Accelerating DETR convergence via semantic-aligned matching

G Zhang, Z Luo, Y Yu, K Cui… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Abstract The recently developed DEtection TRansformer (DETR) establishes a new object
detection paradigm by eliminating a series of hand-crafted components. However, DETR …

Maskocr: Text recognition with masked encoder-decoder pretraining

P Lyu, C Zhang, S Liu, M Qiao, Y Xu, L Wu… - arxiv preprint arxiv …, 2022 - arxiv.org
Text images contain both visual and linguistic information. However, existing pre-training
techniques for text recognition mainly focus on either visual representation learning or …

Language matters: A weakly supervised vision-language pre-training approach for scene text detection and spotting

C Xue, W Zhang, Y Hao, S Lu, PHS Torr… - European Conference on …, 2022 - Springer
Abstract Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited
various vision-language tasks by jointly learning visual and textual representations, which …

Performance enhancement method for multiple license plate recognition in challenging environments

K Khan, A Imran, HZU Rehman, A Fazil… - EURASIP Journal on …, 2021 - Springer
Multiple-license plate recognition is gaining popularity in the Intelligent Transport System
(ITS) applications for security monitoring and surveillance. Advancements in acquisition …

[HTML][HTML] An effective method for detection and recognition of Uyghur texts in images with backgrounds

M Ibrayim, A Mattohti, A Hamdulla - Information, 2022 - mdpi.com
Uyghur text detection and recognition in images with simple backgrounds is still a
challenging task for Uyghur image content analysis. In this paper, we propose a new …

Maskocr: Scene text recognition with masked vision-language pre-training

P Lyu, C Zhang, S Liu, M Qiao, Y Xu, L Wu… - … on Machine Learning …, 2024 - openreview.net
Text images contain both visual and linguistic information. However, existing pre-training
techniques for text recognition mainly focus on either visual representation learning or …

Contextual text block detection towards scene text understanding

C Xue, J Huang, W Zhang, S Lu, C Wang… - European Conference on …, 2022 - Springer
Most existing scene text detectors focus on detecting characters or words that only capture
partial text messages due to missing contextual information. For a better understanding of …

Research on text recognition of natural scenes for complex situations

W Yu, M Ibrayim, A Hamdulla - 2022 3rd International …, 2022 - ieeexplore.ieee.org
As a great invention that affects human development and progress, writing plays an
essential role in human life and learning and the inheritance and development of culture …

[PDF][PDF] Tag recognition from panoramic scans of industrial facilities

E Dahlberg, T Lehtonen, M Yllikäinen - 2022 - utupub.fi
This work contrasts practical requirements of industry with the theory and research behind
text detection and recognition, with experiments conducted to confirm the feasibility of a …

A Model of Vietnamese Optical Character Recognition

KT Huynh, CM Tran, HS Le - 2022 RIVF International …, 2022 - ieeexplore.ieee.org
Optical Character Recognition (OCR) is a method to transform images in words into digital
documents in the computer vision field. This helps digital or hand-written words and …