Matches in SemOpenAlex for { <https://semopenalex.org/work/W2551567353> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2551567353 abstract "Scene recognition is a task in computer vision that aims to understand images at a higher level than the more well known task of object recognition. With recent advances in GPU-based learning and large-scale data sets, neural networks have been able to learn representations directly from images that result in very low error rates on data sets with hundreds of scene categories. Scene understanding is a crucial step towards human-like visual knowledge, as it contextualizes object recognition, a task on which modern systems have surpassed human performance.This thesis adapts scene recognition from vision to language. We leverage image data to provide a visual semantic grounding for text in order to build a corpus for event localization, a novel classification task that aims to learn where the events described by sentences take place. First, we describe the annotation methodology used to construct the corpus and the steps taken to validate the data. We describe the most important characteristics of the corpus, and finally, present results from several classification models, both feature-based and neural, some of which achieve nearly 70% accuracy on the 13-way classification task presented here.Our experiments show that training on the Event Localization Corpus allows classifiers to predict event locations accurately even when information about the location is not explicit in the sentence." @default.
- W2551567353 created "2016-11-30" @default.
- W2551567353 creator A5042196970 @default.
- W2551567353 date "2016-01-01" @default.
- W2551567353 modified "2023-09-24" @default.
- W2551567353 title "A Corpus for Event Localization" @default.
- W2551567353 cites W1423339008 @default.
- W2551567353 cites W1895577753 @default.
- W2551567353 cites W1948566616 @default.
- W2551567353 cites W2064675550 @default.
- W2551567353 cites W2081580037 @default.
- W2551567353 cites W2095705004 @default.
- W2551567353 cites W2101234009 @default.
- W2551567353 cites W2108598243 @default.
- W2551567353 cites W2120615054 @default.
- W2551567353 cites W2152175008 @default.
- W2551567353 cites W2185175083 @default.
- W2551567353 cites W2250201115 @default.
- W2551567353 cites W2252029660 @default.
- W2551567353 cites W2257051837 @default.
- W2551567353 cites W2949117887 @default.
- W2551567353 cites W2950577311 @default.
- W2551567353 cites W2963083845 @default.
- W2551567353 cites W2964121744 @default.
- W2551567353 cites W581956982 @default.
- W2551567353 cites W68733909 @default.
- W2551567353 hasPublicationYear "2016" @default.
- W2551567353 type Work @default.
- W2551567353 sameAs 2551567353 @default.
- W2551567353 citedByCount "0" @default.
- W2551567353 crossrefType "dissertation" @default.
- W2551567353 hasAuthorship W2551567353A5042196970 @default.
- W2551567353 hasConcept C119857082 @default.
- W2551567353 hasConcept C121332964 @default.
- W2551567353 hasConcept C153083717 @default.
- W2551567353 hasConcept C153180895 @default.
- W2551567353 hasConcept C154945302 @default.
- W2551567353 hasConcept C162324750 @default.
- W2551567353 hasConcept C187736073 @default.
- W2551567353 hasConcept C199360897 @default.
- W2551567353 hasConcept C204321447 @default.
- W2551567353 hasConcept C2776321320 @default.
- W2551567353 hasConcept C2777530160 @default.
- W2551567353 hasConcept C2779662365 @default.
- W2551567353 hasConcept C2780451532 @default.
- W2551567353 hasConcept C2780801425 @default.
- W2551567353 hasConcept C41008148 @default.
- W2551567353 hasConcept C62520636 @default.
- W2551567353 hasConceptScore W2551567353C119857082 @default.
- W2551567353 hasConceptScore W2551567353C121332964 @default.
- W2551567353 hasConceptScore W2551567353C153083717 @default.
- W2551567353 hasConceptScore W2551567353C153180895 @default.
- W2551567353 hasConceptScore W2551567353C154945302 @default.
- W2551567353 hasConceptScore W2551567353C162324750 @default.
- W2551567353 hasConceptScore W2551567353C187736073 @default.
- W2551567353 hasConceptScore W2551567353C199360897 @default.
- W2551567353 hasConceptScore W2551567353C204321447 @default.
- W2551567353 hasConceptScore W2551567353C2776321320 @default.
- W2551567353 hasConceptScore W2551567353C2777530160 @default.
- W2551567353 hasConceptScore W2551567353C2779662365 @default.
- W2551567353 hasConceptScore W2551567353C2780451532 @default.
- W2551567353 hasConceptScore W2551567353C2780801425 @default.
- W2551567353 hasConceptScore W2551567353C41008148 @default.
- W2551567353 hasConceptScore W2551567353C62520636 @default.
- W2551567353 hasLocation W25515673531 @default.
- W2551567353 hasOpenAccess W2551567353 @default.
- W2551567353 hasPrimaryLocation W25515673531 @default.
- W2551567353 hasRelatedWork W144280133 @default.
- W2551567353 hasRelatedWork W156899190 @default.
- W2551567353 hasRelatedWork W1992198546 @default.
- W2551567353 hasRelatedWork W2526486375 @default.
- W2551567353 hasRelatedWork W2898692195 @default.
- W2551567353 hasRelatedWork W2940627316 @default.
- W2551567353 hasRelatedWork W2945177723 @default.
- W2551567353 hasRelatedWork W2963540523 @default.
- W2551567353 hasRelatedWork W2963736289 @default.
- W2551567353 hasRelatedWork W2964241990 @default.
- W2551567353 hasRelatedWork W2966466719 @default.
- W2551567353 hasRelatedWork W2988326850 @default.
- W2551567353 hasRelatedWork W3035083084 @default.
- W2551567353 hasRelatedWork W3035184646 @default.
- W2551567353 hasRelatedWork W3089089456 @default.
- W2551567353 hasRelatedWork W3112077297 @default.
- W2551567353 hasRelatedWork W3139022918 @default.
- W2551567353 hasRelatedWork W3154453661 @default.
- W2551567353 hasRelatedWork W3155322285 @default.
- W2551567353 hasRelatedWork W3178036561 @default.
- W2551567353 isParatext "false" @default.
- W2551567353 isRetracted "false" @default.
- W2551567353 magId "2551567353" @default.
- W2551567353 workType "dissertation" @default.