Shimon Ullman

vision language model (3) adaptive sampling (2) zero-shot learning (2) visual question answering (2) multi-task learning (1) few-shot learning (1) image segmentation (1) human analysis (1) vision transformer (1) feature extraction (1) object recognition (1) object detection (1) spectral clustering (1) self-supervised learning (1) in-context learning (1) weakly supervised learning (1) feature embedding (1) multi-modal learning (1) human pose estimation (1) action recognition (1)