[CVPR2023] LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling

About this video

Advanced · Editorial review · 85% confidence

New channel VLP Tutorial 2024: title sample judged 'whole' (Nearly all uploads are substantive conference-tutorial lectures on vision-language/multimodal ML research presented by e); 2 of 3 sampled transcripts showed teaching, 1 not; titles picked one by one, checked strictly; oEmbed verified.

A 8-minute video from VLP Tutorial 2024: “[CVPR2023] LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling”.

Video by VLP Tutorial 2024, played through YouTube's embedded player.