no code implementations • 19 Apr 2023 • Yang Zhou, Hanjie Wu, Wenxi Liu, Zheng Xiong, Jing Qin, Shengfeng He
In this way, the challenging novel view synthesis process is decoupled into two simpler problems of stereo synthesis and 3D reconstruction.
no code implementations • 10 Apr 2023 • Jing Qin, Biyun Xie
In the meanwhile, geometry-based regularizations, such as graph regularizations, can be imposed on the foreground.
no code implementations • 14 Mar 2023 • Jing Zou, Noémie Debroux, Lihao Liu, Jing Qin, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero
We propose a novel framework for deformable image registration.
no code implementations • 20 Feb 2023 • Halyun Jeong, Deanna Needell, Jing Qin
In particular, federated learning (FL) provides such a solution to learn a shared model while keeping training data at local clients.
no code implementations • 23 Jan 2023 • Mingqiang Wei, Yiyang Shen, Yongzhen Wang, Haoran Xie, Jing Qin, Fu Lee Wang
Before answering it, we observe two major obstacles of diffusion models in real-world image deraining: the need for paired training data and the limited utilization of multi-scale rain patterns.
no code implementations • 5 Dec 2022 • Xudong Kang, Haoran Xie, Man-Leung Wong, Jing Qin
In this study, we try to re-interpret these generative methods for image restoration tasks using information theory.
no code implementations • 17 Nov 2022 • Yiyang Shen, Rongwei Yu, Peng Wu, Haoran Xie, Lina Gong, Jing Qin, Mingqiang Wei
We propose ImLiDAR, a new 3OD paradigm to narrow the cross-sensor discrepancies by progressively fusing the multi-scale features of camera Images and LiDAR point clouds.
1 code implementation • 4 Aug 2022 • Zhilei Chen, Honghua Chen, Lina Gong, Xuefeng Yan, Jun Wang, Yanwen Guo, Jing Qin, Mingqiang Wei
High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner.
no code implementations • 1 Aug 2022 • Zhe Zhu, Liangliang Nan, Haoran Xie, Honghua Chen, Mingqiang Wei, Jun Wang, Jing Qin
The first module transfers the intrinsic shape characteristics from single images to guide the geometry generation of the missing regions of point clouds, in which we propose IPAdaIN to embed the global features of both the image and the partial point cloud into completion.
Ranked #2 on Point Cloud Completion on ShapeNet-ViPC
1 code implementation • 17 Jul 2022 • Haorui Song, Yong Du, Tianyi Xiang, Junyu Dong, Jing Qin, Shengfeng He
Consequently, in the decomposition phase, we further present a GAN prior based deghosting network for separating the final fine edited image from the coarse reconstruction.
1 code implementation • 2 Jul 2022 • Wenao Ma, Cheng Chen, Shuang Zheng, Jing Qin, Huimao Zhang, Qi Dou
In this paper, we propose the first method to tackle label shift for medical image classification, which effectively adapt the model learned from a single training label distribution to arbitrary unknown test label distribution.
1 code implementation • 1 Jul 2022 • Zhi Lin, Junhao Lin, Lei Zhu, Huazhu Fu, Jing Qin, Liansheng Wang
Moreover, we learn video-level features to classify the breast lesions of the original video as benign or malignant lesions to further enhance the final breast lesion detection performance in ultrasound videos.
no code implementations • 20 Jun 2022 • Baian Chen, Zhilei Chen, Xiaowei Hu, Jun Xu, Haoran Xie, Mingqiang Wei, Jing Qin
This paper presents a novel deep neural network framework for RGB-D salient object detection by controlling the message passing between the RGB images and depth maps on the feature level and exploring the long-range semantic contexts and geometric information on both RGB and depth features to infer salient objects.
1 code implementation • 16 Jun 2022 • Xin Zhong, Zhaoyi Yan, Jing Qin, WangMeng Zuo, Weigang Lu
However, the heads are not uniformly covered by the sampling points in the deformable convolution, resulting in loss of head information.
1 code implementation • 9 Jun 2022 • Mingqiang Wei, Zeyong Wei, Haoran Zhou, Fei Hu, Huajian Si, Zhilei Chen, Zhe Zhu, Jingbo Qiu, Xuefeng Yan, Yanwen Guo, Jun Wang, Jing Qin
In this paper, we propose Adaptive Graph Convolution (AGConv) for wide applications of point cloud analysis.
1 code implementation • 2 Jun 2022 • Jiacheng Wang, Fei Chen, Yuxi Ma, Liansheng Wang, Zhaodong Fei, Jianwei Shuai, Xiangdong Tang, Qichao Zhou, Jing Qin
Skin lesion segmentation from dermoscopy images is of great significance in the quantitative analysis of skin cancers, which is yet challenging even for dermatologists due to the inherent issues, i. e., considerable size, shape and color variation, and ambiguous boundaries.
1 code implementation • 4 May 2022 • Yongzhen Wang, Xuefeng Yan, Fu Lee Wang, Haoran Xie, Wenhan Yang, Mingqiang Wei, Jing Qin
From a different yet new perspective, this paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images, thus bridging the gap between synthetic and real-world haze is avoided.
no code implementations • 25 Apr 2022 • Jing Qin, Ruilong Shen, Ruihan Zhu, Biyun Xie
In the meanwhile, sparsity or smoothness based regularizations, such as total variation and $\ell_1$, can be imposed on the foreground.
1 code implementation • 6 Apr 2022 • Yiyang Shen, Mingqiang Wei, Sen Deng, Wenhan Yang, Yongzhen Wang, Xiao-Ping Zhang, Meng Wang, Jing Qin
To bridge the two domain gaps, we propose a semi-supervised detail-recovery image deraining network (Semi-DRDNet) with dual sample-augmented contrastive learning.
1 code implementation • CVPR 2022 • Guangyuan Li, Jun Lv, Yapeng Tian, Qi Dou, Chengyan Wang, Chenliang Xu, Jing Qin
However, existing methods still have two shortcomings: (1) they neglect that the multi-contrast features at different scales contain different anatomical details and hence lack effective mechanisms to match and fuse these features for better reconstruction; and (2) they are still deficient in capturing long-range dependencies, which are essential for the regions with complicated anatomical structures.
1 code implementation • 23 Mar 2022 • Haoran Zhou, Honghua Chen, Yingkui Zhang, Mingqiang Wei, Haoran Xie, Jun Wang, Tong Lu, Jing Qin, Xiao-Ping Zhang
Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations.
1 code implementation • Computer-Aided Design 2022 • Yingkui Zhang, Guibao Shen, Qiong Wang, Yinling Qian, Mingqiang Wei, Jing Qin
For the first time, we optimize both positions and normals (i. e., dual domains) in a unified framework of GNN, and show the powerful inter-coordination between the dual domains.
1 code implementation • CVPR 2022 • Huisi Wu, Zhaoze Wang, Youyi Song, Lin Yang, Jing Qin
We study the semi-supervised learning problem, using a few labeled data and a large amount of unlabeled data to train the network, by developing a cross-patch dense contrastive learning framework, to segment cellular nuclei in histopathologic images.
1 code implementation • 6 Dec 2021 • Jiacheng Wang, Xiaomeng Li, Yiming Han, Jing Qin, Liansheng Wang, Zhou Qichao
The SIS is proposed to operate on the image set to rebuild a region set under the guidance of structural information.
1 code implementation • 8 Nov 2021 • Jiacheng Wang, Yueming Jin, Shuntian Cai, Hongzhi Xu, Pheng-Ann Heng, Jing Qin, Liansheng Wang
Compared with existing solutions, which either neglect geometric relationships among targeting objects or capture the relationships by using complicated aggregation schemes, the proposed network is capable of achieving satisfactory accuracy while maintaining real-time performance by taking full advantage of the spatial relations among landmarks.
1 code implementation • 8 Oct 2021 • Jiacheng Wang, Lan Wei, Liansheng Wang, Qichao Zhou, Lei Zhu, Jing Qin
Skin lesion segmentation from dermoscopy images is of great importance for improving the quantitative analysis of skin cancer.
Ranked #4 on Lesion Segmentation on ISIC 2018
no code implementations • ICLR 2022 • Minhao Liu, Ailing Zeng, Qiuxia Lai, Ruiyuan Gao, Min Li, Jing Qin, Qiang Xu
In this work, we propose a novel tree-structured wavelet neural network for time series signal analysis, namely T-WaveNet, by taking advantage of an inherent property of various types of signals, known as the dominant frequency range.
1 code implementation • 28 Sep 2021 • Jiacheng Wang, Yueming Jin, Liansheng Wang, Shuntian Cai, Pheng-Ann Heng, Jing Qin
On the other hand, we develop an active global memory to gather the global semantic correlation in long temporal range to current one, in which we gather the most informative frames derived from model uncertainty and frame similarity.
1 code implementation • ICCV 2021 • Haoran Zhou, Yidan Feng, Mingsheng Fang, Mingqiang Wei, Jing Qin, Tong Lu
Convolution on 3D point clouds that generalized from 2D grid-like domains is widely researched yet far from perfect.
Ranked #10 on 3D Point Cloud Classification on IntrA
no code implementations • 6 Aug 2021 • Yongtuo Liu, Sucheng Ren, Liangyu Chai, Hanjie Wu, Jing Qin, Dan Xu, Shengfeng He
In this way, we can transfer the original spatial labeling redundancy caused by individual similarities to effective supervision signals on the unlabeled regions.
1 code implementation • 6 Aug 2021 • Ye Liu, Lei Zhu, Shunda Pei, Huazhu Fu, Jing Qin, Qing Zhang, Liang Wan, Wei Feng
Our DID-Net predicts the three component maps by progressively integrating features across scales, and refines each map by passing an independent refinement network.
Ranked #4 on Image Dehazing on Haze4k
no code implementations • 29 Jun 2021 • Geng Deng, Guangning Xu, Qiang Fu, Xindong Wang, Jing Qin
In this paper, we introduce the shape-restricted inference to the celebrated Cox regression model (SR-Cox), in which the covariate response is modeled as shape-restricted additive functions.
no code implementations • 15 Jun 2021 • Sen Deng, Yidan Feng, Mingqiang Wei, Haoran Xie, Yiping Chen, Jonathan Li, Xiao-Ping Zhang, Jing Qin
Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image.
no code implementations • 30 May 2021 • Ailing Zeng, Minhao Liu, Zhiwei Liu, Ruiyuan Gao, Jing Qin, Qiang Xu
We propose a novel solution to addressing a long-standing dilemma in the representation learning of graph neural networks (GNNs): how to effectively capture and represent useful information embedded in long-distance nodes to improve the performance of nodes with low homophily without leading to performance degradation in nodes with high homophily.
no code implementations • 29 Apr 2021 • Jing Qin, Joshua Ashley, Biyun Xie
Recognition of hand gestures is one of the most fundamental tasks in human-robot interaction.
1 code implementation • CVPR 2021 • Zhihao Chen, Liang Wan, Lei Zhu, Jia Shen, Huazhu Fu, Wennan Liu, Jing Qin
The bottleneck is the lack of a well-established dataset with high-quality annotations for video shadow detection.
1 code implementation • CVPR 2021 • Quande Liu, Cheng Chen, Jing Qin, Qi Dou, Pheng-Ann Heng
Federated learning allows distributed medical institutions to collaboratively learn a shared prediction model with privacy protection.
no code implementations • 6 Mar 2021 • Xueying Shi, Yueming Jin, Qi Dou, Jing Qin, Pheng-Ann Heng
In this paper, we propose a novel unsupervised domain adaptation framework which can simultaneously transfer multi-modality knowledge, i. e., both kinematic and visual data, from simulator to real robot.
no code implementations • ICCV 2021 • Yi Zheng, Shixiang Tang, Guolong Teng, Yixiao Ge, Kaijian Liu, Jing Qin, Donglian Qi, Dapeng Chen
To tackle the problem, we propose an online pseudo label generation by hierarchical cluster dynamics for adaptive ReID.
no code implementations • ICCV 2021 • Huisi Wu, Guilian Chen, Zhenkun Wen, Jing Qin
In this paper, we present a novel semi-supervised polyp segmentation via collaborative and adversarial learning of focused and dispersive representations learning model, where focused and dispersive extraction module are used to deal with the diversity of location and shape of polyps.
no code implementations • 4 Dec 2020 • Jing Qin
News recommendation systems were the earliest research field regarding recommendation systems, and were also the earliest recommendation field to apply the collaborative filtering method.
no code implementations • 21 May 2020 • Yiyang Shen, Yidan Feng, Sen Deng, Dong Liang, Jing Qin, Haoran Xie, Mingqiang Wei
We observe three intriguing phenomenons that, 1) rain is a mixture of raindrops, rain streaks and rainy haze; 2) the depth from the camera determines the degrees of object visibility, where objects nearby and faraway are visually blocked by rain streaks and rainy haze, respectively; and 3) raindrops on the glass randomly affect the object visibility of the whole image space.
no code implementations • 8 Apr 2020 • Youyi Song, Lei Zhu, Baiying Lei, Bin Sheng, Qi Dou, Jing Qin, Kup-Sze Choi
In the shape evolution, we compensate intensity deficiency for the segmentation by introducing not only the modeled local shape priors but also global shape priors (clump--level) modeled by considering mutual shape constraints of cytoplasms in the clump.
no code implementations • 8 Apr 2020 • Youyi Song, Zhen Yu, Teng Zhou, Jeremy Yuen-Chun Teoh, Baiying Lei, Kup-Sze Choi, Jing Qin
Our insight is that feature maps of two CNNs trained respectively on GT and CT images should be similar on some metric space, because they both are used to describe the same objects for the same purpose.
1 code implementation • 22 Feb 2020 • Cheng Chen, Qi Dou, Yueming Jin, Hao Chen, Jing Qin, Pheng-Ann Heng
We tackle this challenge and propose a novel multimodal segmentation framework which is robust to the absence of imaging modalities.
1 code implementation • 6 Feb 2020 • Cheng Chen, Qi Dou, Hao Chen, Jing Qin, Pheng Ann Heng
In this work, we present a novel unsupervised domain adaptation framework, named as Synergistic Image and Feature Alignment (SIFA), to effectively adapt a segmentation network to an unlabeled target domain.
1 code implementation • 5 Sep 2019 • Xueying Shi, Qi Dou, Cheng Xue, Jing Qin, Hao Chen, Pheng-Ann Heng
In this paper, we present a novel active learning framework for cost-effective skin lesion analysis.
no code implementations • 22 Aug 2019 • Rachel Grotheer, Shuang Li, Anna Ma, Deanna Needell, Jing Qin
In this paper, we utilize the same tensor version of the Restricted Isometry Property (RIP) to extend these results for tensors with low CANDECOMP/PARAFAC (CP) rank.
1 code implementation • 18 Aug 2019 • Luming Liang, Sen Deng, Lionel Gueguen, Mingqiang Wei, Xinming Wu, Jing Qin
We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the salt-and-pepper (s&p) noise.
1 code implementation • 13 Jul 2019 • Yueming Jin, Huaxia Li, Qi Dou, Hao Chen, Jing Qin, Chi-Wing Fu, Pheng-Ann Heng
Mutually leveraging both low-level feature sharing and high-level prediction correlating, our MTRCNet-CL method can encourage the interactions between the two tasks to a large extent, and hence can bring about benefits to each other.
Ranked #3 on Surgical tool detection on Cholec80
1 code implementation • 3 Jul 2019 • Yi Wang, Haoran Dou, Xiao-Wei Hu, Lei Zhu, Xin Yang, Ming Xu, Jing Qin, Pheng-Ann Heng, Tianfu Wang, Dong Ni
Our attention module utilizes the attention mechanism to selectively leverage the multilevel features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers.
no code implementations • 24 May 2019 • Badong Chen, Yuqing Xie, Xin Wang, Zejian yuan, Pengju Ren, Jing Qin
In a recent work, the concept of mixture correntropy (MC) was proposed to improve the learning performance, where the kernel function is a mixture Gaussian kernel, namely a linear combination of several zero-mean Gaussian kernels with different widths.
1 code implementation • 24 Jan 2019 • Cheng Chen, Qi Dou, Hao Chen, Jing Qin, Pheng-Ann Heng
Our proposed SIFA is an elegant learning diagram which presents synergistic fusion of adaptations from both image and feature perspectives.
no code implementations • 26 Dec 2018 • Fuyang Huang, Ailing Zeng, Minhao Liu, Jing Qin, Qiang Xu
Experimental results show that the proposed structure-aware 3D hourglass network is able to achieve a mean joint error of 7. 4 mm in MSRA and 8. 9 mm in NYU datasets, respectively.
1 code implementation • ECCV 2018 • Lei Zhu, Zijun Deng, Xiao-Wei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, Pheng-Ann Heng
Second, we develop a bidirectional feature pyramid network (BFPN) to aggregate shadow contexts spanned across different CNN layers by deploying two series of RAR modules in the network to iteratively combine and refine context features: one series to refine context features from deep to shallow layers, and another series from shallow to deep layers.
Ranked #3 on Shadow Detection on SBU
1 code implementation • 12 May 2018 • Xiaowei Hu, Chi-Wing Fu, Lei Zhu, Jing Qin, Pheng-Ann Heng
This paper presents a novel deep neural network design for shadow detection and removal by analyzing the spatial image context in a direction-aware manner.
Ranked #6 on Shadow Removal on ISTD
no code implementations • 2 Apr 2018 • Xiaowei Hu, Xuemiao Xu, Yongjie Xiao, Hao Chen, Shengfeng He, Jing Qin, Pheng-Ann Heng
Based on these findings, we present a scale-insensitive convolutional neural network (SINet) for fast detecting vehicles with a large variance of scales.
no code implementations • 22 Dec 2017 • Yanning Zhou, Qi Dou, Hao Chen, Jing Qin, Pheng-Ann Heng
Cell nuclei detection and fine-grained classification have been fundamental yet challenging problems in histopathology image analysis.
1 code implementation • CVPR 2018 • Xiaowei Hu, Lei Zhu, Chi-Wing Fu, Jing Qin, Pheng-Ann Heng
To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN.
Ranked #2 on RGB Salient Object Detection on SBU
no code implementations • 13 Aug 2017 • Qi Dou, Hao Chen, Yueming Jin, Huangjing Lin, Jing Qin, Pheng-Ann Heng
In this paper, we propose a novel framework with 3D convolutional networks (ConvNets) for automated detection of pulmonary nodules from low-dose CT scans, which is a challenging yet crucial task for lung cancer early diagnosis and treatment.
2 code implementations • 2 Aug 2017 • Lequan Yu, Jie-Zhi Cheng, Qi Dou, Xin Yang, Hao Chen, Jing Qin, Pheng-Ann Heng
Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data.
no code implementations • 30 Jul 2017 • Huangjing Lin, Hao Chen, Qi Dou, Liansheng Wang, Jing Qin, Pheng-Ann Heng
Lymph node metastasis is one of the most significant diagnostic indicators in breast cancer, which is traditionally observed under the microscope by pathologists.
no code implementations • 21 Dec 2016 • Badong Chen, Lei Xing, Xin Wang, Jing Qin, Nanning Zheng
Correntropy is a second order statistical measure in kernel space, which has been successfully applied in robust learning and signal processing.
no code implementations • 6 Dec 2016 • Xin Yang, Lequan Yu, Lingyun Wu, Yi Wang, Dong Ni, Jing Qin, Pheng-Ann Heng
Additionally, our approach is general and can be extended to other medical image segmentation tasks, where boundary incompleteness is one of the main challenges.
no code implementations • 3 Jul 2016 • Qi Dou, Hao Chen, Yueming Jin, Lequan Yu, Jing Qin, Pheng-Ann Heng
Automatic liver segmentation from CT volumes is a crucial prerequisite yet challenging task for computer-aided hepatic disease diagnosis and treatment.
no code implementations • 9 Apr 2015 • Fang Li, Stanley Osher, Jing Qin, Ming Yan
In this paper, we propose a variational multiphase image segmentation model based on fuzzy membership functions and L1-norm fidelity.
no code implementations • 26 Sep 2014 • Jing Qin, Weihong Guo
Existing methods mostly work well on piecewise constant images but not so well on piecewise smooth images such as natural images, medical images that contain a lot of details.