A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet,, Andrew Zisserman
TL;DR
This paper critically examines the evaluation methods of RepNet for temporal repetition counting in videos, providing standardized results, releasing code, and checkpoints to improve reproducibility and consistency in future research.
Contribution
It identifies evaluation issues with RepNet, offers standardized performance results across datasets, and releases code and checkpoints for reproducibility.
Findings
RepNet performance varies across datasets due to evaluation inconsistencies.
Standardized evaluation code and checkpoints are provided.
Reproducible results facilitate fair comparison and future improvements.
Abstract
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/
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Video Analysis and Summarization · Human Pose and Action Recognition