QQ客服 官方微博 反馈留言

	CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition
	Jinzhi Zheng2; Ruyi Ji1; Libo Zhang2; Yanjun Wu2; Chen Zhao2
	2023
会议日期	2023.06.08
会议地点	中国
英文摘要	Scene text recognition, as a cross-modal task involving vision and text, is an important research topic in computer vision. Most existing methods use language models to extract semantic information for opti mizing visual recognition. However, the guidance of visual cues is ignored in the process of semantic mining, which limits the performance of the algorithm in recognizing irregular scene text. To tackle this issue, we pro pose a novel cross-modal fusion network (CMFN) for irregular scene text recognition, which incorporates visual cues into the semantic mining pro cess. Specifically, CMFN consists of a position self-enhanced encoder, a visual recognition branch and an iterative semantic recognition branch. The position self-enhanced encoder provides character sequence posi tion encoding for both the visual recognition branch and the iterative semantic recognition branch. The visual recognition branch carries out visual recognition based on the visual features extracted by CNN and the position encoding information provided by the position self-enhanced encoder. The iterative semantic recognition branch, which consists of a language recognition module and a cross-modal fusion gate, simulates the way that human recognizes scene text and integrates cross-modal visual cues for text recognition. The experiments demonstrate that the proposed CMFN algorithm achieves comparable performance to state of-the-art algorithms, indicating its effectiveness.
会议录出版者	International Conference on Neural Information Processing
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/58516]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Jinzhi Zheng
作者单位	1.Institute of Automation, Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Jinzhi Zheng,Ruyi Ji,Libo Zhang,et al. CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition[C]. 见:. 中国. 2023.06.08.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。