cocodataset.org Open in urlscan Pro
185.199.110.153  Public Scan

Submitted URL: http://cocodataset.org/
Effective URL: https://cocodataset.org/
Submission: On June 30 via api from US — Scanned from DE

Form analysis 0 forms found in the DOM

Text Content

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
   *   Results Format
   *   Test Guidelines
   *   Upload Results
   * 
   * Evaluate:
   *   Detection
   *   Keypoints
   *   Stuff
   *   Panoptic
   *   DensePose
   *   Captions
   * 
   * Leaderboards:
   *   Detection
   *   Keypoints
   *   Stuff
   *   Panoptic
   *   Captions


NEWS

 * We are pleased to announce the LVIS 2021 Challenge and Workshop to be held at
   ICCV.
 * Please note that there will not be a COCO 2021 Challenge, instead, we
   encourage people to participate in the LVIS 2021 Challenge.
 * We have partnered with the team behind the open-source tool FiftyOne to make
   it easier to download, visualize, and evaluate COCO
 * FiftyOne is an open-source tool facilitating visualization and access to COCO
   data resources and serves as an evaluation tool for model analysis on COCO.
   
   
   


WHAT IS COCO?

COCO is a large-scale object detection, segmentation, and captioning dataset.
COCO has several 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
 * 250,000 people with keypoints


COLLABORATORS

Tsung-Yi Lin Google Brain
Genevieve Patterson MSR, Trash TV
Matteo R. Ronchi Caltech
Yin Cui Google
Michael Maire TTI-Chicago
Serge Belongie Cornell Tech
Lubomir Bourdev WaveOne, Inc.
Ross Girshick FAIR
James Hays Georgia Tech
Pietro Perona Caltech
Deva Ramanan CMU
Larry Zitnick FAIR
Piotr Dollár FAIR



SPONSORS





















































Github Page Source Terms of Use