Simple Baselines for Human Pose Estimation and Tracking
share
There has been significant progress on pose estimation and increasing interests on pose tracking in recent years. At the same time, the overall algorithm and system complexity increases as well, making the algorithm analysis and evaluation more difficult. This work provides baseline methods that are surprisingly simple and effective, thus helpful for inspiring and evaluating new ideas for the field. State-of-the-art results are achieved on challenging benchmarks. The code will be released.
READ FULL TEXT