M
Minghang He
Researcher at Huazhong University of Science and Technology
Publications - 7
Citations - 345
Minghang He is an academic researcher from Huazhong University of Science and Technology. The author has contributed to research in topics: Thresholding & Metaverse. The author has an hindex of 5, co-authored 7 publications receiving 169 citations. Previous affiliations of Minghang He include Peking University.
Papers
More filters
Journal ArticleDOI
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
TL;DR: The recognition module of the Mask TextSpotter method is investigated separately, which significantly outperforms state-of-the-art methods on both regular and irregular text datasets for scene text recognition.
Journal ArticleDOI
TextScanner: Reading Characters in Order for Robust Scene Text Recognition
TL;DR: TextScanner as discussed by the authors generates pixel-wise, multi-channel segmentation maps for character class, position and order, and adopts RNN for context modeling to perform paralleled prediction for character position and class, and ensure that characters are transcripted in the correct order.
Posted Content
TextScanner: Reading Characters in Order for Robust Scene Text Recognition.
TL;DR: TextScanner bears three characteristics: it belongs to the semantic segmentation family, as it generates pixel-wise, multi-channel segmentation maps for character class, position and order, and also adopts RNN for context modeling.
Proceedings ArticleDOI
MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
Minghang He,Minghui Liao,Zhibo Yang,Humen Zhong,Jun Tang,Wenqing Cheng,Cong Yao,Yongpan Wang,Xiang Bai +8 more
TL;DR: Zhang et al. as mentioned in this paper proposed Text Feature Alignment Module (TFAM), Position-Aware Non-Maximum Suppression (PA-NMS), and Instance-wise IoU loss for balanced training to deal with text instances of different scales.
Posted Content
SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
TL;DR: This paper proposes to synthesize scene text images from the 3D virtual worlds, where the precise descriptions of scenes, editable illumination/visibility, and realistic physics are provided.