Statements (31)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:academic_journal
|
gptkbp:arXivID |
1502.03044
|
gptkbp:author |
gptkb:Aaron_Courville
gptkb:Yoshua_Bengio gptkb:Ruslan_Salakhutdinov gptkb:Jimmy_Ba gptkb:Kyunghyun_Cho gptkb:Richard_Zemel Kelvin Xu Ryan Kiros |
gptkbp:citation |
over 8000
|
gptkbp:field |
computer vision
deep learning image captioning |
gptkbp:fullTitle |
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
|
https://www.w3.org/2000/01/rdf-schema#label |
Show, Attend and Tell
|
gptkbp:influenced |
subsequent research in attention models
|
gptkbp:openAccess |
yes
|
gptkbp:proposedBy |
visual attention mechanism
neural image caption generation |
gptkbp:publicationYear |
2015
|
gptkbp:publishedIn |
gptkb:International_Conference_on_Machine_Learning
|
gptkbp:trainer |
gptkb:Flickr30k
gptkb:Flickr8k gptkb:MSCOCO |
gptkbp:url |
https://arxiv.org/abs/1502.03044
|
gptkbp:uses |
convolutional neural networks
attention mechanism recurrent neural networks |
gptkbp:bfsParent |
gptkb:Show_and_Tell
|
gptkbp:bfsLayer |
7
|