186 citations · 390 across the 30 of their papers we have counts for
Showing 2022 · cs.CVShow all
3 papers · 2 filters
cs.CV2022★ 23 cited
ViTKD: Practical Guidelines for ViT feature knowledge distillation
Zhendong Yang, Zhe Li, Ailing Zeng +3
Knowledge Distillation (KD) for Convolutional Neural Network (CNN) is extensively studied as a way to boost the performance of a small model. Recently, Vision Transformer (ViT) has…
cs.CV2022★ 3 cited
HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling
Zhongang Cai, Daxuan Ren, Ailing Zeng +12
4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications. With the advances of new sensors and algorithms, there is an increasing deman…
cs.CV2022★ 1 cited
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation
Ailing Zeng, Xuan Ju, Lei Yang +4
This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any perform…