Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035213908> ?p ?o ?g. }
- W3035213908 endingPage "111493" @default.
- W3035213908 startingPage "111482" @default.
- W3035213908 abstract "Machine learning based bottom-up saliency detection (MLBU) methods are very popular recently. These MLBU methods firstly use prior knowledge to select some regions from the given image as training samples and label them. Based on training set, a saliency classifier is learned to classify salient object and background by applying machine learning algorithms in the given image. Nevertheless, training labels obtained by prior knowledge are not always accurate in some complex scenes, inaccurate training set is hard to make subsequent learning process succeed. To solve this problem, we propose an inaccurate supervised learning (ISL) based saliency detection framework, which assumes that training labels obtained by prior knowledge might be inaccurate and constructs three checking rules to remove mislabeled samples for more accurate training set construction. The refined training set is used to learn a saliency classifier which can better predict each image region. To obtain more accurate saliency inference, the proposed ISL process is introduced into a novel iterative feedback (IF) framework to generate better saliency result. Finally, we use smoothness operator to further smooth saliency result for performance improvement. Experimental results on three benchmark datasets demonstrate adequately the superiority of the proposed method." @default.
- W3035213908 created "2020-06-19" @default.
- W3035213908 creator A5000383993 @default.
- W3035213908 creator A5044628430 @default.
- W3035213908 creator A5070703807 @default.
- W3035213908 creator A5071623616 @default.
- W3035213908 creator A5073414420 @default.
- W3035213908 date "2020-01-01" @default.
- W3035213908 modified "2023-10-14" @default.
- W3035213908 title "Inaccurate Supervised Saliency Detection Based on Iterative Feedback Framework" @default.
- W3035213908 cites W1581590495 @default.
- W3035213908 cites W1595276678 @default.
- W3035213908 cites W1903001680 @default.
- W3035213908 cites W1947031653 @default.
- W3035213908 cites W1985192011 @default.
- W3035213908 cites W2002781701 @default.
- W3035213908 cites W2011900468 @default.
- W3035213908 cites W2024713411 @default.
- W3035213908 cites W2066624635 @default.
- W3035213908 cites W2086791339 @default.
- W3035213908 cites W2100470808 @default.
- W3035213908 cites W2118246710 @default.
- W3035213908 cites W2223308386 @default.
- W3035213908 cites W2342927252 @default.
- W3035213908 cites W2346506533 @default.
- W3035213908 cites W2472480899 @default.
- W3035213908 cites W2552652233 @default.
- W3035213908 cites W2588600710 @default.
- W3035213908 cites W2617634260 @default.
- W3035213908 cites W2740667773 @default.
- W3035213908 cites W2766439555 @default.
- W3035213908 cites W2770863526 @default.
- W3035213908 cites W2794883157 @default.
- W3035213908 cites W2808275385 @default.
- W3035213908 cites W2910149237 @default.
- W3035213908 cites W2945034008 @default.
- W3035213908 cites W2954204101 @default.
- W3035213908 cites W2963136160 @default.
- W3035213908 cites W2963526661 @default.
- W3035213908 cites W2963781443 @default.
- W3035213908 cites W2979355824 @default.
- W3035213908 cites W2999106269 @default.
- W3035213908 cites W3001637006 @default.
- W3035213908 cites W3001989900 @default.
- W3035213908 cites W3008257486 @default.
- W3035213908 cites W3012163793 @default.
- W3035213908 cites W4212906384 @default.
- W3035213908 cites W4232478844 @default.
- W3035213908 cites W4239147634 @default.
- W3035213908 doi "https://doi.org/10.1109/access.2020.3001041" @default.
- W3035213908 hasPublicationYear "2020" @default.
- W3035213908 type Work @default.
- W3035213908 sameAs 3035213908 @default.
- W3035213908 citedByCount "2" @default.
- W3035213908 countsByYear W30352139082023 @default.
- W3035213908 crossrefType "journal-article" @default.
- W3035213908 hasAuthorship W3035213908A5000383993 @default.
- W3035213908 hasAuthorship W3035213908A5044628430 @default.
- W3035213908 hasAuthorship W3035213908A5070703807 @default.
- W3035213908 hasAuthorship W3035213908A5071623616 @default.
- W3035213908 hasAuthorship W3035213908A5073414420 @default.
- W3035213908 hasBestOaLocation W30352139081 @default.
- W3035213908 hasConcept C119857082 @default.
- W3035213908 hasConcept C13280743 @default.
- W3035213908 hasConcept C136389625 @default.
- W3035213908 hasConcept C153180895 @default.
- W3035213908 hasConcept C154945302 @default.
- W3035213908 hasConcept C177264268 @default.
- W3035213908 hasConcept C185798385 @default.
- W3035213908 hasConcept C199360897 @default.
- W3035213908 hasConcept C205649164 @default.
- W3035213908 hasConcept C2776214188 @default.
- W3035213908 hasConcept C41008148 @default.
- W3035213908 hasConcept C50644808 @default.
- W3035213908 hasConcept C95623464 @default.
- W3035213908 hasConceptScore W3035213908C119857082 @default.
- W3035213908 hasConceptScore W3035213908C13280743 @default.
- W3035213908 hasConceptScore W3035213908C136389625 @default.
- W3035213908 hasConceptScore W3035213908C153180895 @default.
- W3035213908 hasConceptScore W3035213908C154945302 @default.
- W3035213908 hasConceptScore W3035213908C177264268 @default.
- W3035213908 hasConceptScore W3035213908C185798385 @default.
- W3035213908 hasConceptScore W3035213908C199360897 @default.
- W3035213908 hasConceptScore W3035213908C205649164 @default.
- W3035213908 hasConceptScore W3035213908C2776214188 @default.
- W3035213908 hasConceptScore W3035213908C41008148 @default.
- W3035213908 hasConceptScore W3035213908C50644808 @default.
- W3035213908 hasConceptScore W3035213908C95623464 @default.
- W3035213908 hasFunder F4320321001 @default.
- W3035213908 hasFunder F4320335787 @default.
- W3035213908 hasLocation W30352139081 @default.
- W3035213908 hasOpenAccess W3035213908 @default.
- W3035213908 hasPrimaryLocation W30352139081 @default.
- W3035213908 hasRelatedWork W2001652754 @default.
- W3035213908 hasRelatedWork W2549006548 @default.
- W3035213908 hasRelatedWork W2623427976 @default.
- W3035213908 hasRelatedWork W2807311372 @default.
- W3035213908 hasRelatedWork W2921036759 @default.