Simple Baselines for Human Pose Estimation and Tracking
This work addresses the difficulty in algorithm analysis and comparison for researchers in computer vision, though it appears incremental by focusing on simplification rather than a new paradigm.
The paper tackled the increasing complexity in human pose estimation and tracking algorithms by providing simple and effective baseline methods, achieving state-of-the-art results on challenging benchmarks.
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 comparison more difficult. This work provides simple and effective baseline methods. They are helpful for inspiring and evaluating new ideas for the field. State-of-the-art results are achieved on challenging benchmarks. The code will be available at https://github.com/leoxiaobin/pose.pytorch.