no code implementations • 28 Apr 2024 • Ruitao Xie, Connor Qiu, Guoping Qiu
This paper explores how artificial intelligence (AI) technology can contribute to achieve progress on good health and well-being, one of the United Nations' 17 Sustainable Development Goals.
1 code implementation • 26 Jan 2024 • Zhenyu Bao, Guibiao Liao, Zhongyuan Zhao, Kanglin Liu, Qing Li, Guoping Qiu
One of the innovative features of Du-NeRF is that it decouples a view-independent component from the density field and uses it as a label to supervise the learning process of the SDF field.
1 code implementation • 23 Jan 2024 • Zhongyuan Zhao, Zhenyu Bao, Qing Li, Guoping Qiu, Kanglin Liu
In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering.
no code implementations • 27 Sep 2023 • Xujie Kang, Kanglin Liu, Jiang Duan, Yuanhao Gong, Guoping Qiu
Given a new $6DoF$ camera pose in an indoor environment, we study the challenging problem of predicting the view from that pose based on a set of reference RGBD views.
1 code implementation • 24 May 2023 • Zehong Zhou, Fei Zhou, Guoping Qiu
Blind image quality assessment (BIQA) is a challenging problem with important real-world applications.
1 code implementation • 25 Nov 2022 • Zhipeng Zhong, Fei Zhou, Guoping Qiu
Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS.
no code implementations • 13 Oct 2022 • Zhendi Gong, Andrew P. French, Guoping Qiu, Xin Chen
We compared our method with many other state-of-the-art hybrid CNN and Transformer segmentation models on binary and multiple class image segmentation tasks using several public medical image datasets, including skin lesion, polyp, cell and brain tissue.
1 code implementation • 26 Sep 2022 • Qinglin Li, Guoping Qiu
Performing our method on a variety of datasets from remote sensing, we show that our method can be effectively applied to remote--sensing images.
1 code implementation • 18 Aug 2022 • Hongming Luo, Fei Zhou, Kin-Man Lam, Guoping Qiu
This paper presents a new general video restoration framework for the restoration of user videos shared on social media platforms.
no code implementations • 16 Jul 2021 • Kanglin Liu, Gaofeng Cao, Jiang Duan, Guoping Qiu
Single-image HDR reconstruction or inverse tone mapping (iTM) is a challenging task.
1 code implementation • 13 Jul 2021 • Qinglin Li, Bin Li, Jonathan M Garibaldi, Guoping Qiu
In supervised deep learning, learning good representations for remote--sensing images (RSI) relies on manual annotations.
2 code implementations • 24 Apr 2021 • Zhi Chen, Jiang Duan, Li Kang, Guoping Qiu
In addition to using the conditional GAN to generate class balanced supplementary training data, an innovative ensemble learning loss function ensuring each discriminator makes up for the deficiencies of the others is designed to overcome the class imbalanced problem, and an active learning algorithm is introduced to significantly reduce the cost of labeling real-world data.
1 code implementation • 2 Mar 2021 • Hongming Luo, Fei Zhou, Guangsen Liao, Guoping Qiu
Based on a mathematical inference model for estimating a clean low-resolution (LR) image and a clean high-resolution (HR) image from a down-sampled and compressed observation, we have designed a CISR architecture consisting of two deep neural network modules: the artefacts removal module (ARM) and the resolution enhancement module (REM).
no code implementations • 20 Jan 2021 • Yuanhao Gong, Wenming Tang, Lebin Zhou, Lantao Yu, Guoping Qiu
Weighted Gaussian Curvature is an important measurement for images.
no code implementations • 20 Jan 2021 • Yuanhao Gong, Wenming Tang, Lebin Zhou, Lantao Yu, Guoping Qiu
The proposed filter can be adopted in a wide range of image processing applications.
no code implementations • 7 Jan 2021 • Hongming Luo, Guangsen Liao, Xianxu Hou, Bozhi Liu, Fei Zhou, Guoping Qiu
In this paper, we focus on the problem of translating VHS video to HDTV video and have developed a solution based on a novel unsupervised multi-task adversarial learning model.
no code implementations • 9 Nov 2020 • Qing Li, Jiasong Zhu, Jun Liu, Rui Cao, Qingquan Li, Sen Jia, Guoping Qiu
Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions.
1 code implementation • 5 Nov 2020 • Kanglin Liu, Gaofeng Cao, Fei Zhou, Bozhi Liu, Jiang Duan, Guoping Qiu
In this paper, we present a new technique termed Structure-Texture Independent Architecture with Weight Decomposition and Orthogonal Regularization (STIA-WO) to disentangle the latent space for unsupervised semantic face editing.
no code implementations • 27 Jun 2020 • Jun Liu, Qing Li, Rui Cao, Wenming Tang, Guoping Qiu
To the best of our knowledge, this work is the first extremely lightweight neural network trained on monocular video sequences for real-time unsupervised monocular depth estimation, which opens up the possibility of implementing deep learning-based real-time unsupervised monocular depth prediction on low-cost embedded devices.
Ranked #5 on Semantic Segmentation on SpectralWaste
no code implementations • 23 Jun 2020 • Kanglin Liu, Qing Li, Guoping Qiu
We present PoseGANs, a conditional generative adversarial networks (cGANs) based framework for the implementation of pose-to-image translation.
no code implementations • 10 May 2020 • Xianxu Hou, Jingxin Liu, Bolei Xu, Xiaolong Wang, Bozhi Liu, Guoping Qiu
To improve the adversarial robustness of neural networks, adversarial training has been proposed to train networks by injecting adversarial examples into the training data.
no code implementations • 11 Dec 2019 • Orod Razeghi, Guoping Qiu
Classifiers embedded within human in the loop visual object recognition frameworks commonly utilise two sources of information: one derived directly from the imagery data of an object, and the other obtained interactively from user interactions.
no code implementations • 11 Dec 2019 • Orod Razeghi, Guoping Qiu
A widely used approach to tackling the problem is a group of subspace methods, where the original features are projected onto a new space.
no code implementations • 25 Sep 2019 • Xianxu Hou, Jingxin Liu, Bolei Xu, Bozhi Liu, Xin Chen, Mohammad Ilyas, Ian Ellis, Jon Garibaldi, Guoping Qiu
The extensive experiments and ablation study demonstrate the effectiveness of our approach on the domain adaptive segmentation task.
2 code implementations • ICCV 2019 • Kanglin Liu, Wenming Tang, Fei Zhou, Guoping Qiu
Theoretical analysis shows that the optimal solution to the discriminator has a strong relationship to the spectral distributions of the weight matrix. Therefore, we monitor the spectral distribution in the discriminator of spectral normalized GANs (SN-GANs), and discover a phenomenon which we refer to as spectral collapse, where a large number of singular values of the weight matrices drop dramatically when mode collapse occurs.
no code implementations • 4 Jun 2019 • Xianxu Hou, Hongming Luo, Jingxin Liu, Bolei Xu, Ke Sun, Yuanhao Gong, Bozhi Liu, Guoping Qiu
In this paper, we propose an effective image denoising method by learning two image priors from the perspective of domain alignment.
no code implementations • 4 Jun 2019 • Xianxu Hou, Ke Sun, Linlin Shen, Guoping Qiu
We present a new method for improving the performances of variational autoencoder (VAE).
1 code implementation • CVPR 2019 • Hui Yin, Yuanhao Gong, Guoping Qiu
In addition to image filtering, we further show that the SWF principle can be extended to other applications involving the use of a local window.
1 code implementation • 12 May 2019 • Wei Pan, Xuequan Lu, Yuanhao Gong, Wenming Tang, Jun Liu, Ying He, Guoping Qiu
This paper presents a simple yet effective method for feature-preserving surface smoothing.
Computational Geometry Graphics
no code implementations • 11 Apr 2019 • Zhuo Lei, Chao Zhang, Qian Zhang, Guoping Qiu
In constructing the dataset, because of the subjectivity of user-generated video summarization, we manually annotate 25 summaries for each video, which are in total 1300 summaries.
no code implementations • 28 Feb 2019 • Bolei Xu, Jingxin Liu, Xianxu Hou, Bozhi Liu, Jon Garibaldi, Ian O. Ellis, Andy Green, Linlin Shen, Guoping Qiu
In this paper, we present a novel deep hybrid attention approach to breast cancer classification.
no code implementations • 15 Feb 2019 • Rui Cao, Qian Zhang, Jiasong Zhu, Qing Li, Qingquan Li, Bozhi Liu, Guoping Qiu
With the rapid growing of remotely sensed imagery data, there is a high demand for effective and efficient image retrieval tools to manage and exploit such data.
no code implementations • 4 Feb 2019 • Wei Liu, Xianxu Hou, Jiang Duan, Guoping Qiu
In addition, we also contribute the first real world nature fog-fogfree image dataset for defogging research.
no code implementations • 4 Jan 2019 • Qing Li, Jiasong Zhu, Rui Cao, Ke Sun, Jonathan M. Garibaldi, Qingquan Li, Bozhi Liu, Guoping Qiu
6DOF camera relocalization is an important component of autonomous driving and navigation.
no code implementations • 6 Nov 2018 • Fei Yang, Qian Zhang, Chi Zheng, Guoping Qiu
In the computer research area, facial expression recognition is a hot research problem.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 16 Mar 2018 • Kanglin Liu, Guoping Qiu
In this paper, we introduce the boundedness and continuity ($BC$) conditions to enforce the Lipschitz constraint on the discriminator functions of GANs.
no code implementations • 19 Jan 2018 • Jingxin Liu, Bolei Xu, Chi Zheng, Yuanhao Gong, Jon Garibaldi, Daniele Soria, Andew Green, Ian O. Ellis, Wenbin Zou, Guoping Qiu
To the best of our knowledge, this is the first end-to-end system that takes a TMA image as input and directly outputs a clinical score.
no code implementations • 19 Jan 2018 • Fei Yang, Qian Zhang, Miaohui Wang, Guoping Qiu
We will present experimental results to show that our quality classified framework can accurately classify images based on the type and severity of image degradations and can significantly boost the performances of state-of-the-art face detector and recognizer in dealing with image datasets containing mixed quality images.
no code implementations • 29 Jul 2017 • 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 Deep Feature Consistent Deep Image Transformation (DFC-DIT) framework which unifies challenging one-to-many mapping image processing problems such as image downscaling, decolorization (colour to grayscale conversion) and high dynamic range (HDR) image tone mapping.
no code implementations • 1 Jul 2017 • Xianxu Hou, Guoping Qiu
First, to the best knowledge of the authors, this is the first work that has successfully developed deep learning based solutions to these two traditional low-level image processing problems.
14 code implementations • 2 Oct 2016 • Xianxu Hou, Linlin Shen, Ke Sun, Guoping Qiu
We present a novel method for constructing Variational Autoencoder (VAE).
no code implementations • 7 Sep 2016 • Ke Sun, Xianxu Hou, Qian Zhang, Guoping Qiu
Furthermore, not all tags have the same descriptive power for visual contents and large vocabulary available from natural language could result in a very diverse set of keywords.
no code implementations • 6 Sep 2016 • Xianxu Hou, Ke Sun, Linlin Shen, Guoping Qiu
We present a method for discovering and exploiting object specific deep learning features and use face detection as a case study.
no code implementations • 27 Aug 2016 • Yangming Zhou, Guoping Qiu
Label ranking aims to learn a mapping from instances to rankings over a finite number of predefined labels.
no code implementations • 5 Jul 2013 • Chris Roadknight, Uwe Aickelin, Guoping Qiu, John Scholefield, Lindy Durrant
For predicting the stage of cancer from the immunological attributes, anti-learning approaches outperform a range of popular algorithms.
no code implementations • 31 Jan 2013 • Anh Cat Le Ngo, Kenneth Li-Minn Ang, Guoping Qiu, Jasmine Kah-Phooi Seng
Discriminant power of features for the classification is measured as mutual information between distributions of image features and corresponding classes .