Actionness Estimation Using Hybrid Fully Convolutional Networks
arXiv:1604.07279
Abstract
Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location. Accurate and efficient estimation of actionness is important in video analysis and may benefit other relevant tasks such as action recognition and action detection. This paper presents a new deep architecture for actionness estimation, called hybrid fully convolutional network (H-FCN), which is composed of appearance FCN (A-FCN) and motion FCN (M-FCN). These two FCNs leverage the strong capacity of deep models to estimate actionness maps from the perspectives of static appearance and dynamic motion, respectively. In addition, the fully convolutional nature of H-FCN allows it to efficiently process videos with arbitrary sizes. Experiments are conducted on the challenging datasets of Stanford40, UCF Sports, and JHMDB to verify the effectiveness of H-FCN on actionness estimation, which demonstrate that our method achieves superior performance to previous ones. Moreover, we apply the estimated actionness maps on action proposal generation and action detection. Our actionness maps advance the current state-of-the-art performance of these tasks substantially.
arXiv commentaccepted by CVPR16
References in corpus (7)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- Towards Good Practices for Very Deep Two-Stream ConvNets
- How good are detection proposals, really?
Cited by in corpus (6)
- R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network
- Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation
- Incremental Tube Construction for Human Action Detection
- Context-Aware RCNN: A Baseline for Action Detection in Videos
- Weakly Supervised Action Selection Learning in Video