Introduction
Visual understanding is one of the main topic in artificial intelligence. With the coming of large volume of images and their unstructured representations, processing and understanding them pose new challenges. VLR group, founded by Prof. Xiang Bai, is affiliated with the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, China. Our team focuses on several of the most exciting directions in computer vision and deep learning, which includes scene text detection and recognition, human-based image analysis, shape representation and analysis, object detection and image segmentation. For more information about our work, please refer to the research and publication pages.
Opening Positions
- We are currently recruiting self-motivated and dedicated Ph.D./M.S. students with solid background in mathematics, programming, or writtern English etc. Please feel free to contact us if you are interested.
- We plan to host a selected number of PostDocs with strong research background.
- Looking for fresh faculty members to join our group, please contact us at least half a year ahead of your arriving.
Recent News More
- 2022-09-01: “机器视觉与智能系统湖北省工程研究中心”即将落户我院 [link]
- 2022-08-22: 被认定为2022年湖北省工程研究中心 [link]
- 2022-07-24: 首次中非非洲文字识别技术创新论坛在华中大举行 [link]
- 2022-04-21: VLR学子成果---这个国家大使馆给华中科技大学发来感谢信！[ link]
- 2022-01-21: VLR研究组作为校方牵头者成立华中科技大学-天瞳威视自动驾驶视觉技术中心。 [link]
- 2021-10-12: 祝贺VLR研究组张拯同学的工作获得ICCV 2021 Best Paper（Marr Prize）！ [link]
- 2020-09-16: VLR组研究生在欧洲计算机视觉会议获得密集人群计数比赛冠军 [link]
- 2020-07-01: 祝贺VLR研究组2020届13位毕业生顺利毕业并取得学位 [link]
- 2019-10-29: VLR学子在国际计算机视觉大会获得短视频追踪比赛冠军 [ link]
- 2019-10-16: VLR研究组项目“答尔文-面向复杂场景的文字识别云平台”获得第五届中国“互联网+”双创大赛金奖 [link]
Selected Works
-
Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
-
Scalable Person Re-Identification on Supervised Smoothed Manifold (CVPR 2017)
proposed an unconventional manifold-preserving algorithm
-
ASTER: An Attentional Scene Text Recognizer with Flexible Rectification (PAMI 2018)
An Attentional Scene Text Recognizer with Flexible Rectification
-
Regularized Diffusion Process on Bidirectional Context for Object Retrieval (PAMI 2018)
propose a new affinity learning algorithm called Regularized Diffusion Process (RDP)
-
Deep-Person: Learning Discriminative Deep Features for Person
we propose to apply Long Short-Term Memory (LSTM) in an end-to-end way to model the pedestrian,seen as a sequence of body parts from head to foot
-
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
-
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition (PAMI 2017)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
Industrial Collabrators
