Paper published in a book (Scientific congresses, symposiums and conference proceedings)
A Revisit of Action Detection using Improved Trajectories
Papadopoulos, Konstantinos; Antunes, Michel; Aouada, Djamila et al.
2018In IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Alberta, Canada, 15–20 April 2018
Peer reviewed
 

Files


Full Text
camera-ready.pdf
Author preprint (269.64 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
action detection; improved trajectories; action proposals
Abstract :
[en] In this paper, we revisit trajectory-based action detection in a potent and non-uniform way. Improved trajectories have been proven to be an effective model for motion description in action recognition. In temporal action localization, however, this approach is not efficiently exploited. Trajectory features extracted from uniform video segments result in significant performance degradation due to two reasons: (a) during uniform segmentation, a significant amount of noise is often added to the main action and (b) partial actions can have negative impact in classifier's performance. Since uniform video segmentation seems to be insufficient for this task, we propose a two-step supervised non-uniform segmentation, performed in an online manner. Action proposals are generated using either 2D or 3D data, therefore action classification can be directly performed on them using the standard improved trajectories approach. We experimentally compare our method with other approaches and we show improved performance on a challenging online action detection dataset.
Disciplines :
Computer science
Author, co-author :
Papadopoulos, Konstantinos ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Antunes, Michel
Aouada, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Ottersten, Björn ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
no
Language :
English
Title :
A Revisit of Action Detection using Improved Trajectories
Publication date :
2018
Event name :
International Conference on Acoustics, Speech and Signal Processing
Event organizer :
IEEE
Event place :
Calgary, Alberta, Canada
Event date :
from 15-04-2018 to 20-04-2018
Main work title :
IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Alberta, Canada, 15–20 April 2018
Peer reviewed :
Peer reviewed
Focus Area :
Security, Reliability and Trust
FnR Project :
FNR10415355 - 3d Action Recognition Using Refinement And Invariance Strategies For Reliable Surveillance, 2015 (01/06/2016-31/05/2019) - Bjorn Ottersten
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 22 February 2018

Statistics


Number of views
174 (24 by Unilu)
Number of downloads
386 (29 by Unilu)

Scopus citations®
 
4
Scopus citations®
without self-citations
0

Bibliography


Similar publications



Contact ORBilu