Statements (19)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:dataset
|
gptkbp:annotationType |
five captions per image
|
gptkbp:contains |
158,915 captions
31,783 images |
gptkbp:hasSubgroup |
gptkb:Flickr30k_Entities
|
https://www.w3.org/2000/01/rdf-schema#label |
Flickr30k
|
gptkbp:language |
English
|
gptkbp:license |
non-commercial research
|
gptkbp:relatedTo |
gptkb:Flickr8k
gptkb:MSCOCO |
gptkbp:releaseYear |
gptkb:University_of_Illinois_at_Urbana-Champaign
2014 |
gptkbp:source |
gptkb:Flickr
|
gptkbp:usedFor |
natural language processing research
computer vision research image captioning |
gptkbp:usedIn |
benchmarking image captioning models
|
gptkbp:bfsParent |
gptkb:CLIP
|
gptkbp:bfsLayer |
6
|