Matches in SemOpenAlex for { <https://semopenalex.org/work/W2566291355> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2566291355 abstract "In this paper, we propose a principled framework for pornographic image recognition. Specifically, we present our definition of pornographic images, which characterizes the pornographic contents in images as the exposure of private body parts. As the private body parts often lie in local image regions, we model each image as a bag of local image patches (instances), and assume that for each pornographic image at least one instance accounts for the pornographic content within it. This treatment allows us to cast the model training as a Multiple Instance Learning (MIL) problem. Furthermore, we propose a strongly-supervised setting for MIL by identifying the most likely pornographic instances in positive bags, which effectively prevents the algorithm from getting trapped in a bad local optima. Last but not least, we formulate our strongly-supervised MIL under the deep CNN framework to learn deep representations; hence we call it Strongly-supervised Deep MIL (SD-MIL). We demonstrate that our SD-MIL based system produces remarkable accuracy with 97.01% TPR at 1% FPR, testing on 117K pornographic images and 117K normal images from our newly-collected large scale dataset." @default.
- W2566291355 created "2017-01-06" @default.
- W2566291355 creator A5004478562 @default.
- W2566291355 creator A5008491549 @default.
- W2566291355 creator A5023967844 @default.
- W2566291355 date "2016-09-01" @default.
- W2566291355 modified "2023-09-26" @default.
- W2566291355 title "Pornographic image recognition by strongly-supervised deep multiple instance learning" @default.
- W2566291355 cites W1575299770 @default.
- W2566291355 cites W1590510366 @default.
- W2566291355 cites W2007917976 @default.
- W2566291355 cites W2016016818 @default.
- W2566291355 cites W2035933607 @default.
- W2566291355 cites W2053037512 @default.
- W2566291355 cites W2075977566 @default.
- W2566291355 cites W2097117768 @default.
- W2566291355 cites W2130287785 @default.
- W2566291355 cites W2132984949 @default.
- W2566291355 cites W2135176316 @default.
- W2566291355 cites W2160541552 @default.
- W2566291355 cites W2163605009 @default.
- W2566291355 cites W2167912153 @default.
- W2566291355 cites W2182953902 @default.
- W2566291355 cites W2296073425 @default.
- W2566291355 cites W2952072685 @default.
- W2566291355 doi "https://doi.org/10.1109/icip.2016.7533195" @default.
- W2566291355 hasPublicationYear "2016" @default.
- W2566291355 type Work @default.
- W2566291355 sameAs 2566291355 @default.
- W2566291355 citedByCount "12" @default.
- W2566291355 countsByYear W25662913552019 @default.
- W2566291355 countsByYear W25662913552020 @default.
- W2566291355 countsByYear W25662913552021 @default.
- W2566291355 countsByYear W25662913552023 @default.
- W2566291355 crossrefType "proceedings-article" @default.
- W2566291355 hasAuthorship W2566291355A5004478562 @default.
- W2566291355 hasAuthorship W2566291355A5008491549 @default.
- W2566291355 hasAuthorship W2566291355A5023967844 @default.
- W2566291355 hasConcept C108583219 @default.
- W2566291355 hasConcept C115961682 @default.
- W2566291355 hasConcept C119857082 @default.
- W2566291355 hasConcept C136389625 @default.
- W2566291355 hasConcept C153180895 @default.
- W2566291355 hasConcept C154945302 @default.
- W2566291355 hasConcept C31972630 @default.
- W2566291355 hasConcept C41008148 @default.
- W2566291355 hasConcept C50644808 @default.
- W2566291355 hasConceptScore W2566291355C108583219 @default.
- W2566291355 hasConceptScore W2566291355C115961682 @default.
- W2566291355 hasConceptScore W2566291355C119857082 @default.
- W2566291355 hasConceptScore W2566291355C136389625 @default.
- W2566291355 hasConceptScore W2566291355C153180895 @default.
- W2566291355 hasConceptScore W2566291355C154945302 @default.
- W2566291355 hasConceptScore W2566291355C31972630 @default.
- W2566291355 hasConceptScore W2566291355C41008148 @default.
- W2566291355 hasConceptScore W2566291355C50644808 @default.
- W2566291355 hasLocation W25662913551 @default.
- W2566291355 hasOpenAccess W2566291355 @default.
- W2566291355 hasPrimaryLocation W25662913551 @default.
- W2566291355 hasRelatedWork W2908875379 @default.
- W2566291355 hasRelatedWork W2947809439 @default.
- W2566291355 hasRelatedWork W3182840600 @default.
- W2566291355 hasRelatedWork W3192794374 @default.
- W2566291355 hasRelatedWork W4220686584 @default.
- W2566291355 hasRelatedWork W4221136938 @default.
- W2566291355 hasRelatedWork W4223943233 @default.
- W2566291355 hasRelatedWork W4225598402 @default.
- W2566291355 hasRelatedWork W4246751904 @default.
- W2566291355 hasRelatedWork W4312200629 @default.
- W2566291355 isParatext "false" @default.
- W2566291355 isRetracted "false" @default.
- W2566291355 magId "2566291355" @default.
- W2566291355 workType "article" @default.