most citedTopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

16 citations · 27 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2022

Featurized Query R-CNN

Wenqiang Zhang, Tianheng Cheng, Xinggang Wang +3

The query mechanism introduced in the DETR method is changing the paradigm of object detection and recently there are many query-based methods have obtained strong object detection…

cs.CV2022★ 16 cited

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

Wenqiang Zhang, Zilong Huang, Guozhong Luo +5

Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semant…

cs.CV2022

AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception

Shaoyu Chen, Xinggang Wang, Tianheng Cheng +4

Studying the inherent symmetry of data is of great importance in machine learning. Point cloud, the most important data format for 3D environmental perception, is naturally endowed…

cs.CV2022★ 10 cited

Sparse Instance Activation for Real-Time Instance Segmentation

Tianheng Cheng, Xinggang Wang, Shaoyu Chen +5

In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods hea…

cs.CV2020★ 1 cited

EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search

Wenqiang Zhang, Jiemin Fang, Xinggang Wang +1

Human pose estimation from image and video is a vital task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into consideration…