Yet Another Computer Vision Index To Datasets (YACVID) - Details

Stand: 2020-07-05 000000m 08:11:55 - Overview

Attribute Current Content New
Name (Institute + Shorttitle)COCO-Stuff 
Description (include details on usage, files and paper references)COCO-Stuff augments the COCO dataset with pixel-level stuff annotations for 10,000 images. These annotations can be used for scene understanding tasks like semantic segmentation, object detection and image captioning. 
URL Link 
Files (#)10000 
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)semantic segmentation stuff things COCO caption annotation groundtruth benchmark 
Last Changed2020-07-05 
Turing (2.12+3.25=?) :-)