Share

Authors: Georgia Gkioxari,Jitendra Malik
Where published: CVPR 2015 6
ArXiv: 1411.6031
Document:  PDF  DOI 
Abstract URL: http://arxiv.org/abs/1411.6031v1


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.

Relevant initiatives   Hide

Comments   Hide

Please log in to add your comments!