HyperAIHyperAI

Command Palette

Search for a command to run...

3 months ago

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

Debidatta Dwibedi Yusuf Aytar Jonathan Tompson Pierre Sermanet Andrew Zisserman

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

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/

Code Repositories

Benchmarks

BenchmarkMethodologyMetrics
repetitive-action-counting-on-countixRepNet
MAE: 0.3002
OBO: 0.7047
repetitive-action-counting-on-repcountRepNet
MAE: 0.3308
OBO: 0.5329
repetitive-action-counting-on-ucfrepRepNet
MAE: 0.2088
OBO: 0.7333

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp
A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos | Papers | HyperAI