Action Recognition Using Discriminative Structured Trajectory Groups
Name:
Action Recognition using Discriminative Structured Trajectory Groups.pdf
Size:
5.701Mb
Format:
PDF
Description:
Accepted Manuscript
Type
Conference PaperKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionElectrical Engineering Program
Image and Video Understanding Lab
VCC Analytics Research Group
Visual Computing Center (VCC)
Date
2015-02-24Online Publication Date
2015-02-24Print Publication Date
2015-01Permanent link to this record
http://hdl.handle.net/10754/556158
Metadata
Show full item recordAbstract
In this paper, we develop a novel framework for action recognition in videos. The framework is based on automatically learning the discriminative trajectory groups that are relevant to an action. Different from previous approaches, our method does not require complex computation for graph matching or complex latent models to localize the parts. We model a video as a structured bag of trajectory groups with latent class variables. We model action recognition problem in a weakly supervised setting and learn discriminative trajectory groups by employing multiple instance learning (MIL) based Support Vector Machine (SVM) using pre-computed kernels. The kernels depend on the spatio-temporal relationship between the extracted trajectory groups and their associated features. We demonstrate both quantitatively and qualitatively that the classification performance of our proposed method is superior to baselines and several state-of-the-art approaches on three challenging standard benchmark datasets.Citation
Indriyati Atmosukarto, Narendra Ahuja, Bernard Ghanem "Action Recognition using Discriminative Structured Trajectory Groups" Winter Conference on Applications of Computer Vision (WACV 2015)Conference/Event name
2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015Additional Links
http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7045978http://vcc.kaust.edu.sa/Documents/B.%20Ghanem/papers/action_recognition_wacv2015.pdf
ae974a485f413a2113503eed53cd6c53
10.1109/WACV.2015.124