When will you do what? - Anticipating Temporal Occurrences of Activities

Analyzing human actions in videos has gained increased attention recently. While most works focus on classifying and labeling observed video frames or anticipating the very recent future, making long-term predictions over more than just a few seconds is a task with many practical applications that h...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 5343 - 5352
Main Authors Farha, Yazan Abu, Richard, Alexander, Gall, Juergen
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Labeling
Matrix converters
Sports
Task analysis
Training
Videos
Visualization
Online AccessGet full text

Cover

More Information
Summary:Analyzing human actions in videos has gained increased attention recently. While most works focus on classifying and labeling observed video frames or anticipating the very recent future, making long-term predictions over more than just a few seconds is a task with many practical applications that has not yet been addressed. In this paper, we propose two methods to predict a considerably large amount of future actions and their durations. Both, a CNN and an RNN are trained to learn future video labels based on previously seen content. We show that our methods generate accurate predictions of the future even for long videos with a huge amount of different actions and can even deal with noisy or erroneous input information.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00560