Journal
IEEE TRANSACTIONS ON CYBERNETICS
Volume 45, Issue 9, Pages 1967-1976Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2014.2362959
Keywords
Manifold regularized; multitask learning; scene recognition; sparse selection
Categories
Funding
- National Basic Research Program of China (973 Program) [2012CB719905]
- National Natural Science Foundation of China [61125106, 61472413, 61100079]
- Key Research Program of the Chinese Academy of Sciences [KGZD-EW-T03]
Ask authors/readers for more resources
Scene recognition has been widely studied to understand visual information from the level of objects and their relationships. Toward scene recognition, many methods have been proposed. They, however, encounter difficulty to improve the accuracy, mainly due to two limitations: 1) lack of analysis of intrinsic relationships across different scales, say, the initial input and its down-sampled versions and 2) existence of redundant features. This paper develops a semi-supervised learning mechanism to reduce the above two limitations. To address the first limitation, we propose a multitask model to integrate scene images of different resolutions. For the second limitation, we build a model of sparse feature selection-based manifold regularization (SFSMR) to select the optimal information and preserve the underlying manifold structure of data. SFSMR coordinates the advantages of sparse feature selection and manifold regulation. Finally, we link the multitask model and SFSMR, and propose the semi-supervised learning method to reduce the two limitations. Experimental results report the improvements of the accuracy in scene recognition.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available