repnet
A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
Dwibedi, Debidatta, Aytar, Yusuf, Tompson, Jonathan, Sermanet, Pierre, Zisserman, Andrew
We discuss some consistent issues on how RepNet has been evaluated in various papers. As a way to mitigate these issues, we report RepNet performance results on different datasets, and release evaluation code and the RepNet checkpoint to obtain these results. Code URL: https://github.com/google-research/google-research/blob/master/repnet/
Why the RepNet is so important
In our daily lives, repeating actions occur frequently. The need to recognise these repetitions, like those in videos, is unavoidable and requires a system that can identify and count repetitions. Think exercising -- how many repetitions are you doing? Isolating repeating actions is a difficult task. I know, it seems pretty straight forward when you see someone in front of you jumping up and down but translating that into the form of a machine learning problem makes it much more difficult.