Conference item icon

Conference item

Human focused action localization in video

Abstract:

We propose a novel human-centric approach to detect and localize human actions in challenging video data, such as Hollywood movies. Our goal is to localize actions in time through the video and spatially in each frame. We achieve this by first obtaining generic spatio-temporal human tracks and then detecting specific actions within these using a sliding window classifier.


We make the following contributions: (i) We show that splitting the action localization task into spatial and temporal search leads to an efficient localization algorithm where generic human tracks can be reused to recognize multiple human actions; (ii) We develop a human detector and tracker which is able to cope with a wide range of postures, articulations, motions and camera viewpoints. The tracker includes detection interpolation and a principled classification stage to suppress false positive tracks; (iii) We propose a track-aligned 3D-HOG action representation, investigate its parameters, and show that action localization benefits from using tracks; and (iv) We introduce a new action localization dataset based on Hollywood movies.


Results are presented on a number of real-world movies with crowded, dynamic environment, partial occlusion and cluttered background. On the Coffee&Cigarettes dataset we significantly improve over the state of the art. Furthermore, we obtain excellent results on the new Hollywood–Localization dataset.

Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1007/978-3-642-35749-7_17

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Brasenose College
Role:
Author
ORCID:
0000-0002-8945-8573


Publisher:
Springer
Host title:
Trends and Topics in Computer Vision: ECCV 2010 Workshops, Heraklion, Crete, Greece, September 10-11, 2010, Revised Selected Papers, Part I
Volume:
6553
Pages:
219–233
Series:
Lecture Notes in Computer Science
Publication date:
2012-11-23
Event title:
11th European Conference on Computer Vision (ECCV 2010)
Event location:
Heraklion, Greece
Event website:
https://projects.ics.forth.gr/eccv2010/intro.php
Event start date:
2010-09-05
Event end date:
2010-09-11
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
EISBN:
9783642357497
ISBN:
9783642357480


Language:
English
Pubs id:
1770604
Local pid:
pubs:1770604
Deposit date:
2024-07-19
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP