Yehao Li

image captioning (6) image generation (3) diffusion model (3) long short-term memory (2) video captioning (2) multimodal learning (2) encoder-decoder network (2) transfer learning (2) convolutional neural network (2) autoregressive transformer (1) visual question answering (1) object recognition (1) deformable convolution (1) semantic segmentation (1) embedding space (1) novel object recognition (1) temporal modeling (1) text generation (1) domain adaptation (1) kl divergence (1)