个人简介Personal Profile
刘禹良,研究员、华南理工大学(广州)本科(2012.9-2016.6),华南理工大学博士(2016.9-2020.8),师从金连文教授,澳大利亚阿德莱德大学访问博士生(2019.3-2020.5)与博士后(2020.5-2020.11),合作导师沈春华教授,香港中文大学博士后(2021.1-2022.1),合作导师林达华教授,2022年3月起任华中科技大学人工智能与自动化学院研究员。更多内容见VLR实验室主页。
研究方向主要围绕计算机视觉中的文档智能(Document AI)问题。文档智能涵盖视觉中一系列任务,包括文字检测、文字识别、图像/视频端到端文字检测及识别、文档板式分析、文字视觉问答、关键信息抽取、文档超像素/恢复重建及数字化、视觉富文档、文字擦除/编辑、文字风格转换与生成、跨模态文字引导下的场景理解、异常文字检测、文字自动标注等。近几年围绕Document AI取得若干高质量研究成果,主要关注与文字相关的应用和研究。兴趣广泛,对其他领域如遥感图像处理,图像生成,视觉与语言结合等也比较关注。
招生相关:希望学生能够对自身足够严格,有较高的追求,同时具备脚踏实地的执行力。期望和学生们共同实现有价值的目标,亦师亦友,互相督促,共同进步。
部分已发表论文:
Yuliang Liu, Chunhua Shen, Lianwen Jin, Tong He, Peng Chen, Chongyu Liu, and Hao Chen. ABCNet v2: Adaptive Bezier-Curve Network for End-to-end Text Spotting. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.
Yuliang Liu, Tong He, Hao Chen, Xinyu Wang, Canjie Luo, Shuaitao Zhang, Chunhua shen, and Lianwen Jin. Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection. International Journal of Computer Vision (IJCV), 2021, 129(6): 1972-1992.
Yuliang Liu, Lianwen Jin*, and Chuanming Fang. Arbitrarily shaped scene text detection with a mask tightness text detector. IEEE Transactions on Image Processing (TIP), 29, 2918-2930, 2019.
Yuliang Liu, Lianwen Jin, Sheng Zhang, Canjie Luo, and Shuaitao Zhang. Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recognition (PR), 90, 337-345, 2019.
Yuliang Liu, Lianwen Jin, Shuaitao Zhang, and Sheng Zhang. Detecting curve text in the wild: New dataset and new solution. arXiv preprint arXiv:1712.02170, 2017.
Yuliang Liu, Lianwen Jin, Songxuan Lai. Automatic labeling of large amounts of handwritten characters with gate-guided dynamic deep learning. Pattern Recognition Letters (PRL), 119, 94-102, 2019.
Yuliang Liu, Lianwen Jin*. Deep matching prior network: Toward tighter multi-oriented text detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1962-1969), 2017. Spotlight.
Yuliang Liu, Hao Chen, Chunhua Shen, Tong He, and Lianwen Jin, and Liangwei Wang. ABCNet: Real-time scene text spotting with adaptive bezier-curve network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 9809-9818), 2020. Oral.
Yuliang Liu, Lianwen Jin, Zecheng Xie, Canjie Luo, Shuaitao Zhang, and Lele Xie. Tightness-aware evaluation protocol for scene text de- tection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 9612-9620), 2019.
Yuliang Liu, Sheng Zhang, Lianwen Jin, Lele Xie, Yaqiang Wu, and Zhepeng Wang. Omnidirectional scene text detection with sequential- free box discretization. International joint conferences on artificial intelligence organization (IJCAI), (pp. 3052-3058), 2019. Oral.