Matches in SemOpenAlex for { <https://semopenalex.org/work/W2812636377> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2812636377 endingPage "5" @default.
- W2812636377 startingPage "154" @default.
- W2812636377 abstract "In VP9 , a 64×64 superblock can be recursively decomposed all the way to blocks of size 4×4 . The encoder performs the encoding process for each possible partitioning and the optimal one is selected by minimizing the rate and distortion cost. This scheme ensures the encoding quality, but also brings in large computational complexity and substantial CPU resources. In this paper, to speed up the partition search without sacrificing the quality, we propose a multi-level machine learning-based early termination scheme. One weighted Support Vector Machine classifier is trained for each block size. The binary classifiers are used to determine that provided a block, whether it is necessary to continue the search down to smaller blocks, or to perform the early termination and take the current block size as the final one. Moreover, the classifiers are trained with varying error-tolerance for different block sizes, i.e., a stricter error-tolerance is adopted for larger block size compared with the smaller ones to control the encoder performance drop. Extensive experimental results demonstrate that for HD and 4K videos, the proposed framework accomplishes remarkable speed-up (20-25%) with less than 0.03% performance drop measured in the Bjøntegaard delta bit rate (BDBR) compared with current VP9 codebase." @default.
- W2812636377 created "2018-07-19" @default.
- W2812636377 creator A5031139212 @default.
- W2812636377 creator A5032320528 @default.
- W2812636377 creator A5045189891 @default.
- W2812636377 creator A5059093719 @default.
- W2812636377 creator A5074244244 @default.
- W2812636377 date "2018-01-28" @default.
- W2812636377 modified "2023-09-27" @default.
- W2812636377 title "Multi-Level Machine Learning-based Early Termination in VP9 Partition Search" @default.
- W2812636377 doi "https://doi.org/10.2352/issn.2470-1173.2018.2.vipc-154" @default.
- W2812636377 hasPublicationYear "2018" @default.
- W2812636377 type Work @default.
- W2812636377 sameAs 2812636377 @default.
- W2812636377 citedByCount "3" @default.
- W2812636377 countsByYear W28126363772019 @default.
- W2812636377 countsByYear W28126363772020 @default.
- W2812636377 crossrefType "journal-article" @default.
- W2812636377 hasAuthorship W2812636377A5031139212 @default.
- W2812636377 hasAuthorship W2812636377A5032320528 @default.
- W2812636377 hasAuthorship W2812636377A5045189891 @default.
- W2812636377 hasAuthorship W2812636377A5059093719 @default.
- W2812636377 hasAuthorship W2812636377A5074244244 @default.
- W2812636377 hasConcept C111919701 @default.
- W2812636377 hasConcept C11413529 @default.
- W2812636377 hasConcept C114614502 @default.
- W2812636377 hasConcept C118505674 @default.
- W2812636377 hasConcept C12267149 @default.
- W2812636377 hasConcept C125411270 @default.
- W2812636377 hasConcept C154945302 @default.
- W2812636377 hasConcept C2524010 @default.
- W2812636377 hasConcept C26517878 @default.
- W2812636377 hasConcept C2777210771 @default.
- W2812636377 hasConcept C33923547 @default.
- W2812636377 hasConcept C38652104 @default.
- W2812636377 hasConcept C41008148 @default.
- W2812636377 hasConcept C41431624 @default.
- W2812636377 hasConcept C42812 @default.
- W2812636377 hasConceptScore W2812636377C111919701 @default.
- W2812636377 hasConceptScore W2812636377C11413529 @default.
- W2812636377 hasConceptScore W2812636377C114614502 @default.
- W2812636377 hasConceptScore W2812636377C118505674 @default.
- W2812636377 hasConceptScore W2812636377C12267149 @default.
- W2812636377 hasConceptScore W2812636377C125411270 @default.
- W2812636377 hasConceptScore W2812636377C154945302 @default.
- W2812636377 hasConceptScore W2812636377C2524010 @default.
- W2812636377 hasConceptScore W2812636377C26517878 @default.
- W2812636377 hasConceptScore W2812636377C2777210771 @default.
- W2812636377 hasConceptScore W2812636377C33923547 @default.
- W2812636377 hasConceptScore W2812636377C38652104 @default.
- W2812636377 hasConceptScore W2812636377C41008148 @default.
- W2812636377 hasConceptScore W2812636377C41431624 @default.
- W2812636377 hasConceptScore W2812636377C42812 @default.
- W2812636377 hasIssue "2" @default.
- W2812636377 hasLocation W28126363771 @default.
- W2812636377 hasOpenAccess W2812636377 @default.
- W2812636377 hasPrimaryLocation W28126363771 @default.
- W2812636377 hasRelatedWork W1868555129 @default.
- W2812636377 hasRelatedWork W2013327104 @default.
- W2812636377 hasRelatedWork W2024652310 @default.
- W2812636377 hasRelatedWork W2166756812 @default.
- W2812636377 hasRelatedWork W2358489738 @default.
- W2812636377 hasRelatedWork W2364375978 @default.
- W2812636377 hasRelatedWork W2376346720 @default.
- W2812636377 hasRelatedWork W2387787602 @default.
- W2812636377 hasRelatedWork W2394200797 @default.
- W2812636377 hasRelatedWork W2547835662 @default.
- W2812636377 hasVolume "2018" @default.
- W2812636377 isParatext "false" @default.
- W2812636377 isRetracted "false" @default.
- W2812636377 magId "2812636377" @default.
- W2812636377 workType "article" @default.