Home Publications
 
Home Publications
One-shot learning for real-time action recognition
Year: 2013 Keywords: real-time action recognition, one-shot action learning
Authors: Sean Ryan Fanello, Ilaria Gori, Giorgio Metta, Francesca Odone  
Editor: João M. Sanches, Luisa Micó, Jaime S. Cardoso Volume: 7887
Book title: Pattern Recognition and Image Analysis, 6th Iberian Conference, IbPRIA
Series: LNCS Pages: 31-40
   
Note:
Special Mention at ibPRIA 2013. Honorable Mention for the oral presentation of the paper "One-Shot Learning for Real-Time Action Recognition".
Abstract:
The goal of the paper is to develop a one-shot real-time learning and recognition system for 3D actions. We use RGBD images, combine motion and appearance cues, and map them into a new overcomplete space. The proposed method relies on descriptors based on 3D Histogram of Flow (3DHOF) and on Global Histogram of Oriented Gradient (GHOG); adaptive sparse coding (SC) is further applied to capture high-level patterns. We add effective on-line video segmentation and finally the recognition of actions through linear SVMs. The main contribution of the paper is a real-time system for one-shot action modeling; moreover we highlight the effectiveness of sparse coding techniques to represent 3D actions. We obtain very good results on the ChaLearn Gesture Dataset and with a Kinect sensor.
Digital version