R. Manmatha

visual document understanding (3) encoder-decoder transformer (3) text recognition (3) multimodal learning (3) knowledge distillation (2) attention mechanism (2) visual question answering (2) semantic segmentation (2) multi-modal transformer (2) scene text recognition (2) unsupervised pretraining (2) multi-task learning (1) object detection (1) image segmentation (1) image classification (1) document understanding (1) hierarchical classification (1) named entity recognition (1) image generation (1) question answering (1)