|
gptkbp:instance_of
|
gptkb:Data
|
|
gptkbp:annotation_types
|
bounding boxes
segmentation masks
keypoints
|
|
gptkbp:categories
|
80
|
|
gptkbp:collaborator
|
universities
research institutions
industry partners
|
|
gptkbp:collection
|
crowdsourcing
manual annotation
|
|
gptkbp:contains
|
annotations
images
|
|
gptkbp:contribution
|
benchmarking algorithms
training models
evaluation of performance
advancement of AI
|
|
gptkbp:created_by
|
gptkb:Microsoft
|
|
gptkbp:data_type
|
real-world images
|
|
gptkbp:evaluates
|
mean Average Precision (m AP)
|
|
gptkbp:evaluation_challenge
|
gptkb:COCO_Detection_Challenge
COCO Captioning Challenge
COCO Keypoint Challenge
|
|
gptkbp:features
|
instance segmentation
object localization
keypoint detection
|
|
gptkbp:has_artwork
|
330,000
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
COCO 2017
|
|
gptkbp:image_format
|
gptkb:JPEG
|
|
gptkbp:impact
|
machine learning applications
image processing techniques
computer vision research
|
|
gptkbp:is_divided_into
|
gptkb:test_subjects
gptkb:train
val
|
|
gptkbp:is_documented_in
|
gptkb:JSON
|
|
gptkbp:is_popular_in
|
computer vision community
|
|
gptkbp:license
|
gptkb:Creative_Commons_Attribution_4.0_International_License
|
|
gptkbp:predecessor
|
gptkb:COCO_2016
|
|
gptkbp:provides_information_on
|
publicly available images
user-contributed images
|
|
gptkbp:related_to
|
gptkb:Open_Images_Dataset
gptkb:Image_Net
gptkb:Pascal_VOC
|
|
gptkbp:release_date
|
gptkb:2017
|
|
gptkbp:resolution
|
varies
varied
|
|
gptkbp:successor
|
gptkb:COCO_2018
|
|
gptkbp:supports
|
deep learning
|
|
gptkbp:target_audience
|
gptkb:students
gptkb:developers
gptkb:researchers
|
|
gptkbp:used_for
|
object detection
image segmentation
captioning
|
|
gptkbp:website
|
cocodataset.org
|
|
gptkbp:bfsParent
|
gptkb:Swin_Transformer
|
|
gptkbp:bfsLayer
|
5
|