(Preprint) From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
Yuxin Wang 王裕鑫 ¹, Hongtao Xie 谢洪涛 ¹, Shancheng Fang ¹, Jing Wang ², Shenggao Zhu ², Yongdong Zhang 张勇东 ¹
¹ University of Science and Technology of China
中国科技大学
² Huawei Cloud & AI
华为云人工智能
arXiv, 2021-08-22
Abstract
In this paper, we abandon the dominant complex language model and rethink the linguistic learning process in the scene text recognition. Different from previous methods considering the visual and linguistic information in two separate structures, we propose a Visual Language Modeling Network (VisionLAN), which views the visual and linguistic information as a union by directly enduing the vision model with language capability. Specially, we introduce the text recognition of character-wise occluded feature maps in the training stage. Such operation guides the vision model to use not only the visual texture of characters, but also the linguistic information in visual context for recognition when the visual cues are confused (e.g. occlusion, noise, etc.).
As the linguistic information is acquired along with visual features without the need of extra language model, VisionLAN significantly improves the speed by 39% and adaptively considers the linguistic information to enhance the visual features for accurate recognition. Furthermore, an Occlusion Scene Text (OST) dataset is proposed to evaluate the performance on the case of missing character-wise visual cues. The state of-the-art results on several benchmarks prove our effectiveness.
High-resolution tumor marker detection based on microwave photonics demodulated dual wavelength fiber laser sensor
Jie Hu, Weihao Lin, Liyang Shao, Chenlong Xue, Fang Zhao, Dongrui Xiao, Yang Ran, Yue Meng, Panpan He, Zhiguang Yu, Jinna Chen, Perry Ping Shum
Opto-Electronic Advances
2024-12-16
Ultra-high-Q photonic crystal nanobeam cavity for etchless lithium niobate on insulator (LNOI) platform
Zhi Jiang, Cizhe Fang, Xu Ran, Yu Gao, Ruiqing Wang, Jianguo Wang, Danyang Yao, Xuetao Gan, Yan Liu, Yue Hao, Genquan Han
Opto-Electronic Advances
2024-10-31