Xiyang Dai

object detection (10) vision transformer (6) convolutional neural network (5) attention mechanism (4) zero-shot learning (4) image classification (4) semantic segmentation (4) video understanding (3) efficient computing (3) contrastive learning (3) semantic alignment (2) self-attention mechanism (2) image captioning (2) transfer learning (2) multimodal learning (2) vision-language alignment (2) self-supervised learning (2) visual question answering (2) weakly supervised learning (2) model architecture (2)