Amir Bar

action recognition (3) video understanding (2) representation learning (2) video generation (2) self-supervised learning (2) cross-modal learning (1) few-shot learning (1) zero-shot learning (1) object detection (1) vision transformer (1) unsupervised pretraining (1) multimodal learning (1) visual reasoning (1) test-time adaptation (1) pose estimation (1) semi-supervised learning (1) image-to-image translation (1) semantic consistency (1) video transformer (1) contrastive learning (1)