The Deep Learning and Vision Computing Lab is dedicated to advanced theoretical research and innovative applications in the fields of artificial intelligence, computer vision, machine learning, and pattern recognition. Our current research focuses on deep learning, text detection and recognition, document analysis and understanding, and artificial intelligence. In recent years, our team has led more than 30 national and provincial research projects, making significant achievements in optical character recognition (OCR), handwriting recognition, gesture recognition and interaction technology, and innovative applications of deep learning. We have published over 300 SCI/EI papers, obtained more than 50 authorized invention patents, won 5 provincial and ministerial science and technology awards, and achieved first place in international academic competitions 4 times.
Pinned Loading
Repositories
- MCCD Public
[ICDAR 2025] The official GitHub page of "MCCD: A Multi-Attribute Chinese Calligraphy Character Dataset Annotated with Script Styles, Dynasties, and Calligraphers"
- DocHighlight Public
[PRCV 25] Towards Real-World Document Specular Highlight Removal: The DocHighlight Dataset and DocSHRNet Method
- HisDoc1B Public
- SCUT-EnsExam Public
SCUT-EnsExam is a real-world handwritten text erasure dataset for examination paper scenarios, which consists of 545 examination paper images. The dataset is randomly divided into training set and test set of 430 and 115 images, respectively.
- MCS-Bench Public
[ACL 25 main] MCS-Bench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in Chinese Classical Studies
- ACP-RAG Public
[NAACL 2025] Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights (ACP-Corpus; ACP-QA; ACP-RAG)
- DARL Public
[ECCV 2026] DARL: Efficient Document-to-Markup Generation via Look-Ahead Diffusion Trajectory Sampling
- AutoHDR Public
[ACL 2025 main] The official GitHub page of "Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration"
- TTFN Public
[IEEE TIFS 2026] Bridging the Reality Gap in Tampered Text Detection: A Human-Crafted Real-World Dataset and a Text-Centric Approach
- Ancient_Bench Public
Top languages
Loading…
Most used topics
Loading…