120 citations · 310 across the 27 of their papers we have counts for
27 papers
Supervision-by-Hallucination-and-Transfer: A Weakly-Supervised Approach for Robust and Precise Facial Landmark Detection
Jun Wan, Yuanzhi Yao, Zhihui Lai +3
High-precision facial landmark detection (FLD) relies on high-resolution deep feature representations. However, low-resolution face images or the compression (via pooling or stride…
GPTFace: Generative Pre-training of Facial-Linguistic Transformer by Span Masking and Weakly Correlated Text-image Data
Yudong Li, Hao Li, Xianxu Hou +1
Compared to the prosperity of pre-training models in natural image understanding, the research on large-scale pre-training models for facial knowledge learning is still limited. Cu…
LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement
Xu Wu, Zhihui Lai, Xianxu Hou +3
Low-light image enhancement (LLIE) aims to improve illumination while preserving high-quality color and texture. However, existing methods often fail to extract reliable feature re…
DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing
Xiaoqin Wang, Xianxu Hou, Meidan Ding +4
Face parsing aims to segment facial images into key components such as eyes, lips, and eyebrows. While existing methods rely on dense pixel-level annotations, such annotations are…
FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs
Xiaoqin Wang, Xusen Ma, Xianxu Hou +6
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely…
Low-Light Enhancement Effect on Classification and Detection: An Empirical Study
Xu Wu, Zhihui Lai, Zhou Jie +4
Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these ima…
Dynamic data sampler for cross-language transfer learning in large language models
Yudong Li, Yuhao Feng, Wen Zhou +4
Large Language Models (LLMs) have gained significant attention in the field of natural language processing (NLP) due to their wide range of applications. However, training LLMs for…
CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement
Xu Wu, XianXu Hou, Zhihui Lai +4
Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness de…
DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation
Feilong Tang, Qiming Huang, Jinfeng Wang +3
Transformer-based models have been widely demonstrated to be successful in computer vision tasks by modelling long-range dependencies and capturing global representations. However,…
Cross Language Image Matching for Weakly Supervised Semantic Segmentation
Jinheng Xie, Xianxu Hou, Kai Ye +1
It has been widely known that CAM (Class Activation Map) usually only activates discriminative object regions and falsely includes lots of object-related backgrounds. As only a fix…
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
Jinheng Xie, Jianfeng Xiang, Junliang Chen +3
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), s…
FEAT: Face Editing with Attention
Xianxu Hou, Linlin Shen, Or Patashnik +2
Employing the latent space of pretrained generators has recently been shown to be an effective means for GAN-based face manipulation. The success of this approach heavily relies on…
Manifold-preserved GANs
Haozhe Liu, Hanbang Liang, Xianxu Hou +3
Generative Adversarial Networks (GANs) have been widely adopted in various fields. However, existing GANs generally are not able to preserve the manifold of data space, mainly due…
VHS to HDTV Video Translation using Multi-task Adversarial Learning
Hongming Luo, Guangsen Liao, Xianxu Hou +3
There are large amount of valuable video archives in Video Home System (VHS) format. However, due to the analog nature, their quality is often poor. Compared to High-definition tel…
GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing
Xianxu Hou, Xiaokang Zhang, Linlin Shen +2
Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there still lac…
Robust Facial Landmark Detection by Cross-order Cross-semantic Deep Network
Jun Wan, Zhihui Lai, Linlin Shen +4
Recently, convolutional neural networks (CNNs)-based facial landmark detection methods have achieved great success. However, most of existing CNN-based facial landmark detection me…
Class-Aware Domain Adaptation for Improving Adversarial Robustness
Xianxu Hou, Jingxin Liu, Bolei Xu +3
Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally desi…
Dual Adaptive Pyramid Network for Cross-Stain Histopathology Image Segmentation
Xianxu Hou, Jingxin Liu, Bolei Xu +6
Supervised semantic segmentation normally assumes the test data being in a similar data domain as the training data. However, in practice, the domain mismatch between the training…
Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
Xianxu Hou, Ke Sun, Linlin Shen +1
We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output…
Learning Deep Image Priors for Blind Image Denoising
Xianxu Hou, Hongming Luo, Jingxin Liu +5
Image denoising is the process of removing noise from noisy images, which is an image domain transferring task, i.e., from a single or several noise level domains to a photo-realis…
Look, Investigate, and Classify: A Deep Hybrid Attention Method for Breast Cancer Classification
Bolei Xu, Jingxin Liu, Xianxu Hou +6
One issue with computer based histopathology image analysis is that the size of the raw image is usually very large. Taking the raw image as input to the deep learning model would…
End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks
Wei Liu, Xianxu Hou, Jiang Duan +1
Single image defogging is a classical and challenging problem in computer vision. Existing methods towards this problem mainly include handcrafted priors based methods that rely on…
Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks
Xianxu Hou, Guoping Qiu
In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contribution…
Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping
Xianxu Hou, Jiang Duan, Guoping Qiu
Building on crucial insights into the determining factors of the visual integrity of an image and the property of deep convolutional neural network (CNN), we have developed the Dee…