Deep Visual-Semantic Alignments for Generating Image Descriptions
GPTKB entity
Statements (16)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:academic_journal
|
gptkbp:author |
gptkb:Andrej_Karpathy
gptkb:Li_Fei-Fei |
gptkbp:citation |
over 5000
|
gptkbp:field |
computer vision
natural language processing |
gptkbp:focusesOn |
image captioning
|
gptkbp:hasMethod |
aligning visual and semantic information
|
https://www.w3.org/2000/01/rdf-schema#label |
Deep Visual-Semantic Alignments for Generating Image Descriptions
|
gptkbp:publicationYear |
2015
|
gptkbp:publishedIn |
gptkb:CVPR
|
gptkbp:url |
https://cs.stanford.edu/people/karpathy/deepimagesent/
|
gptkbp:uses |
convolutional neural networks
bidirectional recurrent neural networks |
gptkbp:bfsParent |
gptkb:Andrej_Karpathy
|
gptkbp:bfsLayer |
7
|