@techreport{oai:ipsj.ixsq.nii.ac.jp:00141863,
 author = {Cuicui, Zhang and Xuefeng, Liang and Takashi, Matsuyama and Cuicui, Zhang and Xuefeng, Liang and Takashi, Matsuyama},
 issue = {33},
 month = {May},
 note = {Visual feature learning is fundamental to many computer vision tasks. State-of-art methods adopt an image block based multilayer framework to learn hierarchical feature representations. However, the image block is not adaptive for low-level feature extraction and the image pyramid based hierarchical models are neither adaptive nor flexible enough to learn high-level features. To solve these problems, this thesis exploits the image spatial and hierarchical structure using Quad-Trees and employs them for local feature analysis and for hierarchical feature learning. To evaluate the reliability of our methods, we also conduct feature learning in other challenging situations: feature learning with small training data and feature learning in dynamic environments (moving camera videos). Face recognition and motion segmentation are utilized as research backgrounds for algorithm evaluation. Experimental results demonstrate the effectiveness of our methods., Visual feature learning is fundamental to many computer vision tasks. State-of-art methods adopt an image block based multilayer framework to learn hierarchical feature representations. However, the image block is not adaptive for low-level feature extraction and the image pyramid based hierarchical models are neither adaptive nor flexible enough to learn high-level features. To solve these problems, this thesis exploits the image spatial and hierarchical structure using Quad-Trees and employs them for local feature analysis and for hierarchical feature learning. To evaluate the reliability of our methods, we also conduct feature learning in other challenging situations: feature learning with small training data and feature learning in dynamic environments (moving camera videos). Face recognition and motion segmentation are utilized as research backgrounds for algorithm evaluation. Experimental results demonstrate the effectiveness of our methods.},
 title = {Quad-Tree based Image Encoding Methods for Data-Adaptive Visual Feature Learning},
 year = {2015}
}