3 papers
cs.CV2024
Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer
Wenhan Wu, Ce Zheng, Zihao Yang +3
Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action…
cs.CV2024
Multi-View Attentive Contextualization for Multi-View 3D Object Detection
Xianpeng Liu, Ce Zheng, Ming Qian +5
We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detectio…
cs.CV2024
A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation
Qucheng Peng, Ce Zheng, Chen Chen
3D human pose data collected in controlled laboratory settings present challenges for pose estimators that generalize across diverse scenarios. To address this, domain generalizati…