2 papers
cs.CV2025
3D Human Pose Estimation via Spatial Graph Order Attention and Temporal Body Aware Transformer
Kamel Aouaidjia, Aofan Li, Wenhao Zhang +1
Nowadays, Transformers and Graph Convolutional Networks (GCNs) are the prevailing techniques for 3D human pose estimation. However, Transformer-based methods either ignore the spat…
cs.CV2025
Improving action segmentation via explicit similarity measurement
Kamel Aouaidjia, Wenhao Zhang, Aofan Li +1
Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependenc…