Driven by the scalable diffusion models trained on large-scale datasets text-to-image
synthesis methods have shown compelling results. However these models still fail to …

Human matting is a foundation task in image and video processing where human
foreground pixels are extracted from the input. Prior works either improve the accuracy by …

Screening similar but non-target images in text-based image retrieval is crucial for
pinpointing the user's desired images accurately. However, conventional methods mainly …