Past year
All results
- All results
- Verbatim
Jan 11, 2024 · The CASIA-AHCDB is a large-scale Chinese ancient handwritten characters dataset, which consists of over 2.2 million annotated characters in over 10,000 classes ...
Jun 17, 2024 · Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual ...
Missing: ancient | Show results with:ancient
Mar 28, 2024 · They possess representation learning capabilities, generalization capabilities, and translational invariance, efficiently handling large-scale images and ...
Jun 7, 2024 · Chinese Named Entity Recognition (CNER) focuses on precisely identifying predefined structural categories in unstructured Chinese text. Most existing CNER.
Jun 11, 2024 · Figure 1. We introduce LingoCL, a simple yet effective continual learning paradigm leveraging language-guided supervision, which can be.
Apr 10, 2024 · In this paper, we firstly review the background of multi-modal pre-training technique in Section 2, from the traditional deep learning paradigm to pre-training ...
Missing: ancient | Show results with:ancient
Apr 17, 2024 · ... large-scale ancient Chinese corpus) unsurprisingly. The pre-trained models ... People name recognition from ancient Chinese literature using distant supervision ...
Jun 16, 2024 · Table 1: A case of data template in instruction tuning. unsupervised pre-trained on large-scale raw text,. LLMs are further trained via instruction tuning to.
Missing: ancient | Show results with:ancient
Apr 21, 2024 · Learning effective representations for Chinese characters presents unique challenges, primarily due to the vast number of characters and their continuous growth ...
Jul 23, 2024 · However, in large-scale handwritten Chinese character recognition tasks, classification errors frequently occur due to the high glyph similarity of handwritten ...
Missing: continual | Show results with:continual