Semi-Supervised Image-to-Video Adaptation for Video Action Recognition
Authors:
- 14 March 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 47 (4) , 960-973
Abstract
Human action recognition has been well explored in applications of computer vision. Many successful action recognition methods have shown that action knowledge can be effectively learned from motion videos or still images. For the same action, the appropriate action knowledge learned from different types of media, e.g., videos or images, may be related. However, less effort has been made to improve the performance of action recognition in videos by adapting the action knowledge conveyed from images to videos. Most of the existing video action recognition methods suffer from the problem of lacking sufficient labeled training videos. In such cases, over-fitting would be a potential problem and the performance of action recognition is restrained. In this paper, we propose an adaptation method to enhance action recognition in videos by adapting knowledge from images. The adapted knowledge is utilized to learn the correlated action semantics by exploring the common components of both labeled videos and images. Meanwhile, we extend the adaptation method to a semi-supervised framework which can leverage both labeled and unlabeled videos. Thus, the over-fitting can be alleviated and the performance of action recognition is improved. Experiments on public benchmark datasets and real-world datasets show that our method outperforms several other state-of-the-art action recognition methods.Keywords
Funding Information
- National Natural Science Foundation of China (U1509206, 61472276, 61373103, 61432011, 61222210)
- Project of Hebei Province Higher Educational Science and Technology Research (QN2015317)
This publication has 39 references indexed in Scilit:
- Knowledge Adaptation with PartiallyShared Features for Event DetectionUsing Few ExemplarsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Weakly-Supervised Cross-Domain Dictionary Learning for Visual RecognitionInternational Journal of Computer Vision, 2014
- Image Attribute AdaptationIEEE Transactions on Multimedia, 2014
- Multilevel Chinese Takeaway Process and Label-Based Processes for Rule Induction in the Context of Automated Sports Video AnnotationIEEE Transactions on Cybernetics, 2014
- Spatio-Temporal Laplacian Pyramid Coding for Action RecognitionIEEE Transactions on Cybernetics, 2013
- Dense Trajectories and Motion Boundary Descriptors for Action RecognitionInternational Journal of Computer Vision, 2013
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Shape matching and object recognition using shape contextsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Nonlinear Component Analysis as a Kernel Eigenvalue ProblemNeural Computation, 1998