Representation Learning Contrastive Cross-View Mutual Information Maximization public – 2 min read What is CV-MIM? CV-MIM stands for Contrastive Cross-View Mutual Information Maximization. This is a method that is used for representation… Apr 23, 2023 Devin Schumacher
Representation Learning Transformers Vision and Language Pre-Trained Models Vision-and-Language BERT public – 2 min read Vision-and-Language BERT, also known as ViLBERT, is an innovative model that combines both natural language and image content to learn… Apr 23, 2023 Devin Schumacher
Representation Learning Transformers VideoBERT public – 2 min read What is VideoBERT? VideoBERT is a machine learning model that is used to learn a joint visual-linguistic representation for video.… Apr 23, 2023 Devin Schumacher