BMN: Boundary-Matching Network for Temporal Action Proposal Generation

ICCV 2019 Tianwei LinXiao LiuXin LiErrui DingShilei Wen

Temporal action proposal generation is an challenging and promising task which aims to locate temporal regions in real-world videos where action or event may occur. Current bottom-up proposal generation methods can generate proposals with precise boundary, but cannot efficiently generate adequately reliable confidence scores for retrieving proposals... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Temporal Action Localization ActivityNet-1.3 BMN mAP [email protected] 50.07 # 2
mAP 36.42 # 1
Temporal Action Proposal Generation ActivityNet-1.3 BMN AUC (val) 67.1 # 1
[email protected] 75.01 # 1
Temporal Action Localization THUMOS’14 BMN mAP [email protected] 32.2 # 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