相关论文: TPS++: Attention-Enhanced Thin-Plate Spline for Sc…
We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text region proposals and their, possibly erroneous,…
Arbitrary text appearance poses a great challenge in scene text recognition tasks. Existing works mostly handle with the problem in consideration of the shape distortion, including perspective distortions, line curvature or other style…
Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…
Text-based person search (TBPS) is a challenging task that aims to search pedestrian images with the same identity from an image gallery given a query text. In recent years, TBPS has made remarkable progress and state-of-the-art methods…
With the rapid development of Natural Language Processing (NLP) technologies, text steganography methods have been significantly innovated recently, which poses a great threat to cybersecurity. In this paper, we propose a novel attentional…
Script identification plays a significant role in analysing documents and videos. In this paper, we focus on the problem of script identification in scene text images and video scripts. Because of low image quality, complex background and…
The success of Transformer-based Language Models (LMs) stems from their attention mechanism. While this mechanism has been extensively studied in explainability research, particularly through the attention values obtained during the forward…
End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, and all…
This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in…
Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge.…
End-to-end scene text spotting, which unifies text detection and recognition within a single framework, has witnessed remarkable progress driven by deep learning advances. However, most existing approaches still suffer from incomplete mask…
Scene text detection has witnessed rapid progress especially with the recent development of convolutional neural networks. However, there still exists two challenges which prevent the algorithm into industry applications. On the one hand,…
Scene text recognition (STR) has been extensively studied in last few years. Many recently-proposed methods are specially designed to accommodate the arbitrary shape, layout and orientation of scene texts, but ignoring that various font (or…
RRPN is among the outstanding scene text detection approaches, but the manually-designed anchor and coarse proposal refinement make the performance still far from perfection. In this paper, we propose RRPN++ to exploit the potential of…
Scene text recognition (STR) suffers from challenges of either less realistic synthetic training data or the difficulty of collecting sufficient high-quality real-world data, limiting the effectiveness of trained models. Meanwhile, despite…
Text-based person search (TBPS) aims to retrieve images of a specific person from a large image gallery based on a natural language description. Existing methods rely on massive annotated image-text data to achieve satisfactory performance…
Automated recognition of texts in scenes has been a research challenge for years, largely due to the arbitrary variation of text appearances in perspective distortion, text line curvature, text styles and different types of imaging…
A precise, controllable, interpretable and easily trainable text removal approach is necessary for both user-specific and large-scale text removal applications. To achieve this, we propose a one-stage mask-based text inpainting network,…
Detection and recognition of scene texts of arbitrary shapes remain a grand challenge due to the super-rich text shape variation in text line orientations, lengths, curvatures, etc. This paper presents a mask-guided multi-task network that…
Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…