Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:convolutional_neural_network
|
| gptkbp:combines |
gptkb:convolutional_neural_network
recurrent neural network |
| gptkbp:component |
feature extractor
sequence generator |
| gptkbp:featureExtractor |
gptkb:CNN
|
| https://www.w3.org/2000/01/rdf-schema#label |
CNN-RNN
|
| gptkbp:input |
images
video frames |
| gptkbp:output |
gptkb:text
sequences |
| gptkbp:popularizedBy |
2015
Show and Tell model |
| gptkbp:relatedTo |
attention mechanism
encoder-decoder architecture |
| gptkbp:sequenceGenerator |
gptkb:RNN
|
| gptkbp:usedFor |
sequence modeling
video analysis image captioning |
| gptkbp:usedIn |
gptkb:artificial_intelligence
deep learning |
| gptkbp:bfsParent |
gptkb:Show_and_Tell
|
| gptkbp:bfsLayer |
7
|