(57) ABSTRACT A deep learning based compression (DLBC) system applies trained
models to compress binary code of an input image to a target codelength. For a set of binary …

The present disclosure relates to video encoding or decoding and, more specifically, to an
apparatus and a method for applying an artificial neural network (ANN) to video encod ing or …

Examples described herein utilize multi-layer neural networks to decode encoded data (eg,
data encoded using one or more encoding techniques). The neural networks have nonlinear …

An artificial intelligence (AI) decoding apparatus includes a memory storing one or more
instructions, and a processor configured to execute the stored one or more instructions, to …

Provided is an artificial intelligence (AI) decoding apparatus includes: a memory storing one
or more instructions, and a processor configured to execute the one or more instructions …

Methods, systems, and apparatus, including computer programs encoded on computer
storage media, for generating discrete latent representations of input data items. One of the …

US11601644B2 - Image and video coding using machine learning prediction coding models -
Google Patents US11601644B2 - Image and video coding using machine learning prediction …

Provided is a computer-recordable recording medium hav ing stored thereon a video file
including artificial intelli gence (AI) encoding data, wherein the AI encoding data includes …

To apply a filter to input image data in accordance with an image characteristic. A CNN filter
includes a neural network configured to receive an input of one or multiple first type input …

Examples described herein utilize multi-layer neural net works, such as multi-layer recurrent
neural networks to decode encoded data (eg, data encoded using one or more encoding …