Alert button
Picture for Jingqun Tang

Jingqun Tang

Alert button

Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer

Nov 23, 2023
Zhen Zhao, Jingqun Tang, Chunhui Lin, Binghong Wu, Hao Liu, Zhizhong Zhang, Xin Tan, Can Huang, Yuan Xie

Viaarxiv icon

UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding

Sep 02, 2023
Hao Feng, Zijian Wang, Jingqun Tang, Jinghui Lu, Wengang Zhou, Houqiang Li, Can Huang

Figure 1 for UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding
Figure 2 for UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding
Figure 3 for UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding
Figure 4 for UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding
Viaarxiv icon

SPTS v2: Single-Point Scene Text Spotting

Jan 04, 2023
Yuliang Liu, Jiaxin Zhang, Dezhi Peng, Mingxin Huang, Xinyu Wang, Jingqun Tang, Can Huang, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin

Figure 1 for SPTS v2: Single-Point Scene Text Spotting
Figure 2 for SPTS v2: Single-Point Scene Text Spotting
Figure 3 for SPTS v2: Single-Point Scene Text Spotting
Figure 4 for SPTS v2: Single-Point Scene Text Spotting
Viaarxiv icon

Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning

Jul 26, 2022
Jingqun Tang, Wenming Qian, Luchuan Song, Xiena Dong, Lan Li, Xiang Bai

Figure 1 for Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning
Figure 2 for Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning
Figure 3 for Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning
Figure 4 for Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning
Viaarxiv icon

Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection

Mar 30, 2022
Jingqun Tang, Wenqing Zhang, Hongye Liu, MingKun Yang, Bo Jiang, Guanglong Hu, Xiang Bai

Figure 1 for Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
Figure 2 for Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
Figure 3 for Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
Figure 4 for Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
Viaarxiv icon