DocumentCode :
3672139
Title :
Finding action tubes
Author :
Georgia Gkioxari;Jitendra Malik
Author_Institution :
UC Berkeley, USA
fYear :
2015
fDate :
6/1/2015 12:00:00 AM
Firstpage :
759
Lastpage :
768
Abstract :
We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance and motion in two ways. First, starting from image region proposals we select those that are motion salient and thus are more likely to contain the action. This leads to a significant reduction in the number of regions being processed and allows for faster computations. Second, we extract spatio-temporal feature representations to build strong classifiers using Convolutional Neural Networks. We link our predictions to produce detections consistent in time, which we call action tubes. We show that our approach outperforms other techniques in the task of action detection.
Keywords :
"Videos","Feature extraction","Electron tubes","Support vector machines","Shape","Optical imaging","Training"
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on
Electronic_ISBN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2015.7298676
Filename :
7298676
Link To Document :
بازگشت