194 citations · 426 across the 16 of their papers we have counts for
7 papers · 1 filter
Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association
Sen Yang, Zhicheng Wang, Ze Chen +7
This paper presents a new method to solve keypoint detection and instance association by using Transformer. For bottom-up multi-person pose estimation models, they need to detect k…
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…
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…
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…
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…
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…
TokenPose: Learning Keypoint Tokens for Human Pose Estimation
Yanjie Li, Shoukui Zhang, Zhicheng Wang +4
Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation,…