Chunyu Wang

Chunyu Wang

Auto-generated profile, based on publicly available information

Chunyu Wang

Microsoft Research Asia, Beijing, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 September 2021 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YZYifu Zhang
Yifu Zhang
CWChunyu Wang
Chunyu Wang
Xinggang WangXinggang Wang
Xinggang Wang
WZWenjun Zeng
Wenjun Zeng
WLWenyu Liu
Wenyu Liu

3 November 2020
Verified
Book Chapter
Closed access
PDF file
HTHanyue Tu
Hanyue Tu
CWChunyu Wang
Chunyu Wang
WZWenjun Zeng
Wenjun Zeng

16 November 2020 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
ZZZhe Zhang
Zhe Zhang
CWChunyu Wang
Chunyu Wang
WQWeichao Qiu
Weichao Qiu
WQWenhu Qin
Wenhu Qin
WZWenjun Zeng
Wenjun Zeng

15 April 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YZYifu Zhang
Yifu Zhang
CWChunyu Wang
Chunyu Wang
Xinggang WangXinggang Wang
Xinggang Wang
WLWenyu Liu
Wenyu Liu
WZWenjun Zeng
Wenjun Zeng
We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines. It employs a multi-branch network to jointly estimate 3D poses and re-identification (Re-ID) features for all people in the environment. In contrast to previous efforts which require to establish cross-view correspondence based on noisy 2D pose estimates, it directly estimates and tracks 3D poses from a 3D voxel-based representation constructed from multi-view images. We first discretize the 3D space by regular voxels and compute a feature vector for each voxel by averaging the body joint heatmaps that are inversely projected from all views. We estimate 3D poses from the voxel representation by predicting whether each voxel contains a particular body joint. Similarly, a Re-ID feature is computed for each voxel which is used to track the estimated 3D poses over time. The main advantage of the approach is that it avoids making any hard decisions based on individual images. The approach can robustly estimate and track 3D poses even when people are severely occluded in some cameras. It outperforms the state-of-the-art methods by a large margin on four public datasets including Shelf, Campus, Human3.6 M and CMU Panoptic.

11 April 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
PTPeng Tang
Peng Tang
CWChunyu Wang
Chunyu Wang
Xinggang WangXinggang Wang
Xinggang Wang
WLWenyu Liu
Wenyu Liu
WZWenjun Zeng
Wenjun Zeng
JWJingdong Wang
Jingdong Wang
Compared with object detection in static images, object detection in videos is more challenging due to degraded image qualities. An effective way to address this problem is to exploit temporal contexts by linking the same object across video to form tubelets and aggregating classification scores in the tubelets. In this paper, we focus on obtaining high quality object linking results for better classification. Unlike previous methods that link objects by checking boxes between neighboring frames, we propose to link in the same frame. To achieve this goal, we extend prior methods in following aspects: (1) a cuboid proposal network that extracts spatio-temporal candidate cuboids which bound the movement of objects; (2) a short tubelet detection network that detects short tubelets in short video segments; (3) a short tubelet linking algorithm that links temporally-overlapping short tubelets to form long tubelets. Experiments on the ImageNet VID dataset show that our method outperforms both the static image detector and the previous state of the art. In particular, our method improves results by 8.8 percent over the static image detector for fast moving objects.

1 October 2023
Verified
Conference Paper
Open access
JNJia Ning
Jia Ning
CLChen Li
Chen Li
ZZZheng Zhang
Zheng Zhang
CWChunyu Wang
Chunyu Wang
ZGZigang Geng
Zigang Geng
HHHu Han
Hu Han
We introduce AiT, a unified output representation for various vision tasks, which is a crucial step towards general-purpose vision task solvers. Despite the challenges posed by the high-dimensional and task-specific outputs, we showcase the potential of using discrete representation (VQVAE) to model the dense outputs of many computer vision tasks as a sequence of discrete tokens. This is inspired by the established ability of VQ-VAE to conserve the structures spanning multiple pixels using few discrete codes. To that end, we present a modified shallower architecture for VQ-VAE that improves efficiency while keeping prediction accuracy. Our approach also incorporates uncertainty into the decoding process by using a soft fusion of the codebook entries, providing a more stable training process, which notably improved prediction accuracy. Our evaluation of AiT on depth estimation and instance segmentation tasks, with both continuous and discrete labels, demonstrates its superiority compared to other unified models. The code and models are available at https://github.com/SwinTransformer/AiT.