Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Title
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Authors
Keywords
Computer vision, Dataset, Image, Scene graph, Question answering, Objects, Attributes, Relationships, Knowledge, Language, Crowdsourcing
Journal
INTERNATIONAL JOURNAL OF COMPUTER VISION
Volume 123, Issue 1, Pages 32-73
Publisher
Springer Nature
Online
2017-02-06
DOI
10.1007/s11263-016-0981-7

Ask authors/readers for more resources

Reprint

Contact the author

Find Funding. Review Successful Grants.

Explore over 25,000 new funding opportunities and over 6,000,000 successful grants.

Explore

Discover Peeref hubs

Discuss science. Find collaborators. Network.

Join a conversation