence":"first","affiliation":[{"name":"University of Information Technology, VNU-HCM,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thuyen","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Information Technology, VNU-HCM,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duy-Dinh","family":"Le","sequence":"additional","affiliation":[{"name":"University of Information Technology, VNU-HCM,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thanh Duc","family":"Ngo","sequence":"additional","affiliation":[{"name":"University of Information Technology, VNU-HCM,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"1","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","volume":"9","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"volume-title":"Qwen2.5-vl technical report","year":"2025","author":"Bai","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04630-7_17"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.43"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/197"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw50498.2020.00281"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3223908"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00922"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref28","first-page":"1288812900","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref29","first-page":"9125","article-title":"Detclip: Dictionary-enriched visualconcept paralleled pre-training for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01984"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611769"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3512354"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref35","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249117.pdf?arnumber=11249117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:24Z","timestamp":1764399024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249117\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249117","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}