Modeling Video Evolution for Action Recognition
Abstract
In this paper we present a method to capture video-wide temporal information for action recognition. We postulate that a function capable of ordering the frames of a video temporally (based on the appearance) captures well the evolution of the appearance within the video. We learn such ranking functions per video via a ranking machine and use the parameters of these as a new video representation. The proposed method is easy to interpret and implement, fast to compute and effective in recognizing a wide variety of actions. We perform a large number of evaluations on datasets for generic action recognition (Hollywood2 and HMDB51), fine-grained actions (MPII- cooking activities) and gestures (Chalearn). Results show that the proposed method brings an absolute improvement of 7-10\%, while being compatible with and complementary to further improvements in appearance and local motion based methods.
Cite
Text
Fernando et al. "Modeling Video Evolution for Action Recognition." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299176Markdown
[Fernando et al. "Modeling Video Evolution for Action Recognition." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/fernando2015cvpr-modeling/) doi:10.1109/CVPR.2015.7299176BibTeX
@inproceedings{fernando2015cvpr-modeling,
title = {{Modeling Video Evolution for Action Recognition}},
author = {Fernando, Basura and Gavves, Efstratios and M., Jose Oramas and Ghodrati, Amir and Tuytelaars, Tinne},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2015},
doi = {10.1109/CVPR.2015.7299176},
url = {https://mlanthology.org/cvpr/2015/fernando2015cvpr-modeling/}
}