Proceedings of 1994 Workshop on Information Theory and Statistics
DOI: 10.1109/wits.1994.513905
|View full text |Cite
|
Sign up to set email alerts
|

Source coding with a reversible memory-binding probability density transformation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Publication Types

Select...
1

Relationship

1
0

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 1 publication
0
1
0
Order By: Relevance
“…We focus here upon a permutation transform as a separate coding stage, termed a memory-binding-transform (MBT) [11] which blends permutation, ranking, and coding concepts to bind memory information to a transformed symbol set by using a probability model to associate permutations with the memory space. The MBT performs well for traditional sources, but is of particular value for more challenging categorical data sources, such as codebook indices, to the extent that appropriate probability models can be constructed.…”
Section: Introductionmentioning
confidence: 99%
“…We focus here upon a permutation transform as a separate coding stage, termed a memory-binding-transform (MBT) [11] which blends permutation, ranking, and coding concepts to bind memory information to a transformed symbol set by using a probability model to associate permutations with the memory space. The MBT performs well for traditional sources, but is of particular value for more challenging categorical data sources, such as codebook indices, to the extent that appropriate probability models can be constructed.…”
Section: Introductionmentioning
confidence: 99%