Text Detection
Text detection, the task of automatically locating textual regions within images and videos, aims to improve machine understanding of visual data containing text. Current research focuses on enhancing robustness to diverse backgrounds, artistic styles, and varying text granularities, employing deep learning architectures like transformers and convolutional neural networks, often combined with techniques like attention mechanisms and feature fusion. These advancements are crucial for applications ranging from automated document processing and scene understanding to combating misinformation spread through AI-generated text detection, impacting fields like computer vision, natural language processing, and information security.
Papers
DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xinyi Yang, Yulin Yuan, Lidia S. Chao
GigaCheck: Detecting LLM-generated Content
Irina Tolstykh, Aleksandra Tsybina, Sergey Yakubson, Aleksandr Gordeev, Vladimir Dokholyan, Maksim Kuprashevich
Training-free LLM-generated Text Detection by Mining Token Probability Sequences
Yihuai Xu, Yongwei Wang, Yifei Bi, Huangsen Cao, Zhouhan Lin, Yu Zhao, Fei Wu
Mero Nagarikta: Advanced Nepali Citizenship Data Extractor with Deep Learning-Powered Text Detection and OCR
Sisir Dhakal, Sujan Sigdel, Sandesh Prasad Paudel, Sharad Kumar Ranabhat, Nabin Lamichhane