Mannat Singh

image classification (3) self-supervised learning (3) multi-modal learning (3) representation learning (2) model pretraining (2) transfer learning (2) transformer architecture (2) masked autoencoder (2) convolutional neural network (2) vision transformer (2) visual recognition (2) image captioning (1) multimodal learning (1) weakly supervised learning (1) computer vision (1) text-to-image generation (1) video classification (1) video understanding (1) model architecture (1) audio-visual learning (1)