Yale Song

video understanding (8) multimodal learning (5) multiple instance learning (3) transfer learning (3) mutual information (2) recurrent neural network (2) generative adversarial network (2) action recognition (2) unsupervised learning (2) contrastive learning (2) domain adaptation (2) representation learning (2) activity recognition (2) video summarization (2) video generation (2) vision transformer (2) self-supervised learning (2) attention mechanism (2) egocentric vision (2) multimodal large language model (2)