Chenxi Xie

high resolution (2) image segmentation (2) video editing (2) diffusion model (2) instruction following (1) saliency detection (1) convolutional neural network (1) classifier-free guidance (1) text-to-video generation (1) temporal consistency (1) rectified flow (1) encoder-decoder architecture (1) pyramid network (1) image-to-video generation (1) mask annotation (1) fine-grained editing (1) high-resolution segmentation (1) transformer architecture (1) image segmentation benchmark (1) semantic segmentation (1)