On recognizing actions in still images via multiple features
Author
Şener, Fadime
Bas, C.
Ikizler-Cinbis, N.
Date
2012Source Title
Computer Vision – ECCV 2012. Workshops and Demonstrations
Print ISSN
0302-9743
Publisher
Springer, Berlin, Heidelberg
Volume
3
Pages
263 - 272
Language
English
Type
Conference PaperItem Usage Stats
182
views
views
253
downloads
downloads
Abstract
We propose a multi-cue based approach for recognizing human actions in still images, where relevant object regions are discovered and utilized in a weakly supervised manner. Our approach does not require any explicitly trained object detector or part/attribute annotation. Instead, a multiple instance learning approach is used over sets of object hypotheses in order to represent objects relevant to the actions. We test our method on the extensive Stanford 40 Actions dataset [1] and achieve significant performance gain compared to the state-of-the-art. Our results show that using multiple object hypotheses within multiple instance learning is effective for human action recognition in still images and such an object representation is suitable for using in conjunction with other visual features. © 2012 Springer-Verlag.
Keywords
Data setsHuman actions
Human-action recognition
Multiple features
Multiple instance learning
Multiple objects
Object detectors
Object region
Object representations
Performance Gain
Stanford
Still images
Visual feature
Gesture recognition
Learning systems
Statistical tests
Computer vision
Permalink
http://hdl.handle.net/11693/28150Published Version (Please cite this version)
http://dx.doi.org/10.1007/978-3-642-33885-4_27https://doi.org/10.1007/978-3-642-33885-4