ViTT Dense Video Description Dataset
Date
3 years ago
Publish URL
Paper URL
License
Other
ViTT stands for Video Timeline Tags, which consists of 8,169 videos with manually generated segment-level annotations. Among them, 5,840 videos are annotated once, and the rest are annotated twice or more. A total of 12,461 sets of annotations have been released for this dataset. The videos in this dataset come from the Youtube-8M dataset.
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