Statements (30)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:dataset
|
| gptkbp:annotationType |
bounding boxes
coreference chains phrase-to-region correspondences |
| gptkbp:availableOn |
https://bryanplummer.com/Flickr30kEntities/
|
| gptkbp:citation |
Plummer et al., 2015
|
| gptkbp:contains |
entity-level annotations
image-sentence correspondences |
| gptkbp:createdBy |
gptkb:Svetlana_Lazebnik
Bryan A. Plummer Chris M. Cervantes Juan C. Caicedo Julia Hockenmaier Liwei Wang |
| gptkbp:language |
English
|
| gptkbp:license |
research only
|
| gptkbp:numberOfCaptionsPerImage |
5
|
| gptkbp:numberOfRooms |
31,783
|
| gptkbp:partOf |
gptkb:Flickr30k
|
| gptkbp:publishedIn |
gptkb:Transactions_of_the_Association_for_Computational_Linguistics
|
| gptkbp:relatedTo |
gptkb:Flickr8k
gptkb:MSCOCO |
| gptkbp:releaseYear |
2015
|
| gptkbp:usedFor |
image captioning
grounding natural language in images phrase localization vision-language research |
| gptkbp:bfsParent |
gptkb:Flickr30k
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Flickr30k Entities
|