3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization

Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models... (read more)

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Action Classification ActivityNet-1.2 3C-Net mAP 92.4 # 2
Weakly Supervised Action Localization ActivityNet-1.2 3C-Net mAP@0.5 37.2 # 5
Mean mAP 21.7 # 4
Action Classification THUMOS'14 3C-Net mAP 86.9 # 1
Weakly Supervised Action Localization THUMOS’14 3C-Net mAP@0.5 26.6 # 8
Action Classification THUMOS’14 3C-Net mAP 86.9 # 1
Weakly Supervised Action Localization THUMOS 2014 3C-Net mAP@0.5 26.6 # 6

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet