Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307980367> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4307980367 endingPage "1261" @default.
- W4307980367 startingPage "1261" @default.
- W4307980367 abstract "The demand for nudity and pornographic content detection is increasing due to the prevalence of media products containing sexually explicit content with Internet being the main source. Recent literature has proved the effectiveness of deep learning techniques for adult image and video detection. However, the requirement for a huge dataset with labeled examples poses a restriction in practical use. Several research has shown that training deep models using an active learning framework could reduce the annotation effort, but this approach has yet to be applied for pornography detection. In this paper, the classification efficiency and annotation requirement of fine-tuned ResNet50V2 model trained using an active learning framework in pornographic image recognition was explored by comparing the method’s performance using three sampling strategies (random sampling, least confidence sampling, and entropy sampling). The baseline for comparison was a fully supervised learning method. The video frames of the public NPDI dataset were utilized to run a 5-fold cross-validation. The results of the experiments demonstrated that similar average test accuracy of five folds could be obtained using the deep active learning method, with only 60% of labeled samples in the training dataset compared to 100% annotated samples in fully supervised learning." @default.
- W4307980367 created "2022-11-07" @default.
- W4307980367 creator A5004443507 @default.
- W4307980367 creator A5019400360 @default.
- W4307980367 creator A5027445807 @default.
- W4307980367 creator A5037300629 @default.
- W4307980367 creator A5052548650 @default.
- W4307980367 creator A5066663861 @default.
- W4307980367 creator A5078810413 @default.
- W4307980367 date "2022-11-03" @default.
- W4307980367 modified "2023-09-26" @default.
- W4307980367 title "Deep Active Learning for Pornography Recognition Using ResNet" @default.
- W4307980367 doi "https://doi.org/10.14716/ijtech.v13i6.5842" @default.
- W4307980367 hasPublicationYear "2022" @default.
- W4307980367 type Work @default.
- W4307980367 citedByCount "0" @default.
- W4307980367 crossrefType "journal-article" @default.
- W4307980367 hasAuthorship W4307980367A5004443507 @default.
- W4307980367 hasAuthorship W4307980367A5019400360 @default.
- W4307980367 hasAuthorship W4307980367A5027445807 @default.
- W4307980367 hasAuthorship W4307980367A5037300629 @default.
- W4307980367 hasAuthorship W4307980367A5052548650 @default.
- W4307980367 hasAuthorship W4307980367A5066663861 @default.
- W4307980367 hasAuthorship W4307980367A5078810413 @default.
- W4307980367 hasBestOaLocation W43079803671 @default.
- W4307980367 hasConcept C106131492 @default.
- W4307980367 hasConcept C108583219 @default.
- W4307980367 hasConcept C110875604 @default.
- W4307980367 hasConcept C119857082 @default.
- W4307980367 hasConcept C136389625 @default.
- W4307980367 hasConcept C136764020 @default.
- W4307980367 hasConcept C140779682 @default.
- W4307980367 hasConcept C153180895 @default.
- W4307980367 hasConcept C154945302 @default.
- W4307980367 hasConcept C167981619 @default.
- W4307980367 hasConcept C17744445 @default.
- W4307980367 hasConcept C199539241 @default.
- W4307980367 hasConcept C2776321320 @default.
- W4307980367 hasConcept C2781301322 @default.
- W4307980367 hasConcept C31972630 @default.
- W4307980367 hasConcept C41008148 @default.
- W4307980367 hasConcept C50644808 @default.
- W4307980367 hasConceptScore W4307980367C106131492 @default.
- W4307980367 hasConceptScore W4307980367C108583219 @default.
- W4307980367 hasConceptScore W4307980367C110875604 @default.
- W4307980367 hasConceptScore W4307980367C119857082 @default.
- W4307980367 hasConceptScore W4307980367C136389625 @default.
- W4307980367 hasConceptScore W4307980367C136764020 @default.
- W4307980367 hasConceptScore W4307980367C140779682 @default.
- W4307980367 hasConceptScore W4307980367C153180895 @default.
- W4307980367 hasConceptScore W4307980367C154945302 @default.
- W4307980367 hasConceptScore W4307980367C167981619 @default.
- W4307980367 hasConceptScore W4307980367C17744445 @default.
- W4307980367 hasConceptScore W4307980367C199539241 @default.
- W4307980367 hasConceptScore W4307980367C2776321320 @default.
- W4307980367 hasConceptScore W4307980367C2781301322 @default.
- W4307980367 hasConceptScore W4307980367C31972630 @default.
- W4307980367 hasConceptScore W4307980367C41008148 @default.
- W4307980367 hasConceptScore W4307980367C50644808 @default.
- W4307980367 hasIssue "6" @default.
- W4307980367 hasLocation W43079803671 @default.
- W4307980367 hasOpenAccess W4307980367 @default.
- W4307980367 hasPrimaryLocation W43079803671 @default.
- W4307980367 hasRelatedWork W3192794374 @default.
- W4307980367 hasRelatedWork W4220686584 @default.
- W4307980367 hasRelatedWork W4223943233 @default.
- W4307980367 hasRelatedWork W4225161397 @default.
- W4307980367 hasRelatedWork W4246751904 @default.
- W4307980367 hasRelatedWork W4312200629 @default.
- W4307980367 hasRelatedWork W4360585206 @default.
- W4307980367 hasRelatedWork W4364306694 @default.
- W4307980367 hasRelatedWork W4380075502 @default.
- W4307980367 hasRelatedWork W4380086463 @default.
- W4307980367 hasVolume "13" @default.
- W4307980367 isParatext "false" @default.
- W4307980367 isRetracted "false" @default.
- W4307980367 workType "article" @default.