Semantic segmentation is a computer vision task that associates a label ...
Submodular maximization has found extensive applications in various doma...
Recently, text-to-image generation has exhibited remarkable advancements...
The large-scale visual pretraining has significantly improve the perform...
Recently, text-guided 3D generative methods have made remarkable advance...
Personalized text-to-image generation using diffusion models has recentl...
The recent upsurge in pre-trained large models (e.g. GPT-4) has swept ac...
Large language models (LLMs) have shown remarkable capabilities across a...
The tremendous success of large models trained on extensive datasets
dem...
We propose SimSC, a remarkably simple framework, to address the problem ...
Interpreting remote sensing imagery enables numerous downstream applicat...
We tackle the issue of generalized category discovery (GCD). GCD conside...
Existing machine learning models demonstrate excellent performance in im...
Recently, the zero-shot semantic segmentation problem has attracted
incr...
We present DreamAvatar, a text-and-shape guided framework for generating...
We address the problem of clothed human reconstruction from a single ima...
Compositional zero-shot learning (CZSL) aims at learning visual concepts...
In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method ...
Masked Image Modeling (MIM) achieves outstanding success in self-supervi...
Adder Neural Network (AdderNet) provides a new way for developing
energy...
The combination of transformers and masked image modeling (MIM) pre-trai...
Light-weight convolutional neural networks (CNNs) are specially designed...
Humans possess an innate ability to identify and differentiate instances...
Network architecture plays a key role in the deep learning-based compute...
Novel Class Discovery (NCD) is a learning paradigm, where a machine lear...
This paper addresses the problem of single view 3D human reconstruction....
Excellent performance has been achieved on instance segmentation but the...
Deploying convolutional neural networks (CNNs) on mobile devices is diff...
In this paper, we consider a highly general image recognition setting
wh...
Transformer networks have achieved great progress for computer vision ta...
Different from traditional convolutional neural network (CNN) and vision...
The ability to identify whether or not a test sample belongs to one of t...
Quantitative estimation of the acute ischemic infarct is crucial to impr...
This paper introduces versatile filters to construct efficient convoluti...
This paper presents Hire-MLP, a simple yet competitive vision MLP
archit...
Recent studies on deep convolutional neural networks present a simple
pa...
The combination of a small unmanned ground vehicle (UGV) and a large unm...
Vision transformers have been successfully applied to image recognition ...
We consider the revenue maximization problem in social advertising, wher...
In this paper, we tackle the problem of novel visual category discovery,...
This paper studies the model compression problem of vision transformers....
Transformer models have achieved great progress on computer vision tasks...
We tackle the problem of discovering novel classes in an image collectio...
Recently, transformer has achieved remarkable performance on a variety o...
Submodular optimization has numerous applications such as crowdsourcing ...
Deep convolutional neural networks (CNNs) are often of sophisticated des...
This paper studies the efficiency problem for visual transformers by
exc...
This paper addresses the problem of reconstructing the surface shape of
...
This paper studies the problem of novel category discovery on single- an...
Visual transformer has achieved competitive performance on a variety of
...