Text recognition is a long-standing research problem for document digitalization. Existing
approaches are usually built based on CNN for image understanding and RNN for char …

Context-aware STR methods typically use internal autoregressive (AR) language models
(LM). Inherent limitations of AR models motivated two-stage methods which employ an …

Scene text spotting is of great importance to the computer vision community due to its wide
variety of applications. Recent methods attempt to introduce linguistic knowledge for …

With advances in data-driven machine learning research, a wide variety of prediction
models have been proposed to capture spatio-temporal features for the analysis of video …

Existing text recognition methods usually need large-scale training data. Most of them rely
on synthetic training data due to the lack of annotated real images. However, there is a …

Remote sighted assistance (RSA) has emerged as a conversational technology aiding
people with visual impairments (VI) through real-time video chat communication with sighted …

Human sketch has already proved its worth in various visual understanding tasks (eg,
retrieval, segmentation, image-captioning, etc). In this paper, we reveal a new trait of …

Linguistic knowledge has brought great benefits to scene text recognition by providing
semantics to refine character sequences. However, since linguistic knowledge has been …

The transformer-based encoder-decoder framework is becoming popular in scene text
recognition, largely because it naturally integrates recognition clues from both visual and …

Typical text recognition methods rely on an encoder-decoder structure, in which the encoder
extracts features from an image, and the decoder produces recognized text from these …