activity
20172019
most citedAction Machine: Rethinking Action Recognition in Trimmed Videos

28 citations · 47 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2019

EPOSIT: An Absolute Pose Estimation Method for Pinhole and Fish-Eye Cameras

Zhaobing Kang, Wei Zou, Zheng Zhu +2

This paper presents a generic 6DOF camera pose estimation method, which can be used for both the pinhole camera and the fish-eye camera. Different from existing methods, relative p…

cs.CV2019

Camera Pose Correction in SLAM Based on Bias Values of Map Points

Zhaobing Kang, Wei Zou, Zheng Zhu

Accurate camera pose estimation result is essential for visual SLAM (VSLAM). This paper presents a novel pose correction method to improve the accuracy of the VSLAM system. Firstly…

cs.CV2019

FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks

Jiabin Zhang, Zheng Zhu, Wei Zou +4

Both accuracy and efficiency are significant for pose estimation and tracking in videos. State-of-the-art performance is dominated by two-stages top-down methods. Despite the leadi…

cs.CV201828 cited

Action Machine: Rethinking Action Recognition in Trimmed Videos

Jiagang Zhu, Wei Zou, Liang Xu +6

Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a concept…

cs.CV2018

An Efficient Optical Flow Based Motion Detection Method for Non-stationary Scenes

Junjie Huang, Wei Zou, Zheng Zhu +1

Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. These challeng…

cs.CV2018

Optical Flow Based Online Moving Foreground Analysis

Junjie Huang, Wei Zou, Zheng Zhu +1

Obtained by moving object detection, the foreground mask result is unshaped and can not be directly used in most subsequent processes. In this paper, we focus on this problem and a…