TY - GEN
T1 - PRIM
T2 - 30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
AU - Tian, Yanzhi
AU - Liu, Zeming
AU - Liu, Zhengyang
AU - Feng, Chong
AU - Li, Xin
AU - Huang, Heyan
AU - Guo, Yuhang
N1 - Publisher Copyright:
© 2025 Association for Computational Linguistics.
PY - 2025
Y1 - 2025
N2 - In-Image Machine Translation (IIMT) aims to translate images containing texts from one language to another. Current research of end-to-end IIMT mainly conducts on synthetic data, with simple background, single font, fixed text position, and bilingual translation, which can not fully reflect real world, causing a significant gap between the research and practical conditions. To facilitate research of IIMT in real-world scenarios, we explore Practical In-Image Multilingual Machine Translation (IIMMT). In order to convince the lack of publicly available data, we annotate the PRIM dataset, which contains real-world captured one-line text images with complex background, various fonts, diverse text positions, and supports multilingual translation directions. We propose an end-to-end model VisTrans to handle the challenge of practical conditions in PRIM, which processes visual text and background information in the image separately, ensuring the capability of multilingual translation while improving the visual quality. Experimental results indicate the VisTrans achieves a better translation quality and visual effect compared to other models. The code and dataset are available at: https://github.com/BITHLP/PRIM.
AB - In-Image Machine Translation (IIMT) aims to translate images containing texts from one language to another. Current research of end-to-end IIMT mainly conducts on synthetic data, with simple background, single font, fixed text position, and bilingual translation, which can not fully reflect real world, causing a significant gap between the research and practical conditions. To facilitate research of IIMT in real-world scenarios, we explore Practical In-Image Multilingual Machine Translation (IIMMT). In order to convince the lack of publicly available data, we annotate the PRIM dataset, which contains real-world captured one-line text images with complex background, various fonts, diverse text positions, and supports multilingual translation directions. We propose an end-to-end model VisTrans to handle the challenge of practical conditions in PRIM, which processes visual text and background information in the image separately, ensuring the capability of multilingual translation while improving the visual quality. Experimental results indicate the VisTrans achieves a better translation quality and visual effect compared to other models. The code and dataset are available at: https://github.com/BITHLP/PRIM.
UR - https://www.scopus.com/pages/publications/105040131888
U2 - 10.18653/v1/2025.emnlp-main.691
DO - 10.18653/v1/2025.emnlp-main.691
M3 - Conference contribution
AN - SCOPUS:105040131888
T3 - EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
SP - 13682
EP - 13697
BT - EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
A2 - Christodoulopoulos, Christos
A2 - Chakraborty, Tanmoy
A2 - Rose, Carolyn
A2 - Peng, Violet
PB - Association for Computational Linguistics (ACL)
Y2 - 4 November 2025 through 9 November 2025
ER -