2008 IEEE Conference on Computer Vision and Pattern Recognition 2008
DOI: 10.1109/cvpr.2008.4587806
|View full text |Cite
|
Sign up to set email alerts
|

Action recognition using ballistic dynamics

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
22
0

Year Published

2009
2009
2021
2021

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 45 publications
(23 citation statements)
references
References 17 publications
1
22
0
Order By: Relevance
“…The recognition rate of individual action is presented in a confusion matrix, shown in Figure 7. The results confirm that our method outperforms the similar state-of-the-art 2D based methods such as [12,19,21,24,29,[48][49][50][51][52] recorded in Table 2. It is important to be mentioned here that the number of classes, actors, and views used in experimentations vary among these methods.…”
Section: Comparison With Similar Methods On Ixmas Datasetsupporting
confidence: 74%
“…The recognition rate of individual action is presented in a confusion matrix, shown in Figure 7. The results confirm that our method outperforms the similar state-of-the-art 2D based methods such as [12,19,21,24,29,[48][49][50][51][52] recorded in Table 2. It is important to be mentioned here that the number of classes, actors, and views used in experimentations vary among these methods.…”
Section: Comparison With Similar Methods On Ixmas Datasetsupporting
confidence: 74%
“…Once the resulting video segments are obtained, sequence-based action recognition can be applied. Such a temporal segmentation is performed in [7], where atomic movements are localised in the video stream based on so-called 'ballistic movements'. These are defined as impulsive movements, which involve a sudden propulsion of the limbs, and rely on the acceleration and deceleration of start and end of the ballistic segments.…”
Section: Related Workmentioning
confidence: 99%
“…Boiman and Irani [21] proposed a graphical Bayesian model which describes the motion data using hidden variables that correspond to hidden ensembles in a database of spatio-temporal patches. Vitaladevuni, Kellokumpu and Davis [22] presented a Bayesian framework for action recognition through ballistic dynamics.…”
Section: Related Workmentioning
confidence: 99%