no code implementations • 20 Jan 2025 • Yepeng Liu, Zhichao Sun, Baosheng Yu, Yitian Zhao, Bo Du, Yongchao Xu, Jun Cheng
Extending such methods to multimodal image matching often requires well-aligned multimodal data to learn modality-invariant descriptors.
1 code implementation • 4 Dec 2024 • Jiongtong Hu, Wei Zhuo, Jun Cheng, Yingying Liu, Wufeng Xue, Dong Ni
Effective solution for such a multi-plane segmentation (MPS) problem is highly demanded for medical images, yet has not been well investigated.
no code implementations • 25 Nov 2024 • Han Yue, Jun Cheng, Yu-Xuan Ren, Philip Heng Wai Leong, Steve Feng Shu
In this paper, we present Ptychoformer, a physics-guided DL framework for ptychographic imaging that aligns attention mechanisms and feature extraction with these diffraction physics properties through introducing a dual-branch architecture which accounts for both local and non-local dependencies from the patterns.
1 code implementation • 23 Oct 2024 • Jun Cheng, Shan Tan
In this paper, we build upon diffusion priors and propose adaptive likelihood estimation and MAP inference during the reverse diffusion process to tackle real-world noise.
no code implementations • 9 Oct 2024 • Baiyu Pan, Jichao Jiao, Bowen Yao, Jianxin Pang, Jun Cheng
In this paper, we conduct a detailed analysis of the previous distribution-based methods and propose a novel supervision method for stereo matching, Sampling-Gaussian.
no code implementations • 25 Sep 2024 • Xinrui Zhou, Yuhao Huang, Haoran Dou, Shijing Chen, Ao Chang, Jia Liu, Weiran Long, Jian Zheng, Erjiao Xu, Jie Ren, Ruobing Huang, Jun Cheng, Wufeng Xue, Dong Ni
In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models.
1 code implementation • 2 Sep 2024 • Yepeng Liu, Baosheng Yu, Tian Chen, Yuliang Gu, Bo Du, Yongchao Xu, Jun Cheng
For that, we use a keypoint detector and a deformation network called GAMorph to estimate the global transformation and local deformable transformation, respectively.
no code implementations • 5 Aug 2024 • Weide Liu, Xingxing Wang, Lu Wang, Jun Cheng, Fayao Liu, Xulei Yang
In this paper, we introduce a novel Gaussian mixture based evidential learning solution for robust stereo matching.
no code implementations • 31 Jul 2024 • Jiangyi Wang, Zhongyao Cheng, Na Zhao, Jun Cheng, Xulei Yang
In this paper, we propose On-the-fly Point Feature Representation (OPFR), which captures abundant geometric information explicitly through Curve Feature Generator module.
no code implementations • 22 Jul 2024 • YiFei Gao, Jie Ou, Lei Wang, Fanhua Shang, Jaji Wu, Jun Cheng
Large Language Models (LLMs) showcase remarkable performance and robust deductive capabilities, yet their expansive size complicates deployment and raises environmental concerns due to substantial resource consumption.
no code implementations • 24 Jun 2024 • YiFei Gao, Jie Ou, Lei Wang, Yuting Xiao, Zhiyuan Xiang, Ruiting Dai, Jun Cheng
LSI uses Singular Value Decomposition to extract singular values of the weights and make them learnable to help weights compensate each other conditioned on activation.
1 code implementation • 20 Jun 2024 • Xinrui Zhou, Yuhao Huang, Wufeng Xue, Haoran Dou, Jun Cheng, Han Zhou, Dong Ni
In this paper, we propose a novel diffusion-based framework named HeartBeat towards controllable and high-fidelity ECHO video synthesis.
1 code implementation • 14 Jun 2024 • Weide Liu, Jingwen Hou, Xiaoyang Zhong, Huijing Zhan, Jun Cheng, Yuming Fang, Guanghui Yue
Secondly, we propose a post-training stage that enables the model to reconstruct missing modalities in the prediction results when only partial modalities are available.
1 code implementation • 11 Jun 2024 • Ming Hu, Peng Xia, Lin Wang, Siyuan Yan, Feilong Tang, Zhongxing Xu, Yimin Luo, Kaimin Song, Jurgen Leitner, Xuelian Cheng, Jun Cheng, Chi Liu, Kaijing Zhou, ZongYuan Ge
With approximately 285 hours of surgical videos, OphNet is about 20 times larger than the largest existing surgical workflow analysis benchmark.
no code implementations • 25 May 2024 • Huizhou Chen, Jiangyi Wang, Yuxin Li, Na Zhao, Jun Cheng, Xulei Yang
3D environment recognition is essential for autonomous driving systems, as autonomous vehicles require a comprehensive understanding of surrounding scenes.
no code implementations • 20 May 2024 • Baiyu Pan, Jichao Jiao, Jianxing Pang, Jun Cheng
Firstly, we review state-of-the-art methods and design our lightweight model by removing redundant modules from those efficient models through a comparison of their contributions.
1 code implementation • 17 May 2024 • Fei Wang, Jun Cheng
Most existing methods often rely on complex models to predict scene depth with high accuracy, resulting in slow inference that is not conducive to deployment.
no code implementations • 29 Apr 2024 • YiFei Gao, Jie Ou, Lei Wang, Jun Cheng
Furthermore, we show that our method is versatile and can be easily integrated, allowing various 3D reconstruction projects to benefit from our approach.
1 code implementation • CVPR 2024 • Jun Cheng, Dong Liang, Shan Tan
Image denoising is a fundamental task in computer vision.
no code implementations • CVPR 2024 • Rui Gong, Weide Liu, Zaiwang Gu, Xulei Yang, Jun Cheng
Geometric knowledge has been shown to be beneficial for the stereo matching task.
no code implementations • 26 Sep 2023 • Jingwei Niu, Jun Cheng, Shan Tan
This leads to the separation of clean contents from noise, effectively denoising the image.
1 code implementation • 9 Sep 2023 • Yuhong He, Long Peng, Lu Wang, Jun Cheng
Since rain streaks show a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining.
1 code implementation • ICCV 2023 • Jun Cheng, Tao Liu, Shan Tan
By considering the deep variational image posterior with a Gaussian form, score priors are extracted based on easily accessible minimum MSE Non-$i. i. d$ Gaussian denoisers and variational samples, which in turn facilitate optimizing the variational image posterior.
1 code implementation • ICCV 2023 • Jieming Lou, Weide Liu, Zhuo Chen, Fayao Liu, Jun Cheng
Although existing stereo matching models have achieved continuous improvement, they often face issues related to trustworthiness due to the absence of uncertainty estimation.
1 code implementation • 25 Jul 2023 • YiFei Gao, Lei Wang, Jun Fang, Longhua Hu, Jun Cheng
Recently, with the emergence of numerous Large Language Models (LLMs), the implementation of AI has entered a new era.
1 code implementation • 15 Jul 2023 • Junyu Li, Han Huang, Dong Ni, Wufeng Xue, Dongmei Zhu, Jun Cheng
In addition, we design an object-level temporal aggregation (OTA) module that can automatically filter low-quality features and efficiently integrate temporal information from multiple frames to improve the accuracy of tumor diagnosis.
no code implementations • 28 Jun 2023 • Mingyuan Luo, Xin Yang, Zhongnuo Yan, Junyu Li, Yuanji Zhang, Jiongquan Chen, Xindi Hu, Jikuan Qian, Jun Cheng, Dong Ni
Ultrasound (US) imaging is a popular tool in clinical diagnosis, offering safety, repeatability, and real-time capabilities.
no code implementations • 10 Jun 2023 • Xiaoyang Hao, Han Li, Jun Cheng, Lei Wang
However, these methods present rotation semantic ambiguity, rotation error accumulation, and shape estimation overfitting, which also leads to errors in the estimated pose.
1 code implementation • 6 Jun 2023 • Fusheng Hao, Fengxiang He, Yikai Wang, Fuxiang Wu, Jing Zhang, Jun Cheng, DaCheng Tao
Massive human-related data is collected to train neural networks for computer vision tasks.
1 code implementation • 30 May 2023 • Fei Wang, Jun Cheng
To this end, we propose a high-quality decoder (HQDec), with which multilevel near-lossless fine-grained information, obtained by the proposed adaptive axial-normalized position-embedded channel attention sampling module (AdaAxialNPCAS), can be adaptively incorporated into a low-resolution feature map with high-level semantics utilizing the proposed adaptive information exchange scheme.
1 code implementation • 25 May 2023 • Xuan Liu, Yaoqin Xie, Jun Cheng, Songhui Diao, Shan Tan, Xiaokun Liang
The results demonstrate that our method outperforms the state-of-the-art unsupervised method and surpasses several supervised deep learning-based methods.
1 code implementation • 13 May 2023 • Jun Cheng, Honglei Su, Jari Korhonen
Then, we gather the features of all the patches of a point cloud for correlation analysis, to obtain the correlation weights.
Ranked #1 on
Point Cloud Quality Assessment
on WPC
1 code implementation • journal 2023 • Qin Cheng, Jun Cheng, Ziliang Ren, Qieshi Zhang, Jianming Liu
Unifying the MSST module, a multi-scale spatial–temporal convolutional neural network (MSSTNet) is proposed to capture high-level spatial–temporal semantic features for action recognition.
Ranked #4 on
Skeleton Based Action Recognition
on UAV-Human
1 code implementation • 24 Mar 2023 • Weide Liu, Zhonghua Wu, Yang Zhao, Yuming Fang, Chuan-Sheng Foo, Jun Cheng, Guosheng Lin
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes.
1 code implementation • ICCV 2023 • Fusheng Hao, Fengxiang He, Liu Liu, Fuxiang Wu, DaCheng Tao, Jun Cheng
This could significantly reduce the efficiency of a large family of few-shot learning algorithms, which have limited data and highly rely on the comparison of image patches.
no code implementations • CVPR 2023 • Tao Liu, Jun Cheng, Shan Tan
In this paper, we propose to quantify spectral Bayesian uncertainty in image SR. To achieve this, a Dual-Domain Learning (DDL) framework is first proposed.
no code implementations • 12 Dec 2022 • Fei Wang, Jun Cheng, Penglei Liu
Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos.
no code implementations • 1 Jul 2022 • Han Huang, Yijie Dong, Xiaohong Jia, Jianqiao Zhou, Dong Ni, Jun Cheng, Ruobing Huang
Furthermore, finding an optimal way to integrate multi-view information also relies on the experience of clinicians and adds further difficulty to accurate diagnosis.
1 code implementation • 2 Jun 2022 • Fei Wu, Qingzhong Wang, Jian Bian, Haoyi Xiong, Ning Ding, Feixiang Lu, Jun Cheng, Dejing Dou
Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.
no code implementations • 25 May 2022 • Tianyang Zhang, Shaoming Zheng, Jun Cheng, Xi Jia, Joseph Bartlett, Xinxing Cheng, Huazhu Fu, Zhaowen Qiu, Jiang Liu, Jinming Duan
It consists of a spatial transformation block followed by an intensity distribution rendering module.
no code implementations • 14 Apr 2022 • Jiamin Liang, Xin Yang, Yuhao Huang, Haoming Li, Shuangchi He, Xindi Hu, Zejian Chen, Wufeng Xue, Jun Cheng, Dong Ni
Our main contributions include: 1) we present the first work that can synthesize realistic B-mode US images with high-resolution and customized texture editing features; 2) to enhance structural details of generated images, we propose to introduce auxiliary sketch guidance into a conditional GAN.
no code implementations • 14 Apr 2022 • Jikuan Qian, Rui Li, Xin Yang, Yuhao Huang, Mingyuan Luo, Zehui Lin, Wenhui Hong, Ruobing Huang, Haining Fan, Dong Ni, Jun Cheng
The hybrid framework consists of a pre-trained backbone and several searched cells (i. e., network building blocks), which takes advantage of the strengths of both NAS and the expert knowledge from existing convolutional neural networks.
no code implementations • CVPR 2022 • Fuxiang Wu, Liu Liu, Fusheng Hao, Fengxiang He, Jun Cheng
Object-guided text-to-image synthesis aims to generate images from natural language descriptions built by two-step frameworks, i. e., the model generates the layout and then synthesizes images from the layout and captions.
2 code implementations • 21 Oct 2021 • Yepeng Liu, Zaiwang Gu, Shenghua Gao, Dong Wang, Yusheng Zeng, Jun Cheng
Very often, the pose is estimated after the face detection.
no code implementations • 5 Oct 2021 • Kang Zhou, Jing Li, Weixin Luo, Zhengxin Li, Jianlong Yang, Huazhu Fu, Jun Cheng, Jiang Liu, Shenghua Gao
To mitigate this problem, in this paper, we propose a novel Proxy-bridged Image Reconstruction Network (ProxyAno) for anomaly detection in medical images.
1 code implementation • 5 Jul 2021 • Haocong Rao, Xiping Hu, Jun Cheng, Bin Hu
In this paper, we for the first time propose a Self-supervised Multi-scale Skeleton Graph Encoding (SM-SGE) framework that comprehensively models human body, component relations, and skeleton dynamics from unlabeled skeleton graphs of various scales to learn an effective skeleton representation for person Re-ID.
no code implementations • 25 Jun 2021 • Jun Cheng, Carolin Lawrence, Mathias Niepert
In contrast, we propose VEGN, which models variant effect prediction using a graph neural network (GNN) that operates on a heterogeneous graph with genes and variants.
1 code implementation • 6 Jun 2021 • Haocong Rao, Shihao Xu, Xiping Hu, Jun Cheng, Bin Hu
To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID.
1 code implementation • 13 Feb 2021 • Shengcong Chen, Changxing Ding, Minfeng Liu, Jun Cheng, DaCheng Tao
Each polygon is represented by a set of centroid-to-boundary distances, which are in turn predicted by features of the centroid pixel for a single nucleus.
1 code implementation • 15 Oct 2020 • Lei Mou, Yitian Zhao, Huazhu Fu, Yonghuai Liu, Jun Cheng, Yalin Zheng, Pan Su, Jianlong Yang, Li Chen, Alejandro F Frang, Masahiro Akiba, Jiang Liu
Automated detection of curvilinear structures, e. g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases.
1 code implementation • 5 Sep 2020 • Haocong Rao, Siqi Wang, Xiping Hu, Mingkui Tan, Yi Guo, Jun Cheng, Xinwang Liu, Bin Hu
This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.
1 code implementation • 21 Aug 2020 • Haocong Rao, Siqi Wang, Xiping Hu, Mingkui Tan, Huang Da, Jun Cheng, Bin Hu
Unlike previous methods, we for the first time propose a generic gait encoding approach that can utilize unlabeled skeleton data to learn gait representations in a self-supervised manner.
1 code implementation • ECCV 2020 • Kang Zhou, Yuting Xiao, Jianlong Yang, Jun Cheng, Wen Liu, Weixin Luo, Zaiwang Gu, Jiang Liu, Shenghua Gao
In the end, we further utilize the reconstructed image to extract the structure and measure the difference between structure extracted from original and the reconstructed image.
2 code implementations • 1 Aug 2020 • Haocong Rao, Shihao Xu, Xiping Hu, Jun Cheng, Bin Hu
In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised manner.
Contrastive Learning
Self-Supervised Human Action Recognition
+1
no code implementations • 5 Jun 2020 • Jianxing Huang, Linfeng Zhang, Han Wang, Jinbao Zhao, Jun Cheng, Weinan E
It has been a challenge to accurately simulate Li-ion diffusion processes in battery materials at room temperature using {\it ab initio} molecular dynamics (AIMD) due to its high computational cost.
Computational Physics Materials Science Chemical Physics
no code implementations • CVPR 2020 • Jun Cheng, Fuxiang Wu, Yanling Tian, Lei Wang, Dapeng Tao
Text-to-image synthesis is a challenging task that generates realistic images from a textual sequence, which usually contains limited information compared with the corresponding image and so is ambiguous and abstractive.
1 code implementation • 22 May 2020 • Shijie Hao, Yuan Zhou, Yanrong Guo, Richang Hong, Jun Cheng, Meng Wang
In SGCPNet, we propose the strategy of spatial-detail guided context propagation.
no code implementations • 16 Apr 2020 • Yujia Zhou, Shumao Pang, Jun Cheng, Yuhang Sun, Yi Wu, Lei Zhao, Yaqin Liu, Zhentai Lu, Wei Yang, Qianjin Feng
In fact, due to the limitation of the receptive field, the 3 x 3 kernel has difficulty in covering the corresponding features at high/original resolution.
no code implementations • 11 Dec 2019 • Huihong Zhang, Jianlong Yang, Kang Zhou, Zhenjie Chai, Jun Cheng, Shenghua Gao, Jiang Liu
Firstly, our method trains a biomarker prediction network to learn the features of the biomarker.
no code implementations • 28 Nov 2019 • Kang Zhou, Shenghua Gao, Jun Cheng, Zaiwang Gu, Huazhu Fu, Zhi Tu, Jianlong Yang, Yitian Zhao, Jiang Liu
With the development of convolutional neural network, deep learning has shown its success for retinal disease detection from optical coherence tomography (OCT) images.
no code implementations • 26 Oct 2019 • Lei Mou, Li Chen, Jun Cheng, Zaiwang Gu, Yitian Zhao, Jiang Liu
Many methods have been proposed for vessel detection.
no code implementations • 9 Aug 2019 • Hao Qiu, Zaiwang Gu, Lei Mou, Xiaoqian Mao, Liyang Fang, Yitian Zhao, Jiang Liu, Jun Cheng
The optic disc segmentation is an important step for retinal image-based disease diagnosis such as glaucoma.
no code implementations • 6 Aug 2019 • Tianyang Zhang, Huazhu Fu, Yitian Zhao, Jun Cheng, Mengjie Guo, Zaiwang Gu, Bing Yang, Yuting Xiao, Shenghua Gao, Jiang Liu
Generative Adversarial Networks (GANs) have the capability of synthesizing images, which have been successfully applied to medical image synthesis tasks.
3 code implementations • 7 Mar 2019 • Zaiwang Gu, Jun Cheng, Huazhu Fu, Kang Zhou, Huaying Hao, Yitian Zhao, Tianyang Zhang, Shenghua Gao, Jiang Liu
In this paper, we propose a context encoder network (referred to as CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation.
Ranked #1 on
Optic Disc Segmentation
on Messidor
1 code implementation • 9 Sep 2018 • Yali Du, Meng Fang, Jin-Feng Yi, Jun Cheng, DaCheng Tao
First, we initialize an adversarial example with a gray color image on which every pixel has roughly the same importance for the target model.
no code implementations • 31 Aug 2018 • Kang Zhou, Zaiwang Gu, Wen Liu, Weixin Luo, Jun Cheng, Shenghua Gao, Jiang Liu
To considering the relationships of images with different stages, we propose a \textbf{Multi-Task} learning strategy which predicts the label with both classification and regression.
3 code implementations • 19 May 2018 • Huazhu Fu, Jun Cheng, Yanwu Xu, Changqing Zhang, Damon Wing Kee Wong, Jiang Liu, Xiaochun Cao
Specifically, a novel Disc-aware Ensemble Network (DENet) for automatic glaucoma screening is proposed, which integrates the deep hierarchical context of the global fundus image and the local optic disc region.
no code implementations • 17 May 2018 • Jun Cheng, Zhengguo Li, Zaiwang Gu, Huazhu Fu, Damon Wing Kee Wong, Jiang Liu
It often obscures the details in the retinal images and posts challenges in retinal image processing and analysing tasks.
no code implementations • 22 Apr 2018 • Fusheng Hao, Jun Cheng, Lei Wang, Xinchao Wang, Jianzhong Cao, Xiping Hu, Dapeng Tao
Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible.
3 code implementations • 3 Jan 2018 • Huazhu Fu, Jun Cheng, Yanwu Xu, Damon Wing Kee Wong, Jiang Liu, Xiaochun Cao
The proposed M-Net mainly consists of multi-scale input layer, U-shape convolutional network, side-output layer, and multi-label loss function.
Ranked #4 on
Optic Disc Segmentation
on REFUGE
no code implementations • 12 Nov 2016 • Dapeng Luo, Zhipeng Zeng, Nong Sang, Xiang Wu, Longsheng Wei, Quanzheng Mou, Jun Cheng, Chen Luo
In this paper, the proposed framework takes a remarkably different direction to resolve the multi-scene detection problem in a bottom-up fashion.
no code implementations • 7 Aug 2016 • Yanan Guo, Lei LI, Weifeng Liu, Jun Cheng, Dapeng Tao
Since human actions can be characterized by multiple feature representations extracted from Kinect and inertial sensors, multiview features must be encoded into a unified space optimal for human action recognition.
no code implementations • CVPR 2015 • Jimmy Addison Lee, Jun Cheng, Beng Hai Lee, Ee Ping Ong, Guozhen Xu, Damon Wing Kee Wong, Jiang Liu, Augustinus Laude, Tock Han Lim
These customized step patterns are robust to non-linear intensity changes, which are well-suited for multimodal retinal image registration.
no code implementations • 15 Jul 2013 • Weifeng Liu, DaCheng Tao, Jun Cheng, Yuanyan Tang
In particular, mHDSC exploits Hessian regularization to steer the solution which varies smoothly along geodesics in the manifold, and treats the label information as an additional view of feature for incorporating the discriminative power for image annotation.