51 citations · 56 across the 10 of their papers we have counts for
10 papers · 1 filter
Pretrained Diffusion Models Are Inherently Skipped-Step Samplers
Wenju Xu
Diffusion models have been achieving state-of-the-art results across various generation tasks. However, a notable drawback is their sequential generation process, requiring long-se…
Domain Generalizable Portrait Style Transfer
Xinbo Wang, Wenju Xu, Qing Zhang +1
This paper presents a portrait style transfer method that generalizes well to various different domains while enabling high-quality semantic-aligned stylization on regions includin…
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
Tianxiao Zhang, Wenju Xu, Bo Luo +1
The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various comp…
Disentangled Representation Learning for Controllable Person Image Generation
Wenju Xu, Chengjiang Long, Yongwei Nie +1
In this paper, we propose a novel framework named DRL-CPG to learn disentangled latent representation for controllable person image generation, which can produce realistic person i…
Learning Dynamic Style Kernels for Artistic Style Transfer
Wenju Xu, Chengjiang Long, Yongwei Nie
Arbitrary style transfer has been demonstrated to be efficient in artistic image generation. Previous methods either globally modulate the content feature ignoring local details, o…
Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition
Zhijun Zhai, Jianhui Zhao, Chengjiang Long +3
Micro-expressions are spontaneous, rapid and subtle facial movements that can neither be forged nor suppressed. They are very important nonverbal communication clues, but are trans…
Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets
Xiangyu Chen, Ying Qin, Wenju Xu +3
Vision Transformers have attracted a lot of attention recently since the successful implementation of Vision Transformer (ViT) on vision tasks. With vision Transformers, specifical…
A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation
Wenju Xu, Guanghui Wang
Recent image-to-image translation models have shown great success in mapping local textures between two domains. Existing approaches rely on a cycle-consistency constraint that sup…
Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
Wenju Xu, Yuanwei Wu, Wenchi Ma +1
In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The propose…
Stacked Wasserstein Autoencoder
Wenju Xu, Shawn Keshmiri, Guanghui Wang
Approximating distributions over complicated manifolds, such as natural images, are conceptually attractive. The deep latent variable model, trained using variational autoencoders…