Ronghang Hu

multimodal learning (4) transformer architecture (3) object detection (3) visual grounding (2) image classification (2) vision-language navigation (2) semantic segmentation (2) vision language model (2) multi-modal learning (2) visual question answering (2) vision-and-language navigation (2) transfer learning (2) convolutional neural network (2) cross-modal learning (1) data augmentation (1) self-supervised learning (1) multi-task learning (1) instruction following (1) instance segmentation (1) object localization (1)