Papers › A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos

A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos

13 Nov 2024arXiv:2411.08878archive 2025-07-28

Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman

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/

PaperPDFCode

Code

google-research/google-research officialmentioned in papertf report
sviprepetitioncounting/transrac officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Repetitive Action Counting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Repetitive Action Counting Countix RepNet MAE 0.3002 #3 of 3 Archive leaderboard report
Repetitive Action Counting Countix RepNet OBO 0.7047 #3 of 3 Archive leaderboard report
Repetitive Action Counting RepCount RepNet MAE 0.3308 #3 of 6 Archive leaderboard report
Repetitive Action Counting RepCount RepNet OBO 0.5329 #3 of 6 Archive leaderboard report
Repetitive Action Counting UCFRep RepNet MAE 0.2088 #2 of 2 Archive leaderboard report
Repetitive Action Counting UCFRep RepNet OBO 0.7333 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections