{"id":"2002.06353","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","url":"https://codeofpaper.com/paper/2002.06353","arxiv_url":"https://arxiv.org/abs/2002.06353","published":"2020-02-15","code":"official","best":{"full_name":"microsoft/UniVL","url":"https://github.com/microsoft/UniVL","tier":"official","stars":366,"license":"MIT","framework":null,"language":"Python","last_commit":"2024-07-25T11:07:33"},"most_starred_community":null,"implementations":[{"full_name":"microsoft/UniVL","url":"https://github.com/microsoft/UniVL","tier":"official","stars":366,"license":"MIT","framework":null,"language":"Python","last_commit":"2024-07-25T11:07:33"}],"possible_matches":0}