Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Heiner Kirchhoffer"'
Autor:
Hamed Rezazadegan-Tavakoli, Wojciech Samek, Werner Bailer, Paul Haase, Karsten Muller, Swayambhoo Jain, Francesco Cricri, Miska Hannuksela, Shan Liu, Emre Aksu, Wei Jiang, Shahab Hamidi-Rad, Fabien Racape, Heiner Kirchhoffer, Wei Wang
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:3203-3216
Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks (NNs). The standard is designed as a toolbox of compression methods, which can be used to create coding pipelines. It can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea3cf414ea189bf657a4b5643281d50c
https://doi.org/10.1109/tcsvt.2021.3095970
https://doi.org/10.1109/tcsvt.2021.3095970
Autor:
Heiner Kirchhoffer, Christian Rudat, Michael Schäfer, Jonathan Pfaff, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
Publikováno v:
2023 Data Compression Conference (DCC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be1c96ba200530a68d6674d80193e292
https://doi.org/10.1109/dcc55655.2023.00081
https://doi.org/10.1109/dcc55655.2023.00081
Autor:
Gerhard Tech, Paul Haase, Daniel Becking, Heiner Kirchhoffer, Karsten Muller, Jonathan Pfaff, Heiko Schwarz, Wojciech Samek, Detlev Marpe, Thomas Wiegand
Publikováno v:
2022 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e1288efe4a1c1d6f261b017eedba2da
https://doi.org/10.1109/icip46576.2022.9897825
https://doi.org/10.1109/icip46576.2022.9897825
Autor:
Daniel Becking, Heiner Kirchhoffer, Gerhard Tech, Paul Haase, Karsten Muller, Heiko Schwarz, Wojciech Samek
Federated learning (FL) scenarios inherently generate a large communication overhead by frequently transmitting neural network updates between clients and server. To minimize the communication cost, introducing sparsity in conjunction with differenti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65fb9e31278617e33bfe11eaab376150
http://arxiv.org/abs/2204.04424
http://arxiv.org/abs/2204.04424
Autor:
Thomas Wiegand, Heiner Kirchhoffer, Paul Haase, Simon Wiedemann, Wojciech Samek, Heiko Schwarz, Arturo Marban, Talmaj Marinc, Detlev Marpe, Karsten Muller
Publikováno v:
ICIP
Recent approaches to compression of deep neural networks, like the emerging standard on compression of neural networks for multimedia content description and analysis (MPEG-7 part 17), apply scalar quantization and entropy coding of the quantization
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::15109ab698cf716241e970b46e2056f8
https://doi.org/10.1109/icip40778.2020.9190955
https://doi.org/10.1109/icip40778.2020.9190955
Autor:
Detlev Marpe, David Neumann, Heiner Kirchhoffer, Wojciech Samek, Heiko Schwarz, Simon Wiedemann, Felix Sattler, Karsten Muller, Thomas Wiegand
Publikováno v:
ICIP
An increasing number of distributed machine learning applications require efficient communication of neural network parameterizations. DeepCABAC, an algorithm in the current working draft of the emerging MPEG-7 part 17 standard for compression of neu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5368dff55d627c66ef68dd640b467393
https://doi.org/10.1109/icip40778.2020.9190821
https://doi.org/10.1109/icip40778.2020.9190821
For the entropy coding of independent and identically distributed (i.i.d.) binary sources, variable-to-variable length (V2V) codes are an interesting alternative to arithmetic coding. Such a V2V code translates variable length words of the source int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8eade74617ab452319d59008263cfbcc
https://publica.fraunhofer.de/handle/publica/256984
https://publica.fraunhofer.de/handle/publica/256984
Autor:
Heiner Kirchhoffer, Heiko Schwarz, Mischa Siekmann, Karsten Suhring, Philipp Helle, Tung Nguyen, Martin Winken, Detlev Marpe, Benjamin Bross, Sebastian Bosse, Oudin Simon, Tobias Hinz, Haricharan Lakshman, Thomas Wiegand
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 20:1676-1687
A video coding architecture is described that is based on nested and pre-configurable quadtree structures for flexible and signal-adaptive picture partitioning. The primary goal of this partitioning concept is to provide a high degree of adaptability
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5031f3ddf653ff5b8f8255d1a9b29723
https://doi.org/10.1109/tcsvt.2010.2092615
https://doi.org/10.1109/tcsvt.2010.2092615
Publikováno v:
ICCE-Berlin
Entropy coding schemes like context-based adaptive binary arithmetic coding (CABAC) as used in the H.264/AVC video coding standard are established in the market. To increase throughput and possibilities for parallelization, probability interval parti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::818c315d191f8ae1d9417a3d1a81612e
https://doi.org/10.1109/icce-berlin.2012.6336524
https://doi.org/10.1109/icce-berlin.2012.6336524
Autor:
Tung Nguyen, Preiss Matthias, Heiner Kirchhoffer, Mischa Siekmann, Benjamin Bross, Thomas Wiegand, Jan Stegemann, Valeri George, Detlev Marpe
Publikováno v:
ICIP
The state-of-the-art hybrid video coding standard H.264/AVC defines two entropy-coding schemes with different complexity-performance trade-offs. Supporting these two schemes within a single standard raises several problems ranging from higher efforts
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2c1d2dd9706f7ce400cead856adf02fc
https://doi.org/10.1109/icip.2012.6466963
https://doi.org/10.1109/icip.2012.6466963