Matches in SemOpenAlex for { <https://semopenalex.org/work/W2497806559> ?p ?o ?g. }
- W2497806559 endingPage "113" @default.
- W2497806559 startingPage "98" @default.
- W2497806559 abstract "Saliency integration has attracted much attention on unifying saliency maps from multiple saliency models. Previous offline integration methods usually face two challenges: 1) if most of the candidate saliency models misjudge the saliency on an image, the integration result will lean heavily on those inferior candidate models; and 2) an unawareness of the ground truth saliency labels brings difficulty in estimating the expertise of each candidate model. To address these problems, in this paper, we propose an arbitrator model (AM) for saliency integration. First, we incorporate the consensus of multiple saliency models and the external knowledge into a reference map to effectively rectify the misleading by candidate models. Second, our quest for ways of estimating the expertise of the saliency models without ground truth labels gives rise to two distinct online model-expertise estimation methods. Finally, we derive a Bayesian integration framework to reconcile the saliency models of varying expertise and the reference map. To extensively evaluate the proposed AM model, we test 27 state-of-the-art saliency models, covering both traditional and deep learning ones, on various combinations over four datasets. The evaluation results show that the AM model improves the performance substantially compared to the existing state-of-the-art integration methods, regardless of the chosen candidate saliency models." @default.
- W2497806559 created "2016-08-23" @default.
- W2497806559 creator A5008922680 @default.
- W2497806559 creator A5010479652 @default.
- W2497806559 creator A5026880795 @default.
- W2497806559 creator A5038550641 @default.
- W2497806559 creator A5058509635 @default.
- W2497806559 creator A5082301986 @default.
- W2497806559 date "2019-01-01" @default.
- W2497806559 modified "2023-09-25" @default.
- W2497806559 title "Saliency Integration: An Arbitrator Model" @default.
- W2497806559 cites W1510835000 @default.
- W2497806559 cites W1903001680 @default.
- W2497806559 cites W1914179642 @default.
- W2497806559 cites W1918837316 @default.
- W2497806559 cites W1942214758 @default.
- W2497806559 cites W1947031653 @default.
- W2497806559 cites W1967125100 @default.
- W2497806559 cites W1977556410 @default.
- W2497806559 cites W1985984012 @default.
- W2497806559 cites W1996326832 @default.
- W2497806559 cites W2008066834 @default.
- W2497806559 cites W2036424138 @default.
- W2497806559 cites W2037328649 @default.
- W2497806559 cites W2039313011 @default.
- W2497806559 cites W2041719651 @default.
- W2497806559 cites W2046863527 @default.
- W2497806559 cites W2047670868 @default.
- W2497806559 cites W2080142539 @default.
- W2497806559 cites W2094493060 @default.
- W2497806559 cites W2098702446 @default.
- W2497806559 cites W2100470808 @default.
- W2497806559 cites W2118246710 @default.
- W2497806559 cites W2122076510 @default.
- W2497806559 cites W2127707449 @default.
- W2497806559 cites W2127723395 @default.
- W2497806559 cites W2128272608 @default.
- W2497806559 cites W2128340050 @default.
- W2497806559 cites W2128446554 @default.
- W2497806559 cites W2133589685 @default.
- W2497806559 cites W2140654078 @default.
- W2497806559 cites W2146103513 @default.
- W2497806559 cites W2152233525 @default.
- W2497806559 cites W2157487943 @default.
- W2497806559 cites W2162216530 @default.
- W2497806559 cites W2166650627 @default.
- W2497806559 cites W2201780148 @default.
- W2497806559 cites W2211996548 @default.
- W2497806559 cites W2283283146 @default.
- W2497806559 cites W2288514685 @default.
- W2497806559 cites W2293332611 @default.
- W2497806559 cites W2293368487 @default.
- W2497806559 cites W2294182682 @default.
- W2497806559 cites W2358876993 @default.
- W2497806559 cites W2461475918 @default.
- W2497806559 cites W2470270897 @default.
- W2497806559 cites W2472782738 @default.
- W2497806559 cites W2509197172 @default.
- W2497806559 cites W2509297762 @default.
- W2497806559 cites W2569272946 @default.
- W2497806559 cites W2581874211 @default.
- W2497806559 cites W2605793178 @default.
- W2497806559 cites W2612390049 @default.
- W2497806559 cites W2617634260 @default.
- W2497806559 cites W2765161239 @default.
- W2497806559 cites W2777511827 @default.
- W2497806559 cites W2789492864 @default.
- W2497806559 cites W3104979525 @default.
- W2497806559 cites W3125520697 @default.
- W2497806559 cites W4239147634 @default.
- W2497806559 doi "https://doi.org/10.1109/tmm.2018.2856126" @default.
- W2497806559 hasPublicationYear "2019" @default.
- W2497806559 type Work @default.
- W2497806559 sameAs 2497806559 @default.
- W2497806559 citedByCount "10" @default.
- W2497806559 countsByYear W24978065592019 @default.
- W2497806559 countsByYear W24978065592020 @default.
- W2497806559 countsByYear W24978065592021 @default.
- W2497806559 countsByYear W24978065592022 @default.
- W2497806559 countsByYear W24978065592023 @default.
- W2497806559 crossrefType "journal-article" @default.
- W2497806559 hasAuthorship W2497806559A5008922680 @default.
- W2497806559 hasAuthorship W2497806559A5010479652 @default.
- W2497806559 hasAuthorship W2497806559A5026880795 @default.
- W2497806559 hasAuthorship W2497806559A5038550641 @default.
- W2497806559 hasAuthorship W2497806559A5058509635 @default.
- W2497806559 hasAuthorship W2497806559A5082301986 @default.
- W2497806559 hasBestOaLocation W24978065592 @default.
- W2497806559 hasConcept C107673813 @default.
- W2497806559 hasConcept C115961682 @default.
- W2497806559 hasConcept C119857082 @default.
- W2497806559 hasConcept C124101348 @default.
- W2497806559 hasConcept C144024400 @default.
- W2497806559 hasConcept C146849305 @default.
- W2497806559 hasConcept C153180895 @default.
- W2497806559 hasConcept C154945302 @default.
- W2497806559 hasConcept C2779304628 @default.
- W2497806559 hasConcept C2779679900 @default.