Výsledky vyhledávání - "Sparenberg, Heiko"

Report

A Study on the Effect of Color Spaces in Learned Image Compression

Autor: Prativadibhayankaram, Srivatsa, Panda, Mahadev Prasad, Seiler, Jürgen, Richter, Thomas, Sparenberg, Heiko, Fößel, Siegfried, Kaup, André

In this work, we present a comparison between color spaces namely YUV, LAB, RGB and their effect on learned image compression. For this we use the structure and color based learned image codec (SLIC) from our prior work, which consists of two branche

Externí odkaz: http://arxiv.org/abs/2406.13709

Zobrazit plný text záznamu

Report

SLIC: A Learned Image Codec Using Structure and Color

Autor: Prativadibhayankaram, Srivatsa, Panda, Mahadev Prasad, Richter, Thomas, Sparenberg, Heiko, Fößel, Siegfried, Kaup, André

We propose the structure and color based learned image codec (SLIC) in which the task of compression is split into that of luminance and chrominance. The deep learning model is built with a novel multi-scale architecture for Y and UV channels in the

Externí odkaz: http://arxiv.org/abs/2401.17246

Zobrazit plný text záznamu

Report

Color Learning for Image Compression

Autor: Prativadibhayankaram, Srivatsa, Richter, Thomas, Sparenberg, Heiko, Fößel, Siegfried

Deep learning based image compression has gained a lot of momentum in recent times. To enable a method that is suitable for image compression and subsequently extended to video compression, we propose a novel deep learning model architecture, where t

Externí odkaz: http://arxiv.org/abs/2306.17460

Zobrazit plný text záznamu

Deep Learning based Beat Event Detection in Action Movie Franchises

Autor: Ejaz, N., Khan, U. A., Martínez del Amor, Miguel Ángel, Sparenberg, Heiko

Publikováno v: idUS: Depósito de Investigación de la Universidad de Sevilla
Universidad de Sevilla (US)
idUS. Depósito de Investigación de la Universidad de Sevilla
instname

Automatic understanding and interpretation of movies can be used in a variety of ways to semantically manage the massive volumes of movies data. “Action Movie Franchises” dataset is a collection of twenty Hollywood action movies from five famous

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0e84e17fe8361f50f91a14ca4acd764b

Zobrazit plný text záznamu

Movies Tags Extraction Using Deep Learning

Autor: Khan, U. A., Ejaz, N., Martínez del Amor, Miguel Ángel, Sparenberg, Heiko

Publikováno v: idUS. Depósito de Investigación de la Universidad de Sevilla
instname

Retrieving information from movies is becoming increasingly demanding due to the enormous amount of multimedia data generated each day. Not only it helps in efficient search, archiving and classification of movies, but is also instrumental in content

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=RECOLECTA___::d35e308db4ac9535022e45192f419684

Zobrazit plný text záznamu

Conference

Parallel Efficient Rate Control Methods for JPEG 2000.

Autor: Martínez-del-Amor, Miguel Á., Bruns, Volker, Sparenberg, Heiko

Publikováno v: Proceedings of SPIE; 6/21/2017, Vol. 10396, p1-16, 16p

Zobrazit plný text záznamu

Comparison of Code-Pass-Skipping Strategies for Accelerating a JPEG 2000 Decoder

Autor: Bruns, Volker, Sparenberg, Heiko

Code-Pass-Skipping allows a JPEG 2000 decoder to be accelerated by sacrificing the output precision. This paper presents an evaluation on how the speed gain can be maximized and the quality loss minimized. In particular, the scenario of rendering a 2

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::813b78df1b2cd1302d5df744b2931447
http://hdl.handle.net/2003/30056

Zobrazit plný text záznamu