This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Actionness Estimation Using Hybrid Fully Convolutional Networks

Limin Wang and Yu Qiao and Xiaoou Tang and Luc Van Gool
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
June 2016


Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific lo- cation. Accurate and efficient estimation of actionness is important in video analysis and may benefit other rele- vant 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.

Download in pdf format
  author = {Limin Wang and Yu Qiao and Xiaoou Tang and Luc Van Gool},
  title = {Actionness Estimation Using Hybrid Fully Convolutional Networks},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
  month = {June},
  pages = {2708-2717},
  keywords = {}