Matches in SemOpenAlex for { <https://semopenalex.org/work/W1942214758> ?p ?o ?g. }
- W1942214758 abstract "Low-level saliency cues or priors do not produce good enough saliency detection results especially when the salient object presents in a low-contrast background with confusing visual appearance. This issue raises a serious problem for conventional approaches. In this paper, we tackle this problem by proposing a multi-context deep learning framework for salient object detection. We employ deep Convolutional Neural Networks to model saliency of objects in images. Global context and local context are both taken into account, and are jointly modeled in a unified multi-context deep learning framework. To provide a better initialization for training the deep neural networks, we investigate different pre-training strategies, and a task-specific pre-training scheme is designed to make the multi-context modeling suited for saliency detection. Furthermore, recently proposed contemporary deep models in the ImageNet Image Classification Challenge are tested, and their effectiveness in saliency detection are investigated. Our approach is extensively evaluated on five public datasets, and experimental results show significant and consistent improvements over the state-of-the-art methods." @default.
- W1942214758 created "2016-06-24" @default.
- W1942214758 creator A5024522346 @default.
- W1942214758 creator A5065073978 @default.
- W1942214758 creator A5079410647 @default.
- W1942214758 creator A5087818121 @default.
- W1942214758 date "2015-06-01" @default.
- W1942214758 modified "2023-10-16" @default.
- W1942214758 title "Saliency detection by multi-context deep learning" @default.
- W1942214758 cites W1510835000 @default.
- W1942214758 cites W1976948919 @default.
- W1942214758 cites W1982075130 @default.
- W1942214758 cites W1996326832 @default.
- W1942214758 cites W2002781701 @default.
- W1942214758 cites W2006180404 @default.
- W1942214758 cites W2017691720 @default.
- W1942214758 cites W2031489346 @default.
- W1942214758 cites W2037328649 @default.
- W1942214758 cites W2037954058 @default.
- W1942214758 cites W2039313011 @default.
- W1942214758 cites W2046835352 @default.
- W1942214758 cites W2047670868 @default.
- W1942214758 cites W2065372998 @default.
- W1942214758 cites W2066624635 @default.
- W1942214758 cites W2078903912 @default.
- W1942214758 cites W2084997728 @default.
- W1942214758 cites W2086791339 @default.
- W1942214758 cites W2100470808 @default.
- W1942214758 cites W2107200795 @default.
- W1942214758 cites W2116064496 @default.
- W1942214758 cites W2118246710 @default.
- W1942214758 cites W2122076510 @default.
- W1942214758 cites W2125378844 @default.
- W1942214758 cites W2128272608 @default.
- W1942214758 cites W2128340050 @default.
- W1942214758 cites W2128715914 @default.
- W1942214758 cites W2138046011 @default.
- W1942214758 cites W2140654078 @default.
- W1942214758 cites W2146103513 @default.
- W1942214758 cites W2147800946 @default.
- W1942214758 cites W2156777442 @default.
- W1942214758 cites W2158983298 @default.
- W1942214758 cites W2161185676 @default.
- W1942214758 cites W2162681317 @default.
- W1942214758 cites W2166650627 @default.
- W1942214758 cites W2396217339 @default.
- W1942214758 cites W3137241515 @default.
- W1942214758 cites W959332845 @default.
- W1942214758 doi "https://doi.org/10.1109/cvpr.2015.7298731" @default.
- W1942214758 hasPublicationYear "2015" @default.
- W1942214758 type Work @default.
- W1942214758 sameAs 1942214758 @default.
- W1942214758 citedByCount "730" @default.
- W1942214758 countsByYear W19422147582014 @default.
- W1942214758 countsByYear W19422147582015 @default.
- W1942214758 countsByYear W19422147582016 @default.
- W1942214758 countsByYear W19422147582017 @default.
- W1942214758 countsByYear W19422147582018 @default.
- W1942214758 countsByYear W19422147582019 @default.
- W1942214758 countsByYear W19422147582020 @default.
- W1942214758 countsByYear W19422147582021 @default.
- W1942214758 countsByYear W19422147582022 @default.
- W1942214758 countsByYear W19422147582023 @default.
- W1942214758 crossrefType "proceedings-article" @default.
- W1942214758 hasAuthorship W1942214758A5024522346 @default.
- W1942214758 hasAuthorship W1942214758A5065073978 @default.
- W1942214758 hasAuthorship W1942214758A5079410647 @default.
- W1942214758 hasAuthorship W1942214758A5087818121 @default.
- W1942214758 hasBestOaLocation W19422147582 @default.
- W1942214758 hasConcept C108583219 @default.
- W1942214758 hasConcept C114466953 @default.
- W1942214758 hasConcept C119857082 @default.
- W1942214758 hasConcept C151730666 @default.
- W1942214758 hasConcept C153180895 @default.
- W1942214758 hasConcept C154945302 @default.
- W1942214758 hasConcept C183322885 @default.
- W1942214758 hasConcept C199360897 @default.
- W1942214758 hasConcept C2776151529 @default.
- W1942214758 hasConcept C2779343474 @default.
- W1942214758 hasConcept C2780719617 @default.
- W1942214758 hasConcept C2781238097 @default.
- W1942214758 hasConcept C2984842247 @default.
- W1942214758 hasConcept C41008148 @default.
- W1942214758 hasConcept C81363708 @default.
- W1942214758 hasConcept C86803240 @default.
- W1942214758 hasConceptScore W1942214758C108583219 @default.
- W1942214758 hasConceptScore W1942214758C114466953 @default.
- W1942214758 hasConceptScore W1942214758C119857082 @default.
- W1942214758 hasConceptScore W1942214758C151730666 @default.
- W1942214758 hasConceptScore W1942214758C153180895 @default.
- W1942214758 hasConceptScore W1942214758C154945302 @default.
- W1942214758 hasConceptScore W1942214758C183322885 @default.
- W1942214758 hasConceptScore W1942214758C199360897 @default.
- W1942214758 hasConceptScore W1942214758C2776151529 @default.
- W1942214758 hasConceptScore W1942214758C2779343474 @default.
- W1942214758 hasConceptScore W1942214758C2780719617 @default.
- W1942214758 hasConceptScore W1942214758C2781238097 @default.
- W1942214758 hasConceptScore W1942214758C2984842247 @default.
- W1942214758 hasConceptScore W1942214758C41008148 @default.
- W1942214758 hasConceptScore W1942214758C81363708 @default.