Multi-granularity Generator for Temporal Action Proposal

CVPR 2019 • Yuan Liu • Lin Ma • Yifeng Zhang • Wei Liu • Shih-Fu Chang

Temporal action proposal generation is an important task, aiming to localize the video segments containing human actions in an untrimmed video. In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on the video visual features equipped with the position embedding information... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Temporal Action Proposal Generation ActivityNet-1.3 MGG AUC (val) 66.43 # 2
Temporal Action Proposal Generation ActivityNet-1.3 MGG [email protected] 74.54 # 2
Action Recognition In Videos THUMOS’14 MGG UNet [email protected] 53.9 # 1
Action Recognition In Videos THUMOS’14 MGG UNet [email protected] 46.8 # 1
Action Recognition In Videos THUMOS’14 MGG UNet [email protected] 37.4 # 1