• Publications
  • Influence
A compressed domain scheme for classifying block edge patterns
TLDR
A fast and systematic algorithm for detecting and classifying edge components of each block in discrete cosine transform (DCT)-compressed images. Expand
  • 65
  • 6
Nonnegative matrix partial co-factorization for drum source separation
TLDR
We present nonnegative matrix partial co-factorization (NMPCF) where the target matrix (spectrograms of music) and drum-only-matrix (collected from various drums) are simultaneously decomposed, sharing some factor matrix partially, to force some portion of basis vectors to be associated with drums only. Expand
  • 57
  • 5
  • PDF
Spatial Audio Object Coding With Two-Step Coding Structure for Interactive Audio Service
TLDR
An interactive audio service is a new conceptual audio service that provides the users with opportunities for a variety of experiences on the alternative and advanced audio services. Expand
  • 10
  • 4
  • PDF
Nonnegative Matrix Partial Co-Factorization for Spectral and Temporal Drum Source Separation
TLDR
We address a problem of separating drum sources from monaural mixtures of polyphonic music containing various pitched instruments as well as drums. Expand
  • 51
  • 3
  • PDF
Personalized Contents Guide and Browsing based on User Preference
Main objectives of metadata usage on the side of set-top shall be easy access to contents or certain parts of contents that user wants. Based on metadata description compatible to the TV-AnytimeExpand
  • 18
  • 2
Agent-based intelligent multimedia broadcasting within MPEG-21 multimedia framework
TLDR
In this paper, we introduce an agent-based multimedia broadcasting framework using the Foundation for Intelligent Physical Agents (FIPA) and MPEG-7 technologies within MPEG-21. Expand
  • 20
  • 1
  • PDF
Blind rhythmic source separation: Nonnegativity and repeatability
TLDR
An unsupervised method is proposed aiming at extracting rhythmic sources from commercial polyphonic music whose number of channels is limited to one. Expand
  • 15
  • 1
  • PDF
An Efficient Time-Frequency Representation for Parametric-Based Audio Object Coding
TLDR
A reconfigured T/F structure is also proposed to enhance the generating performance of sound scenes such as ‘karaoke’ and ‘solo’ play in interactive music scenarios. Expand
  • 4
  • 1
  • PDF
The development of MPEG-7 interface over MPEG-4
TLDR
The paper presents the first results of research on the MPEG-7 interface over MPEG-4 systems, which makes it easy to search MPEG- 4 content. Expand
  • 3
  • 1
Summarization of news video and its description for content‐based access
TLDR
A video summary abstracts the entirety with the gist without losing the essential content of the original video and also facilitates efficient content‐based access to the desired content. Expand
  • 24