FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891639616> ?p ?o ?g. }

• W2891639616 endingPage "5770" @default.
• W2891639616 startingPage "5757" @default.
• W2891639616 abstract "In a typical communication pipeline, images undergo a series of processing steps that can cause visual distortions before being viewed. Given a high quality reference image, a reference (R) image quality assessment (IQA) algorithm can be applied after compression or transmission. However, the assumption of a high quality reference image is often not fulfilled in practice, thus contributing to less accurate quality predictions when using stand-alone R IQA models. This is particularly common on social media, where hundreds of billions of usergenerated photos and videos containing diverse, mixed distortions are uploaded, compressed, and shared annually on sites like Facebook, YouTube, and Snapchat. The qualities of the pictures that are uploaded to these sites vary over a very wide range. While this is an extremely common situation, the problem of assessing the qualities of compressed images against their precompressed, but often severely distorted (reference) pictures has been little studied. Towards ameliorating this problem, we propose a novel two-step image quality prediction concept that combines NR with R quality measurements. Applying a first stage of NR IQA to determine the possibly degraded quality of the source image yields information that can be used to quality-modulate the R prediction to improve its accuracy. We devise a simple and efficient weighted product model of R and NR stages, which combines a pre-compression NR measurement with a post-compression R measurement. This first-of-a-kind two-step approach produces more reliable objective prediction scores. We also constructed a new, first-of-a-kind dedicated database specialized for the design and testing of two-step IQA models. Using this new resource, we show that twostep approaches yield outstanding performance when applied to compressed images whose original, pre-compression quality covers a wide range of realistic distortion types and severities. The two-step concept is versatile as it can use any desired R and NR components. We are making the source code of a particularly efficient model that we call 2stepQA publicly available at https://github.com/xiangxuyu/2stepQA. We are also providing the dedicated new two-step database free of charge at http://live.ece.utexas.edu/research/twostep/index.html." @default.
• W2891639616 created "2018-09-27" @default.
• W2891639616 creator A5030467944 @default.
• W2891639616 creator A5036706118 @default.
• W2891639616 creator A5039848917 @default.
• W2891639616 creator A5075463806 @default.
• W2891639616 date "2019-12-01" @default.
• W2891639616 modified "2023-09-25" @default.
• W2891639616 title "Predicting the Quality of Images Compressed After Distortion in Two Steps" @default.
• W2891639616 cites W1580389772 @default.
• W2891639616 cites W1964859077 @default.
• W2891639616 cites W1974013408 @default.
• W2891639616 cites W1977725648 @default.
• W2891639616 cites W1982471090 @default.
• W2891639616 cites W2015196405 @default.
• W2891639616 cites W2037243393 @default.
• W2891639616 cites W2046119925 @default.
• W2891639616 cites W2102166818 @default.
• W2891639616 cites W2114582993 @default.
• W2891639616 cites W2117535912 @default.
• W2891639616 cites W2129644086 @default.
• W2891639616 cites W2133665775 @default.
• W2891639616 cites W2141983208 @default.
• W2891639616 cites W2143854715 @default.
• W2891639616 cites W2152059677 @default.
• W2891639616 cites W2161907179 @default.
• W2891639616 cites W2162692770 @default.
• W2891639616 cites W2163370434 @default.
• W2891639616 cites W2170947705 @default.
• W2891639616 cites W2303076655 @default.
• W2891639616 cites W2472152852 @default.
• W2891639616 cites W2481798478 @default.
• W2891639616 cites W2511866412 @default.
• W2891639616 cites W2546481984 @default.
• W2891639616 cites W2546855109 @default.
• W2891639616 cites W2549096365 @default.
• W2891639616 cites W2566536172 @default.
• W2891639616 cites W2574780780 @default.
• W2891639616 cites W2766641329 @default.
• W2891639616 cites W2767836774 @default.
• W2891639616 cites W2777280533 @default.
• W2891639616 cites W2790816803 @default.
• W2891639616 cites W2794680924 @default.
• W2891639616 cites W2891645170 @default.
• W2891639616 cites W2963975576 @default.
• W2891639616 cites W3100404621 @default.
• W2891639616 cites W3100498948 @default.
• W2891639616 cites W4252684946 @default.
• W2891639616 doi "https://doi.org/10.1109/tip.2019.2922850" @default.
• W2891639616 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31226076" @default.
• W2891639616 hasPublicationYear "2019" @default.
• W2891639616 type Work @default.
• W2891639616 sameAs 2891639616 @default.
• W2891639616 citedByCount "36" @default.
• W2891639616 countsByYear W28916396162019 @default.
• W2891639616 countsByYear W28916396162020 @default.
• W2891639616 countsByYear W28916396162021 @default.
• W2891639616 countsByYear W28916396162022 @default.
• W2891639616 countsByYear W28916396162023 @default.
• W2891639616 crossrefType "journal-article" @default.
• W2891639616 hasAuthorship W2891639616A5030467944 @default.
• W2891639616 hasAuthorship W2891639616A5036706118 @default.
• W2891639616 hasAuthorship W2891639616A5039848917 @default.
• W2891639616 hasAuthorship W2891639616A5075463806 @default.
• W2891639616 hasConcept C103910844 @default.
• W2891639616 hasConcept C111472728 @default.
• W2891639616 hasConcept C111919701 @default.
• W2891639616 hasConcept C115961682 @default.
• W2891639616 hasConcept C124101348 @default.
• W2891639616 hasConcept C126780896 @default.
• W2891639616 hasConcept C13481523 @default.
• W2891639616 hasConcept C138885662 @default.
• W2891639616 hasConcept C154945302 @default.
• W2891639616 hasConcept C162324750 @default.
• W2891639616 hasConcept C176217482 @default.
• W2891639616 hasConcept C194257627 @default.
• W2891639616 hasConcept C199360897 @default.
• W2891639616 hasConcept C21547014 @default.
• W2891639616 hasConcept C2776257435 @default.
• W2891639616 hasConcept C2779346075 @default.
• W2891639616 hasConcept C2779530757 @default.
• W2891639616 hasConcept C31258907 @default.
• W2891639616 hasConcept C31972630 @default.
• W2891639616 hasConcept C41008148 @default.
• W2891639616 hasConcept C43521106 @default.
• W2891639616 hasConcept C55020928 @default.
• W2891639616 hasConcept C71901391 @default.
• W2891639616 hasConcept C78548338 @default.
• W2891639616 hasConcept C9417928 @default.
• W2891639616 hasConceptScore W2891639616C103910844 @default.
• W2891639616 hasConceptScore W2891639616C111472728 @default.
• W2891639616 hasConceptScore W2891639616C111919701 @default.
• W2891639616 hasConceptScore W2891639616C115961682 @default.
• W2891639616 hasConceptScore W2891639616C124101348 @default.
• W2891639616 hasConceptScore W2891639616C126780896 @default.
• W2891639616 hasConceptScore W2891639616C13481523 @default.
• W2891639616 hasConceptScore W2891639616C138885662 @default.
• W2891639616 hasConceptScore W2891639616C154945302 @default.

• next