US PATENT DOCUMENTS 5,815,601 A 9, 1998 Katata et al. 5,974,181 A 10, 1999 Prieto
6,157,676 A 12/2000 Takaoka et al. 6,476,805 B1 1 1/2002 Shum et al. 6,654,503 B1 1 …

Techniques for improving the accuracy of prediction in intra frame coding. A prediction mode
can specify a pixel along a direction independently of other pixels along the same direc tion …

PREDICTION coded blocks using mode-dependent transform functions. In an embodiment,
an encoder selects a set of transform func tions to represent prediction error based on the …

(*) Notice: Subject to any disclaimer, the term of this 5,815.601 A 9, 1998 Katata et all patent
is extended or adjusted under 35 5.974 is 1 A 10, 1999 Prieto USC 154 (b) by 314 days …

A video decoder may receive, in a bitstream that comprises an encoded representation of
video data, information indicating whether a residual block is partitioned and information …

A method for compressing a digital image includes selecting an image patch of the digital
image; assigning the selected image patch to a specific class (z); transforming the image …

This thesis mainly focuses on the problem of finding good generative models of natural
images. Two main approaches are used to cope with the high dimensional problem of …

A block-based directional DCT framework has been developed recently in which the first
transform may choose to follow a direction other than the vertical or horizontal one–the …

There are provided methods and apparatus for transform selection in video coding. An
apparatus includes a video encoder for encoding at least a block in a picture by selecting a …

This thesis mainly focuses on the problem of finding good generative models of natural
images. Two main approaches are used to cope with the high dimensional problem of …