Yinan He

video understanding (4) zero-shot learning (2) large language model (2) diffusion model (2) benchmark evaluation (2) vision transformer (2) masked autoencoder (2) image restoration (1) multi-task learning (1) semantic segmentation (1) video classification (1) self-supervised learning (1) weakly supervised learning (1) in-context learning (1) video recognition (1) video generation (1) multi-modal learning (1) multimodal learning (1) question answering (1) temporal reasoning (1)