- a
Flickr8k Dataset
- academictorrents.com
bittorrentUpdated Mar 9, 2019
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteMicah Hodosh and Peter Young and Julia Hockenmaier (2019). Flickr8k Dataset [Dataset]. https://academictorrents.com/details/9dea07ba660a722ae1008c4c8afdd303b6f6e53bbittorrent(1117760547)Available download formatsDataset updatedMar 9, 2019Dataset authored and provided byMicah Hodosh and Peter Young and Julia HockenmaierLicensehttps://academictorrents.com/nolicensespecifiedhttps://academictorrents.com/nolicensespecified
Description8,000 photos and up to 5 captions for each photo. We introduce a new benchmark collection for sentence-based image description and search, consisting of 8,000 images that are each paired with five different captions which provide clear descriptions of the salient entities and events. … The images were chosen from six different Flickr groups, and tend not to contain any well-known people or locations, but were manually selected to depict a variety of scenes and situations ## Citation Hodosh, Micah, Peter Young, and Julia Hockenmaier. "Framing image description as a ranking task: Data, models and evaluation metrics." Journal of Artificial Intelligence Research 47 (2013): 853-899.
- O
Flickr8k
- opendatalab.com
zipUpdated Mar 24, 2023ShareFacebookTwitterEmailClick to copy linkLink copiedCiteUniversity of Illinois Urbana-Champaign (2023). Flickr8k [Dataset]. https://opendatalab.com/OpenDataLab/Flickr8kzipAvailable download formatsDataset updatedMar 24, 2023Dataset provided byUniversity of Illinois Urbana-ChampaignLicensehttp://www.flickr.com/terms.gne?legacy=1http://www.flickr.com/terms.gne?legacy=1
DescriptionA new benchmark collection for sentence-based image description and search, consisting of 8,000 images that are each paired with five different captions which provide clear descriptions of the salient entities and events. … The images were chosen from six different Flickr groups, and tend not to contain any well-known people or locations, but were manually selected to depict a variety of scenes and situations
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailhttps://academictorrents.com/nolicensespecifiedhttps://academictorrents.com/nolicensespecified
8,000 photos and up to 5 captions for each photo. We introduce a new benchmark collection for sentence-based image description and search, consisting of 8,000 images that are each paired with five different captions which provide clear descriptions of the salient entities and events. … The images were chosen from six different Flickr groups, and tend not to contain any well-known people or locations, but were manually selected to depict a variety of scenes and situations ## Citation Hodosh, Micah, Peter Young, and Julia Hockenmaier. "Framing image description as a ranking task: Data, models and evaluation metrics." Journal of Artificial Intelligence Research 47 (2013): 853-899.