Contextual Action Recognition with R* CNN
Authors:
- Georgia GkioxariGGGeorgia Gkioxari
- Ross GirshickRGRoss Girshick
- Jitendra MalikJMJitendra Malik
Top Cited Papers
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1080-1088
Abstract
There are multiple cues in an image which reveal what action a person is performing. For example, a jogger has a pose that is characteristic for jogging, but the scene (e.g. road, trail) and the presence of other joggers can be an additional source of information. In this work, we exploit the simple observation that actions are accompanied by contextual cues to build a strong action recognition system. We adapt RCNN to use more than one region for classification while still maintaining the ability to localize the action. We call our system R*CNN. The action-specific models and the feature maps are trained jointly, allowing for action specific representations to emerge. R*CNN achieves 90.2% mean AP on the PASAL VOC Action dataset, outperforming all other approaches in the field by a significant margin. Last, we show that R*CNN is not limited to action recognition. In particular, R*CNN can also be used to tackle fine-grained tasks such as attribute classification. We validate this claim by reporting state-of-the-art performance on the Berkeley Attributes of People dataset.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Fast R-CNN2015
- Actions and Attributes from Wholes and Parts2015
- Finding action tubes2015
- PANDA: Pose Aligned Networks for Deep Attribute Modeling2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Action Recognition From Weak Alignment of Body Parts2014
- Action Recognition with Improved Trajectories2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Combining randomization and discrimination for fine-grained image categorization2011
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989