Zhao Qijie

赵祈杰，Computer Vision Software Engineer at the perception team of Pony.ai


Haidian district, Beijing, China.


E-mail: qijie AT pony.ai OR pkuzqj AT gmail/163.com
WeChat ID: zhaoqijie8356


Zhihu, Github, Google Scholar






 
Biography
I am a Computer Vision Software Engineer at Pony.ai, I focus on helping autonomous vehicles percept and decide. Before that, I obtained my M.S. degree at Wangxuan Institute of Computer Technology(ICST before 2019) from PKU in 2019.
 
Research interests
My research interests include: Autonomous Driving, Computer Vision, Object Detection, Semantic Segmentation, Action Recognition.
 
Recent Events

  • 2020.02: one paper accepted by CVPR'20.
  • 2019.11: two papers accepted by AAAI'20.
  • 2019.07: I obtained my M.S. degree from EECS@PKU.
  • 2019.03: One paper accepted by SIGAI'19, One paper accepted by ICME'19.
  • 2019.03: I released the code of M2Det.
  • 2018.11: One paper accepted by AAAI'19(Spotlight paper).
  • 2018.10: Our team VDIG won the 1st place in both Object Detection task and Semantic Segmentation task in Military Ground Object Recognition Competition, which held by PRCV'18.[slides][code]
  • 2018.09: I submitted a paper to AAAI'19, and one paper accepted by ACCV'18.
  • 2018.08: Our lab took part in workshop Vision Meets Drones: A Challenge, which held by ECCV'18, and won 1st place of Object Detection in videos task and 3rd place of Object Detection in Images task.[slides][code]
  • 2018.07: I took part in Butterfly Detection and Fine-grained Recognition competition held by CCDM2018, and won 1st place among hundreds of participants.[slides]
  • 2018.06: Our team ICST&Ali won the 2nd place in Road Object Detection task of WAD 2018 Challenge! This year the challenge is hosted together with CVPR'18.
  • 2018.06: Our team BaiduVis won the 1st place in Trimmed Action Recognition task of ActivityNet Large Scale Activity Recognition Challenge 2018!, the challenge is hosted together with CVPR'18.
  • 2018.04: I submitted a paper to ACMMM2018.
  • 2018.01: I joined in VDIG Lab.
  • 2016.11: Our lab team PKUMI won the 2nd prize in Traffic Sign Detection task of CCF-BDCI2016 competitions.
  • 2016.08: Our lab team PKUMI won the 2nd place in Video Tagging task of the RACV2016 competitions.
  • 2016.05: I joined in MI lab.
 
Publications
 
Tingting Liang, Yongtao Wang, Qijie Zhao, et al. MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection. Arxiv paper. [pdf]
 
Yibo Yang, Hongyang Li, Xia Li, Qijie Zhao, Jianlong Wu, Zhouchen Lin. SOGNet: Scene Overlap Graph Network for Panoptic Segmentation. AAAI Conference on Artificial Intelligence (AAAI-20). [pdf]
 
Yudong Liu, Yongtao Wang, Siwei Wang, Tingting Liang, Qijie Zhao, Zhi Tang, Haibin Ling. CBNet: A Novel Composite Backbone Network Architecture for Object Detection. AAAI Conference on Artificial Intelligence (AAAI-20). [pdf]
 
Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin. MMDetection: Open MMLab Detection Toolbox and Benchmark. Technical report on Arxiv. [pdf]
 
Qijie Zhao, Yongtao Wang et. al. M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network. AAAI Conference on Artificial Intelligence (AAAI-19). Spotlight [pdf]
 
Tingting Liang, Qijie Zhao, Zhuoying Wang et. al. Pyramidal Region Context Module for Semantic Segmentation. The ACM Turing Celebration Conference - SIGAI CHINA (SIGAI-19). [pdf]
 
Siwei Wang, Xiaoran Qin, Qijie Zhao et. al. Scene Text Recognition via Gated Cascade Attention. International Conference on Multimedia and Expo (ICME-19). Poster [pdf]
 
Qijie Zhao, Yongtao Wang, Tao Sheng et. al. Comprehensive Feature Enhancement Module for Single-Shot Object Detector. Asian Conference on Computer Vision (ACCV-18). Poster [pdf]
 
Qijie Zhao, Feng Ni, Yang Song et. al. Deep Dual Pyramid Network for Barcode Segmentation using Barcode-30k Database. CoRR abs/1807.11886
 
Dongliang He, Fu Li, Qijie Zhao, et. al. Exploiting Spatial-Temporal Modelling and Multi-Modal Fusion for Human Action Recognition. Computer Vision and Pattern Recognition 2018 Workshop.
 
Qijie Zhao, Feng Ni, et. al. CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving. Computer Vision and Pattern Recognition 2018, Workshop of Autonomous Driving technique report.
 
Projects
(More visualizations and demonstrations will come soon)
1, Road Object Detection for Intelligent Transportation
2, Barcode and QR code Segmentation
3, Multi-Object Tracking for Autonomous Driving
4, Anti Fraud Prediction System (based on machine learning)
5, Deep Domain Adaptation for Multimedia Event Detection.
 
Prizes
Excellent student award at Institute of Computer Science&Technology: 2016, 2018
Second Prize Scholarship at Peking University, 2016/2017/2018.
Last modified: Feb 18, 2020
GF: CZhao - czhao AT pku.edu.cn