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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dwibedi, Debidatta, Aytar, Yusuf, Tompson, Jonathan, Sermanet, Pierre, Zisserman, Andrew
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917836352389120
author Dwibedi, Debidatta
Aytar, Yusuf
Tompson, Jonathan
Sermanet, Pierre
Zisserman, Andrew
author_facet Dwibedi, Debidatta
Aytar, Yusuf
Tompson, Jonathan
Sermanet, Pierre
Zisserman, Andrew
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2411_08878
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
Dwibedi, Debidatta
Aytar, Yusuf
Tompson, Jonathan
Sermanet, Pierre
Zisserman, Andrew
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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/
title A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.08878