Many applications can benefit from personalized image generation models,...
This paper proposes a method for generating images of customized objects...
Existing machine learning models demonstrate excellent performance in im...
Recent text-to-image generation models like DreamBooth have made remarka...
Test-time adaptation (TTA) is a technique used to reduce distribution ga...
Reconstructing multi-human body mesh from a single monocular image is an...
We present Mobile Video Networks (MoViNets), a family of computation and...
Object frequencies in daily scenes follow a long-tailed distribution. Ma...
This paper is concerned with ranking many pre-trained deep neural networ...
We study how to leverage Web images to augment human-curated object dete...
We study how to train a student deep neural network for visual recogniti...
We propose a new task towards more practical application for image gener...
There is an increasing number of pre-trained deep neural network models....
Graph neural networks (GNNs) are widely used in many applications. Howev...
Powerful adversarial attack methods are vital for understanding how to
c...
Real-time traffic volume inference is key to an intelligent city. It is ...
There is a growing interest in designing models that can deal with image...
Despite the success of deep learning for static image understanding, it
...
The large volume of video content and high viewing frequency demand auto...
Rich and dense human labeled datasets are among the main enabling factor...
This paper describes our solution for the video recognition task of
Acti...
This paper describes our solution for the video recognition task of the
...