The emergence of vision-language models (VLMs), such as CLIP, has spurre...
Controllable video generation has gained significant attention in recent...
Deep neural networks have played a crucial part in many critical domains...
The growth in social media has exacerbated the threat of fake news to
in...
The growing threats of deepfakes to society and cybersecurity have raise...
Unsupervised domain adaptation (UDA) has witnessed remarkable advancemen...
With the growing interest in pretrained vision-language models like CLIP...
Test-time adaptation (TTA) is a technique aimed at enhancing the
general...
The one-epoch overfitting phenomenon has been widely observed in industr...
Machine learning methods strive to acquire a robust model during trainin...
Out-of-distribution (OOD) generalization is an important issue for Graph...
Domain generalization (DG) tends to alleviate the poor generalization
ca...
Out-of-distribution (OOD) detection is a crucial aspect of deploying mac...
Model adaptation aims at solving the domain transfer problem under the
c...
Zero-shot learning (ZSL) aims to recognize unseen classes by generalizin...
Existing face stylization methods always acquire the presence of the tar...
Existing cross-domain keypoint detection methods always require accessin...
One major issue that challenges person re-identification (Re-ID) is the
...
An off-the-shelf model as a commercial service could be stolen by model
...
Federated learning aims to train models collaboratively across different...
In this paper, we present NUWA-Infinity, a generative model for infinite...
This paper focuses on out-of-distribution generalization on graphs where...
Heterogeneous Face Recognition (HFR) aims to match faces across differen...
In the field of car evaluation, more and more netizens choose to express...
Recently most successful image synthesis models are multi stage process ...
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a
l...
Rich user behavior information is of great importance for capturing and
...
Domain generalization (DG) is essentially an out-of-distribution problem...
Batch normalization (BN) is widely used in modern deep neural networks, ...
Domain generalizable (DG) person re-identification (ReID) aims to test a...
Learning to reject unknown samples (not present in the source classes) i...
Class Incremental Learning (CIL) aims at learning a multi-class classifi...
Domain adaptation (DA) attempts to transfer the knowledge from a labeled...
In this paper, we focus on learning effective entity matching models ove...
This paper presents a unified multimodal pre-trained model called NÜWA t...
Federated learning (FL) has gain growing interests for its capability of...
In this paper, we focus on effective learning over a collaborative resea...
Domain adaptation (DA) paves the way for label annotation and dataset bi...
Existing person re-identification (re-id) methods are stuck when deploye...
The task of video-based commonsense captioning aims to generate event-wi...
Benefited from considerable pixel-level annotations collected from a spe...
A central challenge in training classification models in the real-world
...
To alleviate the burden of labeling, unsupervised domain adaptation (UDA...
Towards better unsupervised domain adaptation (UDA). Recently, researche...
Contrastive self-supervised learning (CSL) leverages unlabeled data to t...
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a
r...
Unsupervised domain adaptation challenges the problem of transferring
kn...
Lane-changing is an important driving behavior and unreasonable lane cha...
Recent studies show that crowd-sourced Natural Language Inference (NLI)
...
Finite Mixture Regression (FMR) refers to the mixture modeling scheme wh...