Xiang Bai
Also known as 白翔
Xiang Bai is a professor at Huazhong University of Science and Technology, and his work includes methods for detecting and spotting text in images. He earned his bachelor's, master's and doctoral degrees at HUST in 2003, 2005 and 2009, and he was a joint PhD student at UCLA, co-supervised by Zhuowen Tu and Alan Yuille. He co-authored TextBoxes, a fast text detector built on a single deep neural network, in 2017. He also co-authored Mask TextSpotter, which spots text with arbitrary shapes, in 2018. The International Association for Pattern Recognition named him a Fellow in 2020, and the IEEE named him a 2026 Fellow for contributions to document image processing and understanding.
- Works
- 494
- Citations
- 45,422
- h-index
- 95
Publication numbers from OpenAlex, as of 15 October 2026.
Timeline
-
2003–2009
Studying at HUST and UCLA
He receives BS, MS and PhD degrees from HUST in 2003, 2005 and 2009, and he works as a joint PhD student at UCLA, co-supervised by Zhuowen Tu and Alan Yuille.
-
2017
A fast text detector
He co-authors TextBoxes, a fast text detector built on a single deep neural network, which AAAI publishes in 2017.
-
2018
Spotting text with arbitrary shapes
He co-authors Mask TextSpotter, an end-to-end trainable network for spotting text with arbitrary shapes, which ECCV presents in 2018.
-
2020
Named IAPR Fellow
The International Association for Pattern Recognition names him a Fellow in 2020 for contributions to shape representation, contextual visual similarity, and camera-based document analysis.
-
2026
Named 2026 IEEE Fellow
The IEEE names him a 2026 Fellow for contributions to document image processing and understanding.
-
As of October 2026
Professor at HUST
He is a professor and Ph.D. supervisor in the Department of Artificial Intelligence and Automation at Huazhong University of Science and Technology.
Sources and credits
Photo: We have no published photo of Xiang Bai yet. Send us a free-licensed photo.
- Keynote talks – CBDAR 2019
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network | Proceedings of the AAAI Conference on Artificial Intelligence
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
- Chronological List of IAPR Fellows – International Association for Pattern Recognition
- IEEE 2026新晋Fellow名单正式公布 – IEEE中国
- IR Associate Editors Named 2025 Clarivate Highly Cited Researchers