Z
Zeng Xingyu
Researcher at SenseTime
Publications - 45
Citations - 2808
Zeng Xingyu is an academic researcher from SenseTime. The author has contributed to research in topics: Object detection & Object (computer science). The author has an hindex of 19, co-authored 45 publications receiving 2075 citations. Previous affiliations of Zeng Xingyu include The Chinese University of Hong Kong.
Papers
More filters
Journal ArticleDOI
T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos
Kai Kang,Hongsheng Li,Junjie Yan,Zeng Xingyu,Bin Yang,Tong Xiao,Cong Zhang,Zhe Wang,Ruohui Wang,Xiaogang Wang,Wanli Ouyang +10 more
TL;DR: A deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos is proposed, called T-CNN.
Proceedings ArticleDOI
DeepID-Net: Deformable deep convolutional neural networks for object detection
Wanli Ouyang,Xiaogang Wang,Zeng Xingyu,Shi Qiu,Ping Luo,Yonglong Tian,Hongsheng Li,Shuo Yang,Zhe Wang,Chen Change Loy,Xiaoou Tang +10 more
TL;DR: The proposed approach improves the mean averaged precision obtained by RCNN, which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set.
Proceedings ArticleDOI
GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
TL;DR: In this article, an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving is presented. But, the 3D structure information of the object is not explored by employing the visual features of visible surfaces.
Proceedings ArticleDOI
Multi-stage Contextual Deep Learning for Pedestrian Detection
TL;DR: A new deep model is proposed that can jointly train multi-stage classifiers through several stages of back propagation and keeps the score map output by a classifier within a local region and uses it as contextual information to support the decision at the next stage.
Posted Content
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
Wanli Ouyang,Ping Luo,Zeng Xingyu,Shi Qiu,Yonglong Tian,Hongsheng Li,Shuo Yang,Zhe Wang,Yuanjun Xiong,Chen Qian,Zhenyao Zhu,Ruohui Wang,Chen Change Loy,Xiaogang Wang,Xiaoou Tang +14 more
TL;DR: A set of models with large diversity are obtained, which significantly improves the effectiveness of modeling averaging, and improves the mean averaged precision obtained by RCNN, which is the state of the art of object detection, from31% to 45%.