Related papers: FASTER: A Font-Agnostic Scene Text Editing and Ren…
Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are…
Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications. State-of-the-art recurrent neural networks (RNN) based models map an input…
To prevent unauthorized use of text in images, Scene Text Removal (STR) has become a crucial task. It focuses on automatically removing text and replacing it with a natural, text-less background while preserving significant details such as…
Text-driven 3D indoor scene generation holds broad applications, ranging from gaming and smart homes to AR/VR applications. Fast and high-fidelity scene generation is paramount for ensuring user-friendly experiences. However, existing…
Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or…
Synthetic data has been a critical tool for training scene text detection and recognition models. On the one hand, synthetic word images have proven to be a successful substitute for real images in training scene text recognizers. On the…
Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insufficient exploration of character morphologies, including the…
Scene text removal (STR) aims at replacing text strokes in natural scenes with visually coherent backgrounds. Recent STR approaches rely on iterative refinements or explicit text masks, resulting in high complexity and sensitivity to the…
Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community. Most existing methods treat text detection and recognition as separate tasks. In this work, we propose a…
Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…
Many approaches have recently been proposed to detect irregular scene text and achieved promising results. However, their localization results may not well satisfy the following text recognition part mainly because of two reasons: 1)…
Visual appearance is considered to be the most important cue to understand images for cross-modal retrieval, while sometimes the scene text appearing in images can provide valuable information to understand the visual semantics. Most of…
In image editing tasks, high-quality text editing capabilities can significantly reduce both human and material resource costs. Existing methods, however, face significant limitations in terms of stroke accuracy for complex text and…
Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…
A new method is proposed for removing text from natural images. The challenge is to first accurately localize text on the stroke-level and then replace it with a visually plausible background. Unlike previous methods that require image…
Existing scene text removal (STR) task suffers from insufficient training data due to the expensive pixel-level labeling. In this paper, we aim to address this issue by introducing a Text-aware Masked Image Modeling algorithm (TMIM), which…
Low-resolution text images are often seen in natural scenes such as documents captured by mobile phones. Recognizing low-resolution text images is challenging because they lose detailed content information, leading to poor recognition…
Detecting and extracting textual information from natural scene images needs Scene Text Detection (STD) algorithms. Fully Convolutional Neural Networks (FCNs) are usually utilized as the backbone model to extract features in these instance…
Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips…
The FEAST algorithm is a subspace iteration method that uses a spectral projector as a rational filter in order to efficiently solve interior eigenvalue problems in parallel. Although the solutions from the FEAST algorithm converge rapidly…