DocumentCode :
157932
Title :
Coupling video segmentation and action recognition
Author :
Ghodrati, Amir ; Pedersoli, Marco ; Tuytelaars, Tinne
Author_Institution :
ESAT-PSI, KULeuven, Leuven, Belgium
fYear :
2014
fDate :
24-26 March 2014
Firstpage :
618
Lastpage :
625
Abstract :
Recently a lot of progress has been made in the field of video segmentation. The question then arises whether and how these results can be exploited for this other video processing challenge, action recognition. In this paper we show that a good segmentation is actually very important for recognition. We propose and evaluate several ways to integrate and combine the two tasks: i) recognition using a standard, bottom-up segmentation, ii) using a top-down segmentation geared towards actions, iii) using a segmentation based on inter-video similarities (co-segmentation), and iv) tight integration of recognition and segmentation via iterative learning. Our results clearly show that, on the one hand, the two tasks are interdependent and therefore an iterative optimization of the two makes sense and gives better results. On the other hand, comparable results can also be obtained with two separate steps but mapping the feature-space with a non-linear kernel.
Keywords :
image segmentation; iterative methods; learning systems; object recognition; video signal processing; action recognition; bottom-up segmentation; intervideo similarities; iterative learning; iterative optimization; top-down segmentation; video segmentation; Hafnium; Image segmentation; Kernel; Motion segmentation; Support vector machines; Training; Trajectory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Applications of Computer Vision (WACV), 2014 IEEE Winter Conference on
Conference_Location :
Steamboat Springs, CO
Type :
conf
DOI :
10.1109/WACV.2014.6836045
Filename :
6836045
Link To Document :
بازگشت