C
Chunyu Wang
Researcher at Microsoft
Publications - 66
Citations - 2899
Chunyu Wang is an academic researcher from Microsoft. The author has contributed to research in topics: Computer science & Pose. The author has an hindex of 16, co-authored 41 publications receiving 1502 citations. Previous affiliations of Chunyu Wang include Peking University.
Papers
More filters
Journal ArticleDOI
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
TL;DR: A simple approach which consists of two homogeneous branches to predict pixel-wise objectness scores and re-ID features allows \emph{FairMOT} to obtain high levels of detection and tracking accuracy and outperform previous state-of-the-arts by a large margin on several public datasets.
Proceedings ArticleDOI
An Approach to Pose-Based Action Recognition
TL;DR: This work improves a state of the art method for estimating human joint locations from videos and incorporates additional segmentation cues and temporal constraints to select the ``best'' one, which is able to localize body joints more accurately than existing methods.
Journal ArticleDOI
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
TL;DR: FairMOT as discussed by the authors proposes a simple yet effective approach based on the anchor-free object detection architecture CenterNet, which achieves high accuracy for both detection and tracking, and outperforms the state-of-the-art methods by a large margin.
Proceedings ArticleDOI
Robust Estimation of 3D Human Poses from a Single Image
TL;DR: In this paper, a linear combination of a sparse set of bases learned from 3D human skeletons is used to estimate the 3D pose by minimizing the 1-norm error between the projection of the 2D pose and the corresponding 2D detection.
Proceedings ArticleDOI
Cross View Fusion for 3D Human Pose Estimation
TL;DR: This work introduces a cross-view fusion scheme into CNN to jointly estimate 2D poses for multiple views and presents a recursive Pictorial Structure Model to recover the 3D pose from the multi-view 2D pose.