Text design is one of the most critical procedures in poster design, as ...
Conventional detectors suffer from performance degradation when dealing ...
Text irregularities pose significant challenges to scene text recognizer...
Vision model have gained increasing attention due to their simplicity an...
Scene text editing (STE) aims to replace text with the desired one while...
Scene text spotting is of great importance to the computer vision commun...
There still remains an extreme performance gap between Vision Transforme...
Layout generation is a novel task in computer vision, which combines the...
Human Video Motion Transfer (HVMT) aims to, given an image of a source
p...
The attention-based encoder-decoder framework is becoming popular in sce...
In this paper, we abandon the dominant complex language model and rethin...
Existing scene text removal methods mainly train an elaborate network wi...
Cross-modal correlation provides an inherent supervision for video
unsup...
Cross-modal video-text retrieval, a challenging task in the field of vis...
Linguistic knowledge is of great benefit to scene text recognition. Howe...
Scene text detection has witnessed rapid development in recent years.
Ho...
Image-text matching has received growing interest since it bridges visio...
Bilinear pooling achieves great success in fine-grained visual recogniti...
Recent methods focus on learning a unified semantic-aligned visual
repre...
Zero-Shot Learning (ZSL) seeks to recognize a sample from either seen or...
Person re-identification aims to identify the same pedestrian across
non...