This paper presents a LoRA-free method for stylized image generation tha...
Scene Graph Generation (SGG) aims to structurally and comprehensively
re...
Stickers have become a ubiquitous part of modern-day communication, conv...
As an important and challenging problem in computer vision, PAnoramic
Se...
Despite the success in large-scale text-to-image generation and
text-con...
Recently, diffusion models have achieved great success in image synthesi...
The incredible generative ability of large-scale text-to-image (T2I) mod...
Vision-language alignment learning for video-text retrieval arouses a lo...
Weakly-supervised action localization aims to localize and classify acti...
Action classification has made great progress, but segmenting and recogn...
Despite that convolution neural networks (CNN) have recently demonstrate...
This paper summarizes our endeavors in the past few years in terms of
ex...
Recent blind super-resolution (SR) methods typically consist of two bran...
In this paper, we propose Stochastic Block-ADMM as an approach to train ...
Short video applications like TikTok and Kwai have been a great hit rece...
Recently, several networks that operate directly on point clouds have be...
Understanding and interpreting the decisions made by deep learning model...
We consider the problem of explaining the decisions of deep neural netwo...
Unlike images which are represented in regular dense grids, 3D point clo...
In this paper, we propose a novel explanation module to explain the
pred...