Title
Localizing Actions Through Sequential 2D Video Projections
Abstract
Action detection in video is a particularly difficult problem because actions must not only be recognized correctly, but must also be localized in the 3D spatio-temporal volume. This paper introduces a technique that transforms the 3D localization problem into a series of 2D detection tasks. This is accomplished by dividing the video into overlapping segments, then representing each segment with a 2D video projection. The advantage of the 2D projection is that it makes it convenient to apply the best techniques from object detection to the action detection problem. Our experiments show that video projection outperforms the latest results on action detection in a direct comparison. © 2011 IEEE.
Publication Date
1-1-2011
Publication Title
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Number of Pages
34-39
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPRW.2011.5981747
Copyright Status
Unknown
Socpus ID
80054964871 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/80054964871
STARS Citation
Boyraz, Hakan; Tappen, Marshall F.; and Sukthankar, Rahul, "Localizing Actions Through Sequential 2D Video Projections" (2011). Scopus Export 2010-2014. 3149.
https://stars.library.ucf.edu/scopus2010/3149