Large-scale object detection, segmentation, and captioning dataset.
COCO is a large-scale object detection, segmentation, and captioning dataset, with these features: Object segmentation, Recognition in context, superpixel stuff segmentation, 330K images (>200K labeled), 1.5 million object instances, 80 object categories, 91 stuff categories, 5 captions per image, and 250,000 people with keypoints.
Additional details available in the PSC Bridges-2 Data Collections User Guide.
|Keywords||object detection, segmentation, captioning|
|Topics||Informatics, Analytics and Information Science|
|Provided By||Pittsburgh Supercomputing Center (PSC)|
|Hosted On||PSC Bridges-2 Regular Memory (Bridges-2 RM)|
|Supported By||XSEDE Help Desk|
|Published By||COCO Consortium Support|