Related papers: Zero-Shot Chinese Character Recognition with Hiera…
In this paper, we investigate the Chinese calligraphy synthesis problem: synthesizing Chinese calligraphy images with specified style from standard font(eg. Hei font) images (Fig. 1(a)). Recent works mostly follow the stroke extraction and…
Blind text image super-resolution (SR) is challenging as one needs to cope with diverse font styles and unknown degradation. To address the problem, existing methods perform character recognition in parallel to regularize the SR task,…
The long-standing challenges for offline handwritten Chinese character recognition (HCCR) are twofold: Chinese characters can be very diverse and complicated while similarly looking, and cursive handwriting (due to increased writing speed…
Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations…
Chinese NER is a challenging task. As pictographs, Chinese characters contain latent glyph information, which is often overlooked. In this paper, we propose the FGN, Fusion Glyph Network for Chinese NER. Except for adding glyph information,…
Vision Language Foundation Models based on CLIP architecture for remote sensing primarily rely on short text captions, which often result in incomplete semantic representations. Although longer captions convey richer information, existing…
Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding. In this work, we propose ChineseBERT,…
The ambiguous annotation criteria lead to divergence of Chinese Word Segmentation (CWS) datasets in various granularities. Multi-criteria Chinese word segmentation aims to capture various annotation criteria among datasets and leverage…
Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP…
Deep convolutional neural networks (DCNNs) have achieved great success in various computer vision and pattern recognition applications, including those for handwritten Chinese character recognition (HCCR). However, most current DCNN-based…
In this paper, we propose an end-to-end trainable framework for restoring historical documents content that follows the correct reading order. In this framework, two branches named character branch and layout branch are added behind the…
We introduce a general detection-based approach to text line recognition, be it printed (OCR) or handwritten (HTR), with Latin, Chinese, or ciphered characters. Detection-based approaches have until now been largely discarded for HTR…
Scene text editing, a subfield of image editing, requires modifying texts in images while preserving style consistency and visual coherence with the surrounding environment. While diffusion-based methods have shown promise in text…
Multi-hop question answering (MHQA) requires integrating knowledge scattered across multiple passages to derive the correct answer. Traditional retrieval-augmented generation (RAG) methods primarily focus on coarse-grained textual semantic…
Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative scarcity of…
Recently, significant advancements have been made in diffusion-based visual text generation models. Although the effectiveness of these methods in visual text rendering is rapidly improving, they still encounter challenges such as…
Pre-trained Language Models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding. Various Chinese PLMs have been successively proposed for learning better Chinese language…
Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly improves the performance. In this…
The flourishing blossom of deep learning has witnessed the rapid development of text recognition in recent years. However, the existing text recognition methods are mainly proposed for English texts. As another widely-spoken language,…
Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works…