Unsupervised Cross-Modal Alignment
Reported on 5 benchmarks across 5 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Computer Vision3 results
- 3DPCK· 2020-08-0478.4best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
- 3DPCK· 2020-08-0478.4best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
- 3DPCK· 2020-08-0478.4best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Methodology1 result
- 78.4best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Audio1 result
- 3DPCK· 2020-08-0478.4best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)