Matches in SemOpenAlex for { <https://semopenalex.org/work/W1979983254> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W1979983254 abstract "Automatically assigning semantically relevant tags to an image is an important task in machine learning. Manyalgorithms have been proposed to annotate images based on features such as color, texture, and shape. Successof these algorithms is dependent on carefully handcrafted features. Deep learning models are widely used tolearn abstract, high level representations from raw data. Deep belief networks are the most commonly useddeep learning models formed by pre-training the individual Restricted Boltzmann Machines in a layer-wisefashion and then stacking together and training them using error back-propagation. In the deep convolutionalnetworks, convolution operation is used to extract features from different sub-regions of the images to learnbetter representations. To reduce the time taken for training, models that use convex optimization and kerneltrick have been proposed. In this paper we explore two such models, Tensor Deep Stacking Network andKernel Deep Convex Network, for the task of automatic image annotation. We use a deep convolutionalnetwork to extract high level features from raw images, and then use them as inputs to the convex deeplearning models. Performance of the proposed approach is evaluated on benchmark image datasets." @default.
- W1979983254 created "2016-06-24" @default.
- W1979983254 creator A5001015846 @default.
- W1979983254 creator A5058597860 @default.
- W1979983254 date "2015-01-01" @default.
- W1979983254 modified "2023-10-16" @default.
- W1979983254 title "Automatic Image Annotation Using Convex Deep Learning Models" @default.
- W1979983254 cites W1612003148 @default.
- W1979983254 cites W189596042 @default.
- W1979983254 cites W1999954155 @default.
- W1979983254 cites W2015861736 @default.
- W1979983254 cites W2052684427 @default.
- W1979983254 cites W2064630666 @default.
- W1979983254 cites W2074818733 @default.
- W1979983254 cites W2100495367 @default.
- W1979983254 cites W2108581046 @default.
- W1979983254 cites W2108597378 @default.
- W1979983254 cites W2130325614 @default.
- W1979983254 cites W2136922672 @default.
- W1979983254 cites W2139622435 @default.
- W1979983254 cites W2143605804 @default.
- W1979983254 cites W2149600041 @default.
- W1979983254 cites W2161000554 @default.
- W1979983254 cites W2163922914 @default.
- W1979983254 cites W2188343820 @default.
- W1979983254 doi "https://doi.org/10.5220/0005216700920099" @default.
- W1979983254 hasPublicationYear "2015" @default.
- W1979983254 type Work @default.
- W1979983254 sameAs 1979983254 @default.
- W1979983254 citedByCount "1" @default.
- W1979983254 countsByYear W19799832542021 @default.
- W1979983254 crossrefType "proceedings-article" @default.
- W1979983254 hasAuthorship W1979983254A5001015846 @default.
- W1979983254 hasAuthorship W1979983254A5058597860 @default.
- W1979983254 hasConcept C108583219 @default.
- W1979983254 hasConcept C114614502 @default.
- W1979983254 hasConcept C119857082 @default.
- W1979983254 hasConcept C13280743 @default.
- W1979983254 hasConcept C153180895 @default.
- W1979983254 hasConcept C154945302 @default.
- W1979983254 hasConcept C162324750 @default.
- W1979983254 hasConcept C185798385 @default.
- W1979983254 hasConcept C187736073 @default.
- W1979983254 hasConcept C192576344 @default.
- W1979983254 hasConcept C199354608 @default.
- W1979983254 hasConcept C205649164 @default.
- W1979983254 hasConcept C2780451532 @default.
- W1979983254 hasConcept C33923547 @default.
- W1979983254 hasConcept C41008148 @default.
- W1979983254 hasConcept C74193536 @default.
- W1979983254 hasConcept C81363708 @default.
- W1979983254 hasConcept C97385483 @default.
- W1979983254 hasConceptScore W1979983254C108583219 @default.
- W1979983254 hasConceptScore W1979983254C114614502 @default.
- W1979983254 hasConceptScore W1979983254C119857082 @default.
- W1979983254 hasConceptScore W1979983254C13280743 @default.
- W1979983254 hasConceptScore W1979983254C153180895 @default.
- W1979983254 hasConceptScore W1979983254C154945302 @default.
- W1979983254 hasConceptScore W1979983254C162324750 @default.
- W1979983254 hasConceptScore W1979983254C185798385 @default.
- W1979983254 hasConceptScore W1979983254C187736073 @default.
- W1979983254 hasConceptScore W1979983254C192576344 @default.
- W1979983254 hasConceptScore W1979983254C199354608 @default.
- W1979983254 hasConceptScore W1979983254C205649164 @default.
- W1979983254 hasConceptScore W1979983254C2780451532 @default.
- W1979983254 hasConceptScore W1979983254C33923547 @default.
- W1979983254 hasConceptScore W1979983254C41008148 @default.
- W1979983254 hasConceptScore W1979983254C74193536 @default.
- W1979983254 hasConceptScore W1979983254C81363708 @default.
- W1979983254 hasConceptScore W1979983254C97385483 @default.
- W1979983254 hasLocation W19799832541 @default.
- W1979983254 hasOpenAccess W1979983254 @default.
- W1979983254 hasPrimaryLocation W19799832541 @default.
- W1979983254 hasRelatedWork W2084146405 @default.
- W1979983254 hasRelatedWork W2108665656 @default.
- W1979983254 hasRelatedWork W2259768202 @default.
- W1979983254 hasRelatedWork W2395709724 @default.
- W1979983254 hasRelatedWork W2547411571 @default.
- W1979983254 hasRelatedWork W2563764042 @default.
- W1979983254 hasRelatedWork W2739937239 @default.
- W1979983254 hasRelatedWork W2766407550 @default.
- W1979983254 hasRelatedWork W2899156142 @default.
- W1979983254 hasRelatedWork W2909196548 @default.
- W1979983254 hasRelatedWork W2914466670 @default.
- W1979983254 hasRelatedWork W2922216261 @default.
- W1979983254 hasRelatedWork W2949797464 @default.
- W1979983254 hasRelatedWork W2962852342 @default.
- W1979983254 hasRelatedWork W2964135318 @default.
- W1979983254 hasRelatedWork W2964407608 @default.
- W1979983254 hasRelatedWork W3011835342 @default.
- W1979983254 hasRelatedWork W3089818419 @default.
- W1979983254 hasRelatedWork W3208601917 @default.
- W1979983254 hasRelatedWork W2556093752 @default.
- W1979983254 isParatext "false" @default.
- W1979983254 isRetracted "false" @default.
- W1979983254 magId "1979983254" @default.
- W1979983254 workType "article" @default.