{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:01:45Z","timestamp":1757628105244,"version":"3.44.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T00:00:00Z","timestamp":1754870400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T00:00:00Z","timestamp":1754870400000},"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":[[2025,8,11]]},"DOI":"10.1109\/avss65446.2025.11149953","type":"proceedings-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:30:18Z","timestamp":1757439018000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Addressing Illiteracy of Vision-Language Model in Underrepresented Language Through Image-Text Mix Augmentation Scheme"],"prefix":"10.1109","author":[{"given":"Seungju","family":"Lee","sequence":"first","affiliation":[{"name":"Samsung Software Academy for Youth,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heejung","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Software Academy for Youth,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jongwon","family":"Seo","sequence":"additional","affiliation":[{"name":"Samsung Software Academy for Youth,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minwook","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Software Academy for Youth,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seoyoung","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Software Academy for Youth,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"WonChul","family":"Shin","sequence":"additional","affiliation":[{"name":"Samsung Software Academy for Youth,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunoh","family":"Kim","sequence":"additional","affiliation":[{"name":"Computer Engineering, Dankook University,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref2","article-title":"Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset","author":"Chen","year":"2023","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref4","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/361237.361242"},{"key":"ref6","article-title":"Llama-omni: Seamless speech interaction with large language models","author":"Fang","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP56322.2022.9965292"},{"key":"ref8","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref9","article-title":"Computing korean stt error rates","author":"Jeon","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13122255"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref12","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref13","volume-title":"Hello gpt-4o","year":"2024"},{"key":"ref14","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML.","author":"Radford","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.91"},{"key":"ref16","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref17","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024"},{"key":"ref18","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"}],"event":{"name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","location":"Tainan, Taiwan","start":{"date-parts":[[2025,8,11]]},"end":{"date-parts":[[2025,8,13]]}},"container-title":["2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11149666\/11149641\/11149953.pdf?arnumber=11149953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:50:59Z","timestamp":1757483459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11149953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,11]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/avss65446.2025.11149953","relation":{},"subject":[],"published":{"date-parts":[[2025,8,11]]}}}