サクサク読めて、アプリ限定の機能も多数!
トップへ戻る
ノーベル賞
mscoco.org
info@cocodataset.org Home People Dataset Overview Explore Download External Terms of Use Tasks Detection 2020 Keypoints 2020 Panoptic 2020 Detection 2019 Keypoints 2019 Stuff 2019 Panoptic 2019 Detection 2018 Keypoints 2018 Stuff 2018 Panoptic 2018 Detection 2017 Keypoints 2017 Stuff 2017 Detection 2016 Keypoints 2016 Detection 2015 Captioning 2015 Evaluate Participate: Data Format Results Format
info@cocodataset.org Home People Dataset Overview Explore Download External Terms of Use Tasks Detection 2020 Keypoints 2020 Panoptic 2020 DensePose 2020 Detection 2019 Keypoints 2019 Stuff 2019 Panoptic 2019 Detection 2018 Keypoints 2018 Stuff 2018 Panoptic 2018 Detection 2017 Keypoints 2017 Stuff 2017 Detection 2016 Keypoints 2016 Detection 2015 Captioning 2015 Evaluate Participate: Data Format
What is COCO? COCO is a new image recognition, segmentation, and captioning dataset. COCO has several features: Object segmentation Recognition in Context Multiple objects per image More than 300,000 images More than 2 Million instances 80 object categories 5 captions per image Keypoints on 100,000 people Tsung-Yi Lin Cornell Tech Genevieve Patterson MSR Matteo Ruggero Ronchi Caltech Yin Cui Corne
このページを最初にブックマークしてみませんか?
『COCO - Common Objects in Context』の新着エントリーを見る
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く