AutoLoc: Weakly-Supervised Temporal Action Localization in Untrimmed Videos.

Zheng Shou Hang Gao Lei Zhang Kazuyuki Miyazawa Shih-Fu Chang

Published in: ECCV (16) (2018)

Keyphrases

weakly supervised
object localization
weakly labeled
relation extraction
superpixels
object class
topic models
video sequences
semi supervised
input image
video frames
named entities
video data
object recognition
semantic relations
long range
learning algorithm