ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention

Open paper
Benchmark Model Rank Results
3d-human-pose-estimation-on-human36mConvFormer (T=243, CPN)#16Average MPJPE (mm): 43.2Using 2D ground-truth joints: No…
3d-human-pose-estimation-on-humaneva-iConvFormer (T=43)#12Mean Reconstruction Error (mm): 24.3
3d-human-pose-estimation-on-mpi-inf-3dhpConvFormer#17MPJPE: 53.6AUC: 69.8PCK: 96.4

Rank counts only results with a code link.