The history of text can be traced back over thousands of years. Rich and precise semantic
information carried by text is important in a wide range of vision-based application …

In this paper, a comparative experimental assessment of computer vision-based methods for
sign language recognition is conducted. By implementing the most recent deep neural …

The diversity in length constitutes a significant characteristic of text. Due to the long-tail
distribution of text lengths, most existing methods for scene text recognition (STR) only work …

Continuous sign language recognition (CSLR) aims to recognize glosses in a sign language
video. State-of-the-art methods typically have two modules, a spatial perception module and …

Text recognition is critical in various domains, including driving assistance, handwriting
recognition, and aiding the visually impaired. In recent years, deep learning-based methods …

End-to-end simultaneous speech translation (SST), which directly translates speech in one
language into text in another language in real-time, is useful in many scenarios but has not …

Text recognition methods are gaining rapid development. Some advanced techniques, eg,
powerful modules, language models, and un-and semi-supervised learning schemes …

Abstract Connectionist Temporal Classification (CTC) is a popular objective function in
sequence recognition, which provides supervision for unsegmented sequence data through …

Connectionist temporal classification (CTC) models are known to have peaky output
distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it …

Each year, hundreds of thousands of people contract Healthcare Associated Infections
(HAIs). Poor hand hygiene compliance among healthcare workers is thought to be the …