ALIGN: Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
About this video
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by videoALIGN scales visual and vision-language representation learning using noisy text supervision. Research talk explains training methods for large-scale vision models.
Video by Microsoft Research, played through YouTube's embedded player.