MMM
YYYY
From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
从二到一:一种新的基于视觉语言建模网络的场景文本识别器
2から1へ:視覚言語モデリングネットワークを備えた新しいシーンテキスト認識装置
2 부터 1 까지:새로운 시각 언어 모델 링 네트워크 를 바탕 으로 하 는 장면 텍스트 식별 기
De dos a uno: un nuevo identificador de texto de escena basado en la red de modelado de lenguaje visual
De deux à un: un nouvel identificateur de texte de scène basé sur un réseau de modélisation de langage visuel
от 2 до 1: новая модель, основанная на визуальном языке
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, 22 August 2021
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.
arXiv_1
arXiv_2
arXiv_3
arXiv_4
Reviews and Discussions
https://www.hotpaper.io/index.html
Self-polarized RGB device realized by semipolar micro-LEDs and perovskite-in-polymer films for backlight applications
A highly sensitive LITES sensor based on a multi-pass cell with dense spot pattern and a novel quartz tuning fork with low frequency
Multi-wavelength nanowire micro-LEDs for future high speed optical communication
Luminescence regulation of Sb3+ in 0D hybrid metal halides by hydrogen bond network for optical anti-counterfeiting
Breaking the optical efficiency limit of virtual reality with a nonreciprocal polarization rotator
Simultaneously realizing thermal and electromagnetic cloaking by multi-physical null medium
Generation of lossy mode resonances (LMR) using perovskite nanofilms
Acousto-optic scanning multi-photon lithography with high printing rate
Tailoring electron vortex beams with customizable intensity patterns by electron diffraction holography
Miniature tunable Airy beam optical meta-device
Data-driven polarimetric imaging: a review
Robust measurement of orbital angular momentum of a partially coherent vortex beam under amplitude and phase perturbations



Previous Article                                Next Article
About
|
Contact
|
Copyright © Hot Paper