VideoCLIP: Contrastive Pre-Training for Zero-Shot Video-Text Understanding

1 points by LuisMondragon 4 years ago | 2 comments

sharemywin 4 years ago |

Not sure if this is the same thing?

LuisMondragon 4 years ago | |

Not the same. CLIP is trained with pairs of images and texts, whereas VideoCLIP uses pairs of videos and texts.

sharemywin 4 years ago |

Not sure if this is the same thing?

LuisMondragon 4 years ago | |

Not the same. CLIP is trained with pairs of images and texts, whereas VideoCLIP uses pairs of videos and texts.