Matches in SemOpenAlex for { <https://semopenalex.org/work/W2078903912> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2078903912 abstract "Saliency prediction typically relies on hand-crafted (multiscale) features that are combined in different ways to form a master saliency map, which encodes local image conspicuity. Recent improvements to the state of the art on standard benchmarks such as MIT1003 have been achieved mostly by incrementally adding more and more hand-tuned features (such as car or face detectors) to existing models. In contrast, we here follow an entirely automatic data-driven approach that performs a large-scale search for optimal features. We identify those instances of a richly-parameterized bio-inspired model family (hierarchical neuromorphic networks) that successfully predict image saliency. Because of the high dimensionality of this parameter space, we use automated hyperparameter optimization to efficiently guide the search. The optimal blend of such multilayer features combined with a simple linear classifier achieves excellent performance on several image saliency benchmarks. Our models outperform the state of the art on MIT1003, on which features and classifiers are learned. Without additional training, these models generalize well to two other image saliency data sets, Toronto and NUSEF, despite their different image content. Finally, our algorithm scores best of all the 23 models evaluated to date on the MIT300 saliency challenge, which uses a hidden test set to facilitate an unbiased comparison." @default.
- W2078903912 created "2016-06-24" @default.
- W2078903912 creator A5041967088 @default.
- W2078903912 creator A5052325705 @default.
- W2078903912 creator A5079778751 @default.
- W2078903912 date "2014-06-01" @default.
- W2078903912 modified "2023-10-12" @default.
- W2078903912 title "Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images" @default.
- W2078903912 cites W1490100156 @default.
- W2078903912 cites W1510835000 @default.
- W2078903912 cites W2008066834 @default.
- W2078903912 cites W2041719651 @default.
- W2078903912 cites W2055111849 @default.
- W2078903912 cites W2097295641 @default.
- W2078903912 cites W2128272608 @default.
- W2078903912 cites W2133589685 @default.
- W2078903912 cites W2137484966 @default.
- W2078903912 cites W2144161366 @default.
- W2078903912 cites W2146103513 @default.
- W2078903912 cites W2149095485 @default.
- W2078903912 cites W2151900481 @default.
- W2078903912 cites W2158983298 @default.
- W2078903912 cites W2164716063 @default.
- W2078903912 cites W2168020168 @default.
- W2078903912 doi "https://doi.org/10.1109/cvpr.2014.358" @default.
- W2078903912 hasPublicationYear "2014" @default.
- W2078903912 type Work @default.
- W2078903912 sameAs 2078903912 @default.
- W2078903912 citedByCount "319" @default.
- W2078903912 countsByYear W20789039122014 @default.
- W2078903912 countsByYear W20789039122015 @default.
- W2078903912 countsByYear W20789039122016 @default.
- W2078903912 countsByYear W20789039122017 @default.
- W2078903912 countsByYear W20789039122018 @default.
- W2078903912 countsByYear W20789039122019 @default.
- W2078903912 countsByYear W20789039122020 @default.
- W2078903912 countsByYear W20789039122021 @default.
- W2078903912 countsByYear W20789039122022 @default.
- W2078903912 countsByYear W20789039122023 @default.
- W2078903912 crossrefType "proceedings-article" @default.
- W2078903912 hasAuthorship W2078903912A5041967088 @default.
- W2078903912 hasAuthorship W2078903912A5052325705 @default.
- W2078903912 hasAuthorship W2078903912A5079778751 @default.
- W2078903912 hasConcept C111030470 @default.
- W2078903912 hasConcept C11413529 @default.
- W2078903912 hasConcept C115961682 @default.
- W2078903912 hasConcept C119857082 @default.
- W2078903912 hasConcept C153180895 @default.
- W2078903912 hasConcept C154945302 @default.
- W2078903912 hasConcept C165464430 @default.
- W2078903912 hasConcept C177264268 @default.
- W2078903912 hasConcept C199360897 @default.
- W2078903912 hasConcept C41008148 @default.
- W2078903912 hasConcept C8642999 @default.
- W2078903912 hasConcept C95623464 @default.
- W2078903912 hasConceptScore W2078903912C111030470 @default.
- W2078903912 hasConceptScore W2078903912C11413529 @default.
- W2078903912 hasConceptScore W2078903912C115961682 @default.
- W2078903912 hasConceptScore W2078903912C119857082 @default.
- W2078903912 hasConceptScore W2078903912C153180895 @default.
- W2078903912 hasConceptScore W2078903912C154945302 @default.
- W2078903912 hasConceptScore W2078903912C165464430 @default.
- W2078903912 hasConceptScore W2078903912C177264268 @default.
- W2078903912 hasConceptScore W2078903912C199360897 @default.
- W2078903912 hasConceptScore W2078903912C41008148 @default.
- W2078903912 hasConceptScore W2078903912C8642999 @default.
- W2078903912 hasConceptScore W2078903912C95623464 @default.
- W2078903912 hasLocation W20789039121 @default.
- W2078903912 hasOpenAccess W2078903912 @default.
- W2078903912 hasPrimaryLocation W20789039121 @default.
- W2078903912 hasRelatedWork W2001652754 @default.
- W2078903912 hasRelatedWork W2160451891 @default.
- W2078903912 hasRelatedWork W2961085424 @default.
- W2078903912 hasRelatedWork W3199608561 @default.
- W2078903912 hasRelatedWork W4210794429 @default.
- W2078903912 hasRelatedWork W4223456145 @default.
- W2078903912 hasRelatedWork W4280535922 @default.
- W2078903912 hasRelatedWork W4283697347 @default.
- W2078903912 hasRelatedWork W4295309597 @default.
- W2078903912 hasRelatedWork W4309113015 @default.
- W2078903912 isParatext "false" @default.
- W2078903912 isRetracted "false" @default.
- W2078903912 magId "2078903912" @default.
- W2078903912 workType "article" @default.