activity
20192021
most citedRethinking on Multi-Stage Networks for Human Pose Estimation

109 citations · 218 across the 9 of their papers we have counts for

collaborators

14 papers

cs.CV20211 cited

Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads

Xiaohu Jiang, Ze Chen, Zhicheng Wang +2

After DETR was proposed, this novel transformer-based detection paradigm which performs several cross-attentions between object queries and feature maps for predictions has subsequ…

cs.CV20212 cited

Adaptive Dilated Convolution For Human Pose Estimation

Zhengxiong Luo, Zhicheng Wang, Yan Huang +3

Most existing human pose estimation (HPE) methods exploit multi-scale information by fusing feature maps of four different spatial sizes, \ie , , , and of th…

cs.LG202150 cited

Graph-MLP: Node Classification without Message Passing in Graph

Yang Hu, Haoxuan You, Zhecan Wang +3

Graph Neural Network (GNN) has been demonstrated its effectiveness in dealing with non-Euclidean structural data. Both spatial-based and spectral-based GNNs are relying on adjacenc…

cs.CV2021

DAVOS: Semi-Supervised Video Object Segmentation via Adversarial Domain Adaptation

Jinshuo Zhang, Zhicheng Wang, Songyan Zhang +1

Domain shift has always been one of the primary issues in video object segmentation (VOS), for which models suffer from degeneration when tested on unfamiliar datasets. Recently, m…

cs.CV2021

General Instance Distillation for Object Detection

Xing Dai, Zeren Jiang, Zhao Wu +4

In recent years, knowledge distillation has been proved to be an effective solution for model compression. This approach can make lightweight student models acquire the knowledge e…

cs.CV20215 cited

V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection

Mingyang Shang, Dawei Xiang, Zhicheng Wang +1

Occlusion is very challenging in pedestrian detection. In this paper, we propose a simple yet effective method named V2F-Net, which explicitly decomposes occluded pedestrian detect…