Dimosthenis Karatzas

multimodal learning (6) image captioning (3) visual reasoning (3) text recognition (3) visual question answering (3) scene text (3) self-supervised learning (2) image classification (2) handwritten text recognition (2) multi-modal reasoning (2) image retrieval (2) named entity recognition (2) cross-modal retrieval (2) fine-grained classification (2) social media analysis (1) data augmentation (1) transfer learning (1) feature learning (1) embedding learning (1) document understanding (1)