Learning a non-linear knowledge transfer model for cross-view action recognition
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2458-2466
Abstract
This paper concerns action recognition from unseen and unknown views. We propose unsupervised learning of a non-linear model that transfers knowledge from multiple views to a canonical view. The proposed Non-linear Knowledge Transfer Model (NKTM) is a deep network, with weight decay and sparsity constraints, which finds a shared high-level virtual path from videos captured from different unknown viewpoints to the same canonical view. The strength of our technique is that we learn a single NKTM for all actions and all camera viewing directions. Thus, NKTM does not require action labels during learning and knowledge of the camera viewpoints during training or testing. NKTM is learned once only from dense trajectories of synthetic points fitted to mocap data and then applied to real video data. Trajectories are coded with a general codebook learned from the same mocap data. NKTM is scalable to new action classes and training data as it does not require re-learning. Experiments on the IXMAS and N-UCLA datasets show that NKTM outperforms existing state-of-the-art methods for cross-view action recognition.Keywords
This publication has 25 references indexed in Scilit:
- Dense Trajectories and Motion Boundary Descriptors for Action RecognitionInternational Journal of Computer Vision, 2013
- A Practical Guide to Training Restricted Boltzmann Machines2012
- Practical Recommendations for Gradient-Based Training of Deep Architectures2012
- Contour graph based human tracking and action sequence recognitionPattern Recognition, 2008
- Direct visibility of point setsACM Transactions on Graphics, 2007
- Free viewpoint action recognition using motion history volumesComputer Vision and Image Understanding, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- View Invariance for Human Action RecognitionInternational Journal of Computer Vision, 2006
- On Space-Time Interest PointsInternational Journal of Computer Vision, 2005
- Task-specific gesture analysis in real-time using interpolated viewsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996