Contextual Action Recognition with R* CNN
- 1 December 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2015 IEEE International Conference on Computer Vision (ICCV)
- p. 1080-1088
- https://doi.org/10.1109/iccv.2015.129
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
Other Versions
This publication has 22 references indexed in Scilit:
- Fast R-CNNPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Actions and Attributes from Wholes and PartsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Finding action tubesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- PANDA: Pose Aligned Networks for Deep Attribute ModelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Action Recognition From Weak Alignment of Body PartsPublished by British Machine Vision Association and Society for Pattern Recognition ,2014
- Action Recognition with Improved TrajectoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Combining randomization and discrimination for fine-grained image categorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989