Finding Action Tubes
Preprint
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
All Related Versions
This publication has 27 references indexed in Scilit:
- Video Action Detection with Relational Dynamic-Poselets2014
- Human Focused Action Localization in Video2012
- A survey of vision-based methods for action representation, segmentation and recognitionComputer Vision and Image Understanding, 2011
- Convolutional Learning of Spatio-temporal Features2010
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Learning realistic human actions from movies2008
- Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition2008
- Histograms of Oriented Gradients for Human Detection2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- High Accuracy Optical Flow Estimation Based on a Theory for Warping2004