FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2560838595> ?p ?o ?g. }

• W2560838595 endingPage "293" @default.
• W2560838595 startingPage "279" @default.
• W2560838595 abstract "Recent literature has explored automated pornographic detection - a bold move to replace humans in the tedious task of moderating online content. Unfortunately, on scenes with high skin exposure, such as people sunbathing and wrestling, the state of the art can have many false alarms. This paper is based on the premise that incorporating motion information in the models can alleviate the problem of mapping skin exposure to pornographic content, and advances the bar on automated pornography detection with the use of motion information and deep learning architectures. Deep Learning, especially in the form of Convolutional Neural Networks, have striking results on computer vision, but their potential for pornography detection is yet to be fully explored through the use of motion information. We propose novel ways for combining static (picture) and dynamic (motion) information using optical flow and MPEG motion vectors. We show that both methods provide equivalent accuracies, but that MPEG motion vectors allow a more efficient implementation. The best proposed method yields a classification accuracy of 97.9% - an error reduction of 64.4% when compared to the state of the art - on a dataset of 800 challenging test cases. Finally, we present and discuss results on a larger, and more challenging, dataset." @default.
• W2560838595 created "2016-12-16" @default.
• W2560838595 creator A5006749804 @default.
• W2560838595 creator A5043147904 @default.
• W2560838595 creator A5048972305 @default.
• W2560838595 creator A5051880838 @default.
• W2560838595 creator A5052913710 @default.
• W2560838595 creator A5054749111 @default.
• W2560838595 creator A5057680257 @default.
• W2560838595 creator A5087463290 @default.
• W2560838595 date "2017-03-01" @default.
• W2560838595 modified "2023-10-14" @default.
• W2560838595 title "Video pornography detection through deep learning techniques and motion information" @default.
• W2560838595 cites W1000180593 @default.
• W2560838595 cites W1480498941 @default.
• W2560838595 cites W1587328194 @default.
• W2560838595 cites W1606858007 @default.
• W2560838595 cites W1867429401 @default.
• W2560838595 cites W1966385142 @default.
• W2560838595 cites W1967098370 @default.
• W2560838595 cites W1970974937 @default.
• W2560838595 cites W1976921161 @default.
• W2560838595 cites W1983364832 @default.
• W2560838595 cites W1992150801 @default.
• W2560838595 cites W1999192586 @default.
• W2560838595 cites W2016053056 @default.
• W2560838595 cites W2017028970 @default.
• W2560838595 cites W2020163092 @default.
• W2560838595 cites W2022588182 @default.
• W2560838595 cites W2065636378 @default.
• W2560838595 cites W2065867336 @default.
• W2560838595 cites W2069796578 @default.
• W2560838595 cites W2082627290 @default.
• W2560838595 cites W2097117768 @default.
• W2560838595 cites W2105101328 @default.
• W2560838595 cites W2111220184 @default.
• W2560838595 cites W2111308925 @default.
• W2560838595 cites W2112397370 @default.
• W2560838595 cites W2117539524 @default.
• W2560838595 cites W2119605622 @default.
• W2560838595 cites W2126579184 @default.
• W2560838595 cites W2127241327 @default.
• W2560838595 cites W2130372280 @default.
• W2560838595 cites W2135176316 @default.
• W2560838595 cites W2141423371 @default.
• W2560838595 cites W2142194269 @default.
• W2560838595 cites W2153635508 @default.
• W2560838595 cites W2153746365 @default.
• W2560838595 cites W2155893237 @default.
• W2560838595 cites W2167277498 @default.
• W2560838595 cites W2167912153 @default.
• W2560838595 cites W2364255476 @default.
• W2560838595 cites W2409697880 @default.
• W2560838595 cites W2521373549 @default.
• W2560838595 cites W4252684946 @default.
• W2560838595 doi "https://doi.org/10.1016/j.neucom.2016.12.017" @default.
• W2560838595 hasPublicationYear "2017" @default.
• W2560838595 type Work @default.
• W2560838595 sameAs 2560838595 @default.
• W2560838595 citedByCount "93" @default.
• W2560838595 countsByYear W25608385952017 @default.
• W2560838595 countsByYear W25608385952018 @default.
• W2560838595 countsByYear W25608385952019 @default.
• W2560838595 countsByYear W25608385952020 @default.
• W2560838595 countsByYear W25608385952021 @default.
• W2560838595 countsByYear W25608385952022 @default.
• W2560838595 countsByYear W25608385952023 @default.
• W2560838595 crossrefType "journal-article" @default.
• W2560838595 hasAuthorship W2560838595A5006749804 @default.
• W2560838595 hasAuthorship W2560838595A5043147904 @default.
• W2560838595 hasAuthorship W2560838595A5048972305 @default.
• W2560838595 hasAuthorship W2560838595A5051880838 @default.
• W2560838595 hasAuthorship W2560838595A5052913710 @default.
• W2560838595 hasAuthorship W2560838595A5054749111 @default.
• W2560838595 hasAuthorship W2560838595A5057680257 @default.
• W2560838595 hasAuthorship W2560838595A5087463290 @default.
• W2560838595 hasConcept C104114177 @default.
• W2560838595 hasConcept C108583219 @default.
• W2560838595 hasConcept C11171543 @default.
• W2560838595 hasConcept C119857082 @default.
• W2560838595 hasConcept C154945302 @default.
• W2560838595 hasConcept C15744967 @default.
• W2560838595 hasConcept C2781301322 @default.
• W2560838595 hasConcept C31972630 @default.
• W2560838595 hasConcept C41008148 @default.
• W2560838595 hasConceptScore W2560838595C104114177 @default.
• W2560838595 hasConceptScore W2560838595C108583219 @default.
• W2560838595 hasConceptScore W2560838595C11171543 @default.
• W2560838595 hasConceptScore W2560838595C119857082 @default.
• W2560838595 hasConceptScore W2560838595C154945302 @default.
• W2560838595 hasConceptScore W2560838595C15744967 @default.
• W2560838595 hasConceptScore W2560838595C2781301322 @default.
• W2560838595 hasConceptScore W2560838595C31972630 @default.
• W2560838595 hasConceptScore W2560838595C41008148 @default.
• W2560838595 hasFunder F4320320997 @default.
• W2560838595 hasFunder F4320321091 @default.
• W2560838595 hasFunder F4320322025 @default.
• W2560838595 hasLocation W25608385951 @default.

• next