STGSFormer: a 3d human pose estimation model that integrates GCN and self-attention in the spatio-temporal domain

Related articles

1. TCFNet: An End-to-End Framework for Multimodal Action Quality Assessment via Temporal Enhancement and Contrastive Fusion

   This article has 4 authors:

   1. Zhenxian Lin
   2. Minghui Zhang
   3. Chengmao Wu
   4. Mingzhu Zhang

2. TriORU2-Net++: Attention-Guided Three-StageU2-Net++ for Light Field Occlusion Removal

   This article has 5 authors:

   1. Mostafa Farouk Senussi
   2. Mahmoud Abdalla
   3. Mahmoud SalahEldin Kasem
   4. Mohamed Mahmoud
   5. Hyun-Soo Kang

3. SPARK: Sparse-Perception Action Recognition with Keyframes for Quadruped Robots

   This article has 2 authors:

   1. Sehun Park
   2. Andrew Jaeyong Choi