Roei Herzig

action recognition (5) multimodal learning (4) zero-shot learning (4) few-shot learning (4) vision-language model (4) large multimodal model (4) scene graph (4) video understanding (3) compositional reasoning (3) object detection (3) vision language model (3) self-supervised learning (3) visual reasoning (2) representation learning (2) video transformer (2) transfer learning (1) domain generalization (1) image segmentation (1) semantic segmentation (1) image classification (1)