Zeming Li (黎泽明)

I am a Researcher for the Detection Team at Megvii (Face++). My research interests focus on the computer vision and artificical intelligence, specifically on the topic of object detection, instance segmentation, 3D detection. Currently i am master student in Tsinghua University.
Email: lizeming@megvii.com
zengarden2009@gmail.com

News

we have won the first place in Video Instance Segmentation in the WAD2018 (Workshop on Autonomous Driving) Challenge.
We have won COCO and Places Challenges 2017 with two champions on: COCO Detection and COCO Keypoint.
COCO Detection Leaderboard: http://cocodataset.org/#detections-leaderboard
COCO Keypoint Leaderboard: http://cocodataset.org/#keypoints-leaderboard

I'm first place in Pascal VOC detection learderboard.
VOC Detection Leaderboard: http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php?challengeid=11&compid=4

Conference

+ Equal contribution

DetNet: A Backbone network for Object Detection
Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun
ECCV, 2018

MegDet: A Large Mini-Batch ObjectDetector
Chao Peng+ , Tete Xiao+ , Zeming Li+ , Yuning Jiang, Xiangyu Zhang, Kai Jia, Gang Yu, Jian Sun
CVPR spotlight, 2018

R-FCN++: Towards Accurate Region-based Fully Convolutional Networks for Object Detection
Zeming Li, Yilun Chen, Gang Yu, Yangdong Deng
AAAI Oral, 2018

Arxiv

Light-Head R-CNN: In Defense of Two-Stage Object Detector
Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun
Arxiv, 2017
code/models

Links

Research Leader: 俞刚(Gang Yu)
Research Collaborator: 彭超(Peng Chao)

stats counter unique visitors since Dec 2018