About: A Deep CNN-LSTM Framework for Fast Video Coding

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: A Deep CNN-LSTM Framework for Fast Video Coding Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	A Deep CNN-LSTM Framework for Fast Video Coding
Creator	Sayadi, Fatma Atri, Mohamed Bouaafia, Soulef Khemiri, Randa Liouane, Noureddine
topic	covid:c9bfbd62086f9369f9e95b77fd9bd8b89b8849fb#this
Source	PMC
abstract	High Efficiency Video Coding (HEVC) doubles the compression rates over the previous H.264 standard for the same video quality. To improve the coding efficiency, HEVC adopts the hierarchical quadtree structured Coding Unit (CU). However, the computational complexity significantly increases due to the full search for Rate-Distortion Optimization (RDO) to find the optimal Coding Tree Unit (CTU) partition. Here, this paper proposes a deep learning model to predict the HEVC CU partition at inter-mode, instead of brute-force RDO search. To learn the learning model, a large-scale database for HEVC inter-mode is first built. Second, to predict the CU partition of HEVC, we propose as a model a combination of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network. The simulation results prove that the proposed scheme can achieve a best compromise between complexity reduction and RD performance, compared to existing approaches.
has issue date	2020-06-05(xsd:dateTime)
bibo:doi	10.1007/978-3-030-51935-3_22
has license	no-cc
sha1sum (hex)	c9bfbd62086f9369f9e95b77fd9bd8b89b8849fb
schema:url	https://doi.org/10.1007/978-3-030-51935-3_22
resource representing a document's title	A Deep CNN-LSTM Framework for Fast Video Coding
has PubMed Central identifier	PMC7340939
schema:publication	Image and Signal Processing
resource representing a document's body	covid:c9bfbd62086f9369f9e95b77fd9bd8b89b8849fb#body_text
is http://vocab.deri.ie/void#inDataset of	proxy:http/ns.inria.fr/covid19/c9bfbd62086f9369f9e95b77fd9bd8b89b8849fb
is schema:about of	named entity 'partition' named entity 'Coding' named entity 'CNN' named entity 'Tree' named entity 'doubles' named entity 'Framework' named entity 'QUALITY' named entity 'RESULTS' named entity 'COMBINATION' named entity 'LONG' named entity 'REDUCTION' named entity 'COMPRESSION' named entity 'HIGH EFFICIENCY' named entity 'LEARNING' named entity 'PREDICT' named entity 'UNIT' named entity 'model' named entity 'standard' named entity 'adopts' named entity 'quadtree' named entity 'H.264' named entity 'coding efficiency' named entity 'Coding Tree Unit' named entity 'Convolutional Neural Network' named entity 'compression rates' named entity 'brute-force' named entity 'Long Short-Term Memory' named entity 'Rate-Distortion Optimization' named entity 'HEVC' named entity 'CNN' named entity 'network' named entity 'LSTM' named entity 'Rate-Distortion Optimization' named entity 'level 2' named entity 'database' named entity 'algorithm' named entity 'correlation' named entity 'Tensorflow' named entity 'video coding' named entity 'probability' named entity 'LSTM' named entity 'GHz' named entity 'HEVC' named entity 'HEVC' named entity 'look-ahead' named entity 'stochastic gradient descent' named entity 'video content' named entity 'loss function' named entity 'average BitRate' named entity 'loss function' named entity 'sigmoid function' named entity 'LSTM' named entity 'CNN' named entity 'BitRate' named entity 'LSTM' named entity 'quadtree' named entity 'GPU' named entity 'LSTM' named entity 'algorithm' named entity 'deep learning' named entity 'cross entropy' named entity 'Coding Tree Unit' named entity 'HEVC' named entity 'quadtree' named entity 'HEVC' named entity 'LSTM' named entity 'JCT-VC' named entity 'coding efficiency' named entity 'HEVC' named entity 'LSTM' named entity 'Class A' named entity 'make decisions' named entity 'HEVC' named entity 'windows 10' named entity 'HEVC' named entity 'CTU' named entity 'inter prediction'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software