Zuming Huang
Scholar

Zuming Huang

Google Scholar ID: UjnuehYAAAAJ
Senior Algorithm Engineer, Ant Group
OCRDocument IntelligenceLarge Multimodal Models
Citations & Impact
All-time
Citations
697
 
H-index
7
 
i10-index
6
 
Publications
13
 
Co-authors
14
list available
Resume (English only)
Academic Achievements
  • Publication: Fine-grained Pesudo Labels for Scene Text Recognition, In ACM MM, 2023 (CCF A)
  • Publication: Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes, In CVPR, 2019 (CCF A)
  • Publication: A Single-shot Arbitrarily-shaped Text Detector based on Context Attended Multi-task Learning, In ACM MM, 2019 (CCF A)
  • Publication: TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network, In ACCV, 2018 (Oral, CCF C)
  • Publication: Building Extraction from Multi-source Remote Sensing Images via Deep Deconvolution Neural Networks, In IGRASS, 2016
  • Publication: Extraction of Virtual Baselines from Distorted Document Images using Curvilinear Projection, In ICCV, 2015 (CCF A)
  • Publication: Text Line Extraction of Curved Document Images using Hybrid Metric, In ACPR, 2015
  • Publication: Distance-weighted Backlog Differentials for Back-pressure Routing in Multi-hop Wireless Networks, In ICCC, 2014 (Best Paper Award)
Background
  • Research interests include OCR, Document Intelligence, and Large Multimodal Models. Currently, he is a senior algorithm engineer at the multi-modality cognition team of Ant Group.
Miscellany
  • A football fan who has been watching and playing football matches since middle school.