FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2528287124> ?p ?o ?g. }

• W2528287124 abstract "We address the problem of estimating image difficulty defined as the human response time for solving a visual search task. We collect human annotations of image difficulty for the PASCAL VOC 2012 data set through a crowd-sourcing platform. We then analyze what human interpretable image properties can have an impact on visual search difficulty, and how accurate are those properties for predicting difficulty. Next, we build a regression model based on deep features learned with state of the art convolutional neural networks and show better results for predicting the ground-truth visual search difficulty scores produced by human annotators. Our model is able to correctly rank about 75% image pairs according to their difficulty score. We also show that our difficulty predictor generalizes well to new classes not seen during training. Finally, we demonstrate that our predicted difficulty scores are useful for weakly supervised object localization (8% improvement) and semi-supervised object classification (1% improvement)." @default.
• W2528287124 created "2016-10-14" @default.
• W2528287124 creator A5003940396 @default.
• W2528287124 creator A5045881151 @default.
• W2528287124 creator A5073141800 @default.
• W2528287124 creator A5081017623 @default.
• W2528287124 creator A5083743189 @default.
• W2528287124 creator A5086392501 @default.
• W2528287124 date "2016-06-01" @default.
• W2528287124 modified "2023-09-26" @default.
• W2528287124 title "How Hard Can It Be? Estimating the Difficulty of Visual Search in an Image" @default.
• W2528287124 cites W1510073064 @default.
• W2528287124 cites W1566135517 @default.
• W2528287124 cites W1946367136 @default.
• W2528287124 cites W1965729921 @default.
• W2528287124 cites W1975080851 @default.
• W2528287124 cites W1976047850 @default.
• W2528287124 cites W1999478155 @default.
• W2528287124 cites W2002178334 @default.
• W2528287124 cites W2006104434 @default.
• W2528287124 cites W2009627211 @default.
• W2528287124 cites W2016016818 @default.
• W2528287124 cites W2020477327 @default.
• W2528287124 cites W2035447781 @default.
• W2528287124 cites W2061629163 @default.
• W2528287124 cites W2066624635 @default.
• W2528287124 cites W2097430540 @default.
• W2528287124 cites W2102605133 @default.
• W2528287124 cites W2107363596 @default.
• W2528287124 cites W2110119381 @default.
• W2528287124 cites W2117539524 @default.
• W2528287124 cites W2119531662 @default.
• W2528287124 cites W2128272608 @default.
• W2528287124 cites W2128715914 @default.
• W2528287124 cites W2146103513 @default.
• W2528287124 cites W2153635508 @default.
• W2528287124 cites W2164716063 @default.
• W2528287124 cites W2208417422 @default.
• W2528287124 cites W2296073425 @default.
• W2528287124 cites W2485261912 @default.
• W2528287124 cites W2963934231 @default.
• W2528287124 doi "https://doi.org/10.1109/cvpr.2016.237" @default.
• W2528287124 hasPublicationYear "2016" @default.
• W2528287124 type Work @default.
• W2528287124 sameAs 2528287124 @default.
• W2528287124 citedByCount "68" @default.
• W2528287124 countsByYear W25282871242016 @default.
• W2528287124 countsByYear W25282871242017 @default.
• W2528287124 countsByYear W25282871242018 @default.
• W2528287124 countsByYear W25282871242019 @default.
• W2528287124 countsByYear W25282871242020 @default.
• W2528287124 countsByYear W25282871242021 @default.
• W2528287124 countsByYear W25282871242022 @default.
• W2528287124 countsByYear W25282871242023 @default.
• W2528287124 crossrefType "proceedings-article" @default.
• W2528287124 hasAuthorship W2528287124A5003940396 @default.
• W2528287124 hasAuthorship W2528287124A5045881151 @default.
• W2528287124 hasAuthorship W2528287124A5073141800 @default.
• W2528287124 hasAuthorship W2528287124A5081017623 @default.
• W2528287124 hasAuthorship W2528287124A5083743189 @default.
• W2528287124 hasAuthorship W2528287124A5086392501 @default.
• W2528287124 hasBestOaLocation W25282871242 @default.
• W2528287124 hasConcept C114614502 @default.
• W2528287124 hasConcept C115961682 @default.
• W2528287124 hasConcept C119857082 @default.
• W2528287124 hasConcept C146849305 @default.
• W2528287124 hasConcept C153180895 @default.
• W2528287124 hasConcept C154945302 @default.
• W2528287124 hasConcept C162324750 @default.
• W2528287124 hasConcept C164226766 @default.
• W2528287124 hasConcept C177264268 @default.
• W2528287124 hasConcept C187736073 @default.
• W2528287124 hasConcept C189430467 @default.
• W2528287124 hasConcept C199360897 @default.
• W2528287124 hasConcept C2780451532 @default.
• W2528287124 hasConcept C2781238097 @default.
• W2528287124 hasConcept C33923547 @default.
• W2528287124 hasConcept C36464697 @default.
• W2528287124 hasConcept C41008148 @default.
• W2528287124 hasConcept C75608658 @default.
• W2528287124 hasConcept C81363708 @default.
• W2528287124 hasConcept C86037889 @default.
• W2528287124 hasConceptScore W2528287124C114614502 @default.
• W2528287124 hasConceptScore W2528287124C115961682 @default.
• W2528287124 hasConceptScore W2528287124C119857082 @default.
• W2528287124 hasConceptScore W2528287124C146849305 @default.
• W2528287124 hasConceptScore W2528287124C153180895 @default.
• W2528287124 hasConceptScore W2528287124C154945302 @default.
• W2528287124 hasConceptScore W2528287124C162324750 @default.
• W2528287124 hasConceptScore W2528287124C164226766 @default.
• W2528287124 hasConceptScore W2528287124C177264268 @default.
• W2528287124 hasConceptScore W2528287124C187736073 @default.
• W2528287124 hasConceptScore W2528287124C189430467 @default.
• W2528287124 hasConceptScore W2528287124C199360897 @default.
• W2528287124 hasConceptScore W2528287124C2780451532 @default.
• W2528287124 hasConceptScore W2528287124C2781238097 @default.
• W2528287124 hasConceptScore W2528287124C33923547 @default.
• W2528287124 hasConceptScore W2528287124C36464697 @default.
• W2528287124 hasConceptScore W2528287124C41008148 @default.
• W2528287124 hasConceptScore W2528287124C75608658 @default.

• next