Pengyang Ling

semantic segmentation (3) diffusion model (3) image restoration (3) temporal consistency (2) self-supervised learning (2) image editing (1) autonomous driving (1) domain adaptation (1) attention mechanism (1) text-to-video generation (1) domain generalization (1) multi-modal learning (1) computer vision (1) image denoising (1) foundation model (1) feature extraction (1) parameter-efficient fine-tuning (1) vision foundation model (1) iterative optimization (1) zero-shot learning (1)