Section: New Software and Platforms

HowTo100M

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

Keywords: Computer vision - Video analysis

Functional Description: Implements the method provides the dataset used in the paper HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips (2019), A. Miech, D. Zhukov, J.-B. Alayrac, M. Tapaswi, I. Laptev and J. Sivic, in Proc. ICCV'19, Seoul, South Korea.

• Contact: Ivan Laptev

• URL: https://www.di.ens.fr/willow/research/howto100m/