We present EgoHumans, a new multi-view multi-human video benchmark to ad...
Ensemble approaches for deep-learning-based semantic segmentation remain...
Multi-Object Tracking (MOT) has rapidly progressed with the development ...
Top-down methods for monocular human mesh recovery have two stages: (1)
...
The use of iterative pose refinement is a critical processing step for 6...
A key assumption of top-down human pose estimation approaches is their
e...
We address the issue of learning from synthetic domain randomized data
e...
We address the issue of domain gap when making use of synthetic data to ...