Who's Waldo Image Captioning Dataset
Date
3 years ago
Organization
Publish URL
Paper URL
License
Other
Who's Waldo contains 270k image-text pairs and automatically annotates the alignment between the mentioned people and their corresponding visual regions.
The Who's Waldo dataset is constructed from freely licensed images and descriptions from Wikimedia Commons. Who's Waldo is a benchmark dataset for human-centric visual grounding.
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.
AI Co-coding
Ready-to-use GPUs
Best Pricing
Hyper Newsletters
Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp