PARALLELIZED CONTEXT MODELLING USING INFORMATION SHARED BETWEEN PATCHES

PARALLELIZED CONTEXT MODELLING USING INFORMATION SHARED BETWEEN PATCHES

Methods and apparatuses are provided for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into patches and obtaining a probability model for the entropy encoding of a current element of the latent tensor by processing a set of elements from different patc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Boev, Atanas, Koyuncu, Ahmet Burakhan, Alshina, Elena Alexandrovna
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Methods and apparatuses are provided for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into patches and obtaining a probability model for the entropy encoding of a current element of the latent tensor by processing a set of elements from different patches by one or more layers of a neural network. The processing of the set of elements by applying a convolution kernel enables sharing of information between the separated patches.