Most sports analysis research often moves from performance to motion: starting with the outcomes and working backward to explain them.

Once each stroke could be represented in the compressed form, it was possible to compare them. Two putting strokes might

At this point, the core question became unavoidable: how do you learn structure from motion without defining that structure in

Once I had reliable stroke trajectories, the new problem that appeared was that raw motion data is overwhelming. A putting

Happy new year! After re-framing the putting as a time-series problem, the next question was how you can capture the