Siyang Qin

I am a senior software engineer at Google Research, Perception. My research interest lies at the intersection of computer vision and machine learning, with the focus on optical character recognition (OCR).

Previously, I received my B.E. degree from Tsinghua University and Ph.D. degree from University of California, Santa Cruz, advised by Professor Roberto Manduchi.

qinb[at]google.com / Google Scholar / LinkedIn / GitHub

News

04/2022: The HierText dataset is publicly available now.
03/2022: Our paper on Towards End-to-End Unified Scene Text Detection and Layout Analysis is accepted to CVPR 2022.

Research

	Towards End-to-End Unified Scene Text Detection and Layout Analysis Shangbang Long, Siyang Qin, Dmitry Panteleev, Alessandro Bissacco, Yasuhisa Fujii, Michalis Raptis CVPR 2022 arXiv / github
	ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction Chen-Yu Lee, Chun-Liang Li, Chu Wang, Renshen Wang, Yasuhisa Fujii, Siyang Qin, Ashok Popat, Tomas Pfister ACL 2021 (Oral Presentation) arXiv
	Rethinking Text Line Recognition Models Daniel Hernandez Diaz, Siyang Qin, Reeve Ingle, Yasuhisa Fujii, Alessandro Bissacco arXiv
	Towards Unconstrained End-to-End Text Spotting Siyang Qin, Alessandro Bissacco, Michalis Raptis, Yasuhisa Fujii, Ying Xiao ICCV 2019 (Oral Presentation) paper
	Scene Text Access: A Comparison of Mobile OCR Modalities for Blind Users Leo Neat, Ren Peng, Siyang Qin, Roberto Manduchi IUI 2019 paper
	Automatic Semantic Content Removal by Learning to Neglect Siyang Qin, Jiahui Wei, Roberto Manduchi BMVC 2018 (Best Industry Paper Award) arXiv
	Multi-planar Monocular Reconstruction of Manhattan Indoor Scenes Seongdo Kim, Roberto Manduchi, Siyang Qin 3DV 2018 paper
	Robust and Accurate Text Stroke Segmentation Siyang Qin, Peng Ren, Seongdo Kim, Roberto Manduchi WACV 2018 paper
	Cascaded Segmentation-Detection Networks for Word-Level Text Spotting Siyang Qin, Roberto Manduchi ICDAR 2017 paper
	Automatic Skin and Hair Masking using Fully Convolutional Networks Siyang Qin, Seongdo Kim, Roberto Manduchi ICME 2017 (Oral Presentation) paper
	A Fast and Robust Text Spotter Siyang Qin, Roberto Manduchi WACV 2016 paper
	Dynamic Mapping for Multiview Autostereoscopic Displays Jing Liu, Tom Malzbender, Siyang Qin, Bipeng Zhang, Che-AnWu, James Davis IS&T/SPIE Electronic Imaging, 2015 paper

Source code credit to Dr. Jon Barron