285 citations · 670 across the 26 of their papers we have counts for
26 papers
Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion
Haogeng Liu, Tao Wang, Jie Cao +2
Denoising Diffusion Probabilistic Models have shown extraordinary ability on various generative tasks. However, their slow inference speed renders them impractical in speech synthe…
MODIFY: Model-driven Face Stylization without Style Images
Yuhe Ding, Jian Liang, Jie Cao +2
Existing face stylization methods always acquire the presence of the target (style) domain during the translation process, which violates privacy regulations and limits their appli…
AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection
Puning Yang, Jian Liang, Jie Cao +1
Out-of-distribution (OOD) detection aims to detect test samples that do not fall into any training in-distribution (ID) classes. Prior efforts focus on regularizing models with ID…
ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data
Jie Cao, Mandi Luo, Junchi Yu +2
Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. To facilitate GAN training, current methods propose to use data-sp…
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification
Jijie Wu, Dongliang Chang, Aneeshan Sain +5
The main challenge for fine-grained few-shot image classification is to learn feature representations with higher inter-class and lower intra-class variations, with a mere few labe…
Vision Transformer with Super Token Sampling
Huaibo Huang, Xiaoqiang Zhou, Jie Cao +2
Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self…
Styleverse: Towards Identity Stylization across Heterogeneous Domains
Jia Li, Jie Cao, JunXian Duan +1
We propose a new challenging task namely IDentity Stylization (IDS) across heterogeneous domains. IDS focuses on stylizing the content identity, rather than completely swapping it…
Improving Subgraph Recognition with Variational Graph Information Bottleneck
Junchi Yu, Jie Cao, Ran He
Subgraph recognition aims at discovering a compressed substructure of a graph that is most informative to the graph property. It can be formulated by optimizing Graph Information B…
SwinIR: Image Restoration Using Swin Transformer
Jingyun Liang, Jiezhang Cao, Guolei Sun +3
Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). Whil…
Video Super-Resolution Transformer
Jiezhang Cao, Yawei Li, Kai Zhang +1
Video super-resolution (VSR), with the aim to restore a high-resolution video from its corresponding low-resolution version, is a spatial-temporal sequence prediction problem. Rece…
PersonalityGate: A General Plug-and-Play GNN Gate to Enhance Cascade Prediction with Personality Recognition Task
Dengcheng Yan, Jie Cao, Yiwen Zhang +1
Cascade prediction estimates the size or the state of a cascade from either microscope or macroscope. It is of paramount importance for understanding the information diffusion proc…
LocalViT: Analyzing Locality in Vision Transformers
Yawei Li, Kai Zhang, Jiezhang Cao +4
The aim of this paper is to study the influence of locality mechanisms in vision transformers. Transformers originated from machine translation and are particularly good at modelli…
ReMix: Towards Image-to-Image Translation with Limited Data
Jie Cao, Luanxuan Hou, Ming-Hsuan Yang +2
Image-to-image (I2I) translation methods based on generative adversarial networks (GANs) typically suffer from overfitting when limited training data is available. In this work, we…
Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation
Luanxuan Hou, Jie Cao, Yuan Zhao +3
We propose an augmented Parallel-Pyramid Net () with feature refinement by dilated bottleneck and attention module. During data preprocessing, we proposed a differentiable…
Reference-guided Face Component Editing
Qiyao Deng, Jie Cao, Yunfan Liu +3
Face portrait editing has achieved great progress in recent years. However, previous methods either 1) operate on pre-defined face attributes, lacking the flexibility of controllin…
Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation
Luanxuan Hou, Jie Cao, Yuan Zhao +4
The target of human pose estimation is to determine body part or joint locations of each person from an image. This is a challenging problems with wide applications. To address thi…
Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
Jie Cao, Huaibo Huang, Yi Li +2
The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models. Existing approaches can use a unified model…
Learning 3D Human Shape and Pose from Dense Body Parts
Hongwen Zhang, Jie Cao, Guo Lu +2
Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred…
PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
Wentao Jiang, Si Liu, Chen Gao +4
In this paper, we address the makeup transfer task, which aims to transfer the makeup from a reference image to a source image. Existing methods have achieved promising progress in…
Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
Jie Cao, Huaibo Huang, Yi Li +3
Despite that the performance of image-to-image translation has been significantly improved by recent progress in generative models, current methods still suffer from severe degrada…
Cross-spectral Face Completion for NIR-VIS Heterogeneous Face Recognition
Ran He, Jie Cao, Lingxiao Song +2
Near infrared-visible (NIR-VIS) heterogeneous face recognition refers to the process of matching NIR to VIS face images. Current heterogeneous methods try to extend VIS face recogn…
Geometry-Aware Face Completion and Editing
Linsen Song, Jie Cao, Linxiao Song +2
Face completion is a challenging generation task because it requires generating visually pleasing new pixels that are semantically consistent with the unmasked face region. This pa…
Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization
Jie Cao, Yibo Hu, Hongwen Zhang +2
Face frontalization refers to the process of synthesizing the frontal view of a face from a given profile. Due to self-occlusion and appearance distortion in the wild, it is extrem…
Load Balanced GANs for Multi-view Face Image Synthesis
Jie Cao, Yibo Hu, Bing Yu +2
Multi-view face synthesis from a single image is an ill-posed problem and often suffers from serious appearance distortion. Producing photo-realistic and identity preserving multi-…