已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition

计算机科学 粒度 人工智能 语言模型 自然语言处理 概括性 代表(政治) 光学字符识别 机器学习 图像(数学) 心理学 政治学 政治 操作系统 法学 心理治疗师
作者
Cheng Da,Peng Wang,Cong Yao
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:4
标识
DOI:10.48550/arxiv.2307.13244
摘要

Due to the enormous technical challenges and wide range of applications, scene text recognition (STR) has been an active research topic in computer vision for years. To tackle this tough problem, numerous innovative methods have been successively proposed, and incorporating linguistic knowledge into STR models has recently become a prominent trend. In this work, we first draw inspiration from the recent progress in Vision Transformer (ViT) to construct a conceptually simple yet functionally powerful vision STR model, which is built upon ViT and a tailored Adaptive Addressing and Aggregation (A$^3$) module. It already outperforms most previous state-of-the-art models for scene text recognition, including both pure vision models and language-augmented methods. To integrate linguistic knowledge, we further propose a Multi-Granularity Prediction strategy to inject information from the language modality into the model in an implicit way, \ie, subword representations (BPE and WordPiece) widely used in NLP are introduced into the output space, in addition to the conventional character level representation, while no independent language model (LM) is adopted. To produce the final recognition results, two strategies for effectively fusing the multi-granularity predictions are devised. The resultant algorithm (termed MGP-STR) is able to push the performance envelope of STR to an even higher level. Specifically, MGP-STR achieves an average recognition accuracy of $94\%$ on standard benchmarks for scene text recognition. Moreover, it also achieves state-of-the-art results on widely-used handwritten benchmarks as well as more challenging scene text datasets, demonstrating the generality of the proposed MGP-STR algorithm. The source code and models will be available at: \url{https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/MGP-STR}.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Dyeing发布了新的文献求助10
刚刚
大葱鸭发布了新的文献求助10
刚刚
天瑜完成签到 ,获得积分10
刚刚
万能图书馆应助鱼憨儿采纳,获得10
刚刚
N你好完成签到,获得积分10
1秒前
Lucas应助俊逸的素采纳,获得10
1秒前
1秒前
初景发布了新的文献求助10
2秒前
爱吃芫荽完成签到 ,获得积分10
2秒前
hxx111发布了新的文献求助10
4秒前
5秒前
hoede完成签到 ,获得积分10
6秒前
6秒前
6秒前
pumpkin发布了新的文献求助10
7秒前
7秒前
唐唐完成签到,获得积分20
7秒前
LS完成签到,获得积分20
9秒前
hoede关注了科研通微信公众号
11秒前
YitingW完成签到 ,获得积分10
11秒前
11秒前
v0id应助灯影采纳,获得10
11秒前
丸子发布了新的文献求助20
12秒前
12秒前
乌鱼子发布了新的文献求助10
12秒前
Lin发布了新的文献求助10
12秒前
爱吃芫荽关注了科研通微信公众号
13秒前
13秒前
小瞎子_Zora完成签到 ,获得积分10
14秒前
科研通AI6.4应助轻松板栗采纳,获得10
14秒前
斯文败类应助聪慧的以菱采纳,获得10
16秒前
LS发布了新的文献求助30
18秒前
18秒前
瑞幸少加冰完成签到 ,获得积分10
20秒前
CipherSage应助懦弱的冰岚采纳,获得10
20秒前
科研通AI6.4应助完美千秋采纳,获得10
21秒前
hxx111发布了新的文献求助10
24秒前
24秒前
25秒前
25秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Essentials of Carbohydrate Chemistry and Biochemistry, 4th Edition 800
Navigating Normative Orders. Interdisciplinary Perspectives 800
Organizational Behavior 510
Management and the Arts 510
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
CLSI VET01S-2024 Performance Standards for Antimicrobial Disk and Dilution Susceptibility Tests for Bacteria Isolated From Animals (7th Ed) 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7759230
求助须知:如何正确求助?哪些是违规求助? 9304838
关于积分的说明 20283097
捐赠科研通 7343193
什么是DOI,文献DOI怎么找? 3312451
关于科研通互助平台的介绍 2463044
邀请新用户注册赠送积分活动 2326457