CASE + Zhou et al.

Reported on 5 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

VideoonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
49.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Temporal Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
49.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
49.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Weakly Supervised Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
49.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138

Methodology1 result

Zero-Shot LearningonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
49.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138