• Publications
  • Influence
Database retrieval for similar images using ICA and PCA bases
TLDR
Similar-image retrieval systems using ICA and PCA bases using weighted inner products of similar bases . Expand
  • 43
  • 3
Independent Component Analysis Minimizing Convex Divergence
TLDR
A new class of learning algorithms for independent component analysis (ICA) is presented. Expand
  • 11
Towards the Unification of Human Movement, Animation and Humanoid in the Network
TLDR
A network environment that unifies the human movement, animation and humanoid is generated. Expand
  • 4
/spl alpha/-EM algorithm and /spl alpha/-ICA learning based upon extended logarithmic information measures
TLDR
A general property of the /spl alpha/-logarithm is expected to be effective to speedup of convergence, i.e., on the improvement of learning aptitude. Expand
  • 8
Retrieval-Aware Image Compression, Its Format and Viewer Based Upon Learned Bases
TLDR
A retrieval-aware image format (rim format) is developed for the usage in the similar-image retrieval. Expand
  • 2
  • PDF
Optimization transfer for computational learning: a hierarchy from f-ICA and alpha-EM to their offsprings
TLDR
Likelihood optimization methods for learning algorithms are generalized and faster algorithms are provided. Expand
  • 3
Independent Component Analysis Using Convex Divergence
The convex divergence is used as a surrogate function for obtaining a class of ICA algorithms (Independent Component Analysis) called the f-ICA. The convex divergence is a super class ofExpand
  • 3
  • PDF
INDEPENDENT COMPONENT ANALYSIS WITH JOINT SPEEDUP AND SUPERVISORY CONCEPT INJECTION : APPLICATIONS TO BRAIN fMRI MAP DISTILLATION
Methods to combine speedup terms and supervisory concept injection are presented. The speedup is based upon iterative optimization of the convex divergence. The injection of supervisory informationExpand
Image-to-Image Retrieval Using Computationally Learned Bases and Color Information
TLDR
New methods for joint compression and Image-to-image retrieval (12I retrieval) are presented. Expand