Statements (29)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:model
|
gptkbp:application |
multimodal tasks
vision tasks language tasks |
gptkbp:arXivID |
2107.14795
|
gptkbp:author |
gptkb:Andrew_Zisserman
gptkb:Oriol_Vinyals gptkb:Andrew_Brock Andrew Jaegle Felix Gimeno |
gptkbp:basedOn |
Perceiver architecture
|
gptkbp:citation |
1000+
|
gptkbp:developedBy |
gptkb:DeepMind
|
gptkbp:handles |
gptkb:DVD
audio images point clouds multimodal data multilabel classification |
https://www.w3.org/2000/01/rdf-schema#label |
Perceiver IO
|
gptkbp:improves |
gptkb:Perceiver
|
gptkbp:input |
variable-sized inputs
|
gptkbp:notablePublication |
Perceiver IO: A General Architecture for Structured Inputs & Outputs
|
gptkbp:openSource |
yes
|
gptkbp:output |
variable-sized outputs
|
gptkbp:publishedIn |
2021
|
gptkbp:uses |
attention mechanism
|
gptkbp:bfsParent |
gptkb:convolutional_neural_network
|
gptkbp:bfsLayer |
5
|