Learning Latent Super-Events to Detect Multiple Activities in Videos

CVPR 2018 AJ PiergiovanniMichael S. Ryoo

In this paper, we introduce the concept of learning latent super-events from activity videos, and present how it benefits activity detection in continuous videos. We define a super-event as a set of multiple events occurring together in videos with a particular temporal organization; it is the opposite concept of sub-events... (read more)

PDF Abstract

Evaluation Results from the Paper


#2 best model for Action Detection on Charades (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Action Detection Charades Super-events mAP 19.41 # 2
Action Detection Multi-THUMOS Super-events mAP 36.4 # 2