HyperAIHyperAI

Command Palette

Search for a command to run...

LSVTD Video Text Understanding Dataset

Date

3 years ago

Organization

Zhejiang University

Paper URL

arxiv.org

License

Other

Join the Discord Community
Featured Image

LSVTD stands for large-scale video text dataset, which contains 100 videos from 21 natural scenes. The dataset covers a wide range of 13 indoor (such as bookstores, shopping malls) and 9 outdoor scenes, and its diversity is more than 3 times that of the IC15 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
Get Started

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
LSVTD Video Text Understanding Dataset | Datasets | HyperAI