no code implementations • 28 Mar 2022 • Jialian Li, Jingyi Zhang, Zhiyong Wang, Siqi Shen, Chenglu Wen, Yuexin Ma, Lan Xu, Jingyi Yu, Cheng Wang
Quantitative and qualitative experiments show that our method outperforms the techniques based only on RGB images.
1 code implementation • 17 Mar 2022 • Yudi Dai, Yitai Lin, Chenglu Wen, Siqi Shen, Lan Xu, Jingyi Yu, Yuexin Ma, Cheng Wang
We propose Human-centered 4D Scene Capture (HSC4D) to accurately and efficiently create a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, and rich interactions between humans and environments.
no code implementations • 8 Mar 2022 • Jibing Gong, Yao Wan, Ye Liu, Xuewen Li, Yi Zhao, Cheng Wang, Qing Li, Wenzheng Feng, Jie Tang
Specifically, we first formulate the concept recommendation in MOOCs as a reinforcement learning problem to better model the dynamic interaction among users and knowledge concepts.
1 code implementation • 24 Jan 2022 • Shangbin Wu, Xu Yan, Xiaoliang Fan, Shirui Pan, Shichao Zhu, Chuanpan Zheng, Ming Cheng, Cheng Wang
Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks.
no code implementations • 10 Jan 2022 • Shuyin Xia, Cheng Wang, Guoyin Wang, Weiping Ding, Xinbo Gao, JianHang Yu, Yujia Zhai, Zizhong Chen
The granular-ball rough set can simultaneously represent Pawlak rough sets, and the neighborhood rough set, so as to realize the unified representation of the two.
1 code implementation • 4 Jan 2022 • Yuanhang Zhou, Kun Zhou, Wayne Xin Zhao, Cheng Wang, Peng Jiang, He Hu
To implement this framework, we design both coarse-grained and fine-grained procedures for modeling user preference, where the former focuses on more general, coarse-grained semantic fusion and the latter focuses on more specific, fine-grained semantic fusion.
no code implementations • 27 Dec 2021 • Jiahuan Pei, Cheng Wang, György Szarvas
In this work, we propose a novel way to enable transformers to have the capability of uncertainty estimation and, meanwhile, retain the original predictive performance.
no code implementations • 14 Dec 2021 • Binyan Jiang, Chenlei Leng, Cheng Wang, Zhongqing Yang
Datasets containing both categorical and continuous variables are frequently encountered in many areas, and with the rapid development of modern measurement technologies, the dimensions of these variables can be very high.
no code implementations • 25 Nov 2021 • Chuanpan Zheng, Xiaoliang Fan, Shirui Pan, Zonghan Wu, Cheng Wang, Philip S. Yu
In such a graph, the correlations between different nodes at different time steps are not explicitly reflected, which may restrict the learning ability of graph neural networks.
no code implementations • 11 Oct 2021 • Chen Zhao, Shi Shi, Zhuo He, Cheng Wang, Zhongqiang Zhao, Xinli Li, Yanli Zhou, Weihua Zhou
By integrating the spatial features from each cardiac frame of gated MPS and the temporal features from the sequential cardiac frames of the gated MPS, we develop a Spatial-Temporal V-Net (S-T-V-Net) for automatic extraction of RV endocardial and epicardial contours.
no code implementations • 27 Sep 2021 • Xu Yan, Xiaoliang Fan, Peizhen Yang, Zonghan Wu, Shirui Pan, Longbiao Chen, Yu Zang, Cheng Wang
Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems.
no code implementations • 14 Sep 2021 • Bing Han, Cheng Wang, Kaushik Roy
To address these challenges, we propose a novel neuron model that has cosine activation with a time varying component for sequential processing.
no code implementations • 13 Sep 2021 • Yue Chen, Wei Wei, Cheng Wang, Miadreza Shafie-khah, João P. S. Catalão
Large solar power stations usually locate in remote areas and connect to the main grid via a long transmission line.
no code implementations • 31 Aug 2021 • Jingtang Liang, Cheng Wang, Yujie Cheng, Zheng Wang, Fang Wang, Liyu Huang, Zhibin Yu, YuBo Wang
Mitotic figure count is an important marker of tumor proliferation and has been shown to be associated with patients' prognosis.
no code implementations • 27 Aug 2021 • Weiwen Wu, Yaohui Tang, Tianling Lv, Chuang Niu, Cheng Wang, Yiyan Guo, Yunheng Chang, Ge Wang, Yan Xi
The reconstructed volumetric images convincingly demonstrate the merits of the SMART system using the AI-empowered interior tomography approach, enabling cardiac micro-CT with the unprecedented temporal resolution of 30ms, which is an order of magnitude higher than the state of the art.
no code implementations • CVPR 2021 • Yunsong Zhou, Yuan He, Hongzi Zhu, Cheng Wang, Hongyang Li, Qinhong Jiang
Due to the lack of insight in industrial application, existing methods on open datasets neglect the camera pose information, which inevitably results in the detector being susceptible to camera extrinsic parameters.
Ranked #4 on
Monocular 3D Object Detection
on KITTI Cars Moderate
(using extra training data)
no code implementations • Findings (ACL) 2021 • Cheng Wang, Sungjin Lee, Sunghyun Park, Han Li, Young-Bum Kim, Ruhi Sarikaya
Real-world machine learning systems are achieving remarkable performance in terms of coarse-grained metrics like overall accuracy and F-1 score.
no code implementations • 1 Jun 2021 • Yanfei Su, Weiquan Liu, Zhimin Yuan, Ming Cheng, Zhihong Zhang, Xuelun Shen, Cheng Wang
As there is a lack of 3D point clouds datasets related to the fine-grained building facade, we construct the first large-scale building facade point clouds benchmark dataset for semantic segmentation.
1 code implementation • 30 Apr 2021 • Zheng Wang, Xiaoliang Fan, Jianzhong Qi, Chenglu Wen, Cheng Wang, Rongshan Yu
Fairness has emerged as a critical problem in federated learning (FL).
no code implementations • 26 Apr 2021 • Cheng Wang, Sun Kim, Taiwoo Park, Sajal Choudhary, Sunghyun Park, Young-Bum Kim, Ruhi Sarikaya, Sungjin Lee
We have been witnessing the usefulness of conversational AI systems such as Siri and Alexa, directly impacting our daily lives.
1 code implementation • 2 Apr 2021 • Xuelun Shen, Cheng Wang, Xin Li, Qian Hu, Jingyi Zhang
This paper presents a matching network to establish point correspondence between images.
no code implementations • 21 Mar 2021 • Renfei Tu, Yang Liu, Yongzeng Xue, Cheng Wang, Maozu Guo
Being one of the most popular generative framework, variational autoencoders(VAE) are known to suffer from a phenomenon termed posterior collapse, i. e. the latent variational distributions collapse to the prior, especially when a strong decoder network is used.
no code implementations • 9 Mar 2021 • Xian Sun, Peijin Wang, Zhiyuan Yan, Feng Xu, Ruiping Wang, Wenhui Diao, Jin Chen, Jihao Li, Yingchao Feng, Tao Xu, Martin Weinmann, Stefan Hinz, Cheng Wang, Kun fu
In this paper, we propose a novel benchmark dataset with more than 1 million instances and more than 15, 000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery which is named as FAIR1M.
no code implementations • 16 Feb 2021 • Peng Miao, Yifan Zhang, Cheng Wang, Shanbao Tong
We find that the dynamic speckle patterns can be utilized to decouple the singly and multiply backscattered components.
Optics Applied Physics
no code implementations • 18 Jan 2021 • Zhaoxi Chen, Qing Xu, Ke Zhang, Wing-Han Wong, De-Long Zhang, Edwin Yue-Bun Pun, Cheng Wang
Lithium niobate on insulator (LNOI) is an emerging photonic platform with great promises for future optical communications, nonlinear optics and microwave photonics.
Optics Applied Physics
no code implementations • 22 Dec 2020 • Juan Zhang, Cheng Wang, Steven M. Wise, Zhengru Zhang
In the second order numerical scheme, the BDF temporal stencil is applied, and an alternate convex-concave decomposition is derived, so that the concave part corresponds to a quadratic energy.
Numerical Analysis Numerical Analysis 35A15 (Primary) 12-XX, 12-08 (Secondary) F.2.2; G.2
1 code implementation • 10 Dec 2020 • Linfeng Jiang, Cheng Wang, Shuang Liu, Chao Sun, Enrico Calzavarini
We successfully perform the three-dimensional tracking in a turbulent fluid flow of small asymmetrical particles that are neutrally-buoyant and bottom-heavy, i. e., they have a non-homogeneous mass distribution along their symmetry axis.
Fluid Dynamics
no code implementations • ICLR 2021 • Cheng Wang, Carolin Lawrence, Mathias Niepert
Uncertainty quantification is crucial for building reliable and trustable machine learning systems.
1 code implementation • 8 Aug 2020 • Yan Xia, Yusheng Xu, Cheng Wang, Uwe Stilla
Moreover, a new refiner module is also presented to preserve the vehicle details from inputs and refine the complete outputs with fine-grained information.
no code implementations • CVPR 2020 • Cheng Wang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen
In the re-ID stage, we predict identity labels of detected bounding boxes, and use these examples to construct a more practical mixed train set for the DRA model.
no code implementations • 11 Apr 2020 • Cheng Wang, Kang Wei, Lingjun Kong, Long Shi, Zhen Mei, Jun Li, Kui Cai
The error correcting performance of multi-level-cell (MLC) NAND flash memory is closely related to the block length of error correcting codes (ECCs) and log-likelihood-ratios (LLRs) of the read-voltage thresholds.
no code implementations • 17 Jan 2020 • Saifullahi Aminu Bello, Shangshu Yu, Cheng Wang
Deep learning is now the most powerful tool for data processing in computer vision, becoming the most preferred technique for tasks such as classification, segmentation, and detection.
no code implementations • 23 Dec 2019 • Wenkai Han, Chenglu Wen, Cheng Wang, Xin Li, Qing Li
Point2Node can dynamically explore correlation among all graph nodes from different levels, and adaptively aggregate the learned features.
6 code implementations • 11 Nov 2019 • Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, Jianzhong Qi
Between the encoder and the decoder, a transform attention layer is applied to convert the encoded traffic features to generate the sequence representations of future time steps as the input of the decoder.
Ranked #2 on
Image Dehazing
on KITTI
1 code implementation • ISPRS Journal of Photogrammetry and Remote Sensing 2019 • Yangbin Lin, Cheng Wang, Dawei Zhai, Wei Li, Jonathan Li
In this paper, we present a simple but effective supervoxel segmentation method for point clouds, which formalizes supervoxel segmentation as a subset selection problem.
no code implementations • 20 Jun 2019 • Jonathan Li, Rongren Wu, Yiping Chen, Qing Zhu, Zhipeng Luo, Cheng Wang
Second, to accurately extract trees from all point clouds, we propose a 3D deep learning network, PointNLM, to semantically segment tree crowns.
no code implementations • 20 Jun 2019 • Zhuang Yang, Zengping Chen, Cheng Wang
Motivated by this gap, we proposed a variant of the Barzilai-Borwein (BB) method, referred to as the Random Barzilai-Borwein (RBB) method, to calculate step size for SARAH in the mini-batch setting, thereby leading to a new SARAH method: MB-SARAH-RBB.
1 code implementation • CVPR 2019 • Xuelun Shen, Cheng Wang, Xin Li, Zenglei Yu, Jonathan Li, Chenglu Wen, Ming Cheng, Zijian He
This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images.
no code implementations • 20 May 2019 • Yangbin Lin, Jialian Li, Cheng Wang, Zhonggui Chen, Zongyue Wang, Jonathan Li
Man-made environments typically comprise planar structures that exhibit numerous geometric relationships, such as parallelism, coplanarity, and orthogonality.
no code implementations • CVPR 2019 • Qing Li, Shaoyang Chen, Cheng Wang, Xin Li, Chenglu Wen, Ming Cheng, Jonathan Li
We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation.
no code implementations • 26 Mar 2019 • Cheng Wang, Mathias Niepert, Hui Li
Although various transfer learning methods have shown promising performance in this context, our proposed novel method RecSys-DAN focuses on alleviating the cross-domain and within-domain data sparsity and data imbalance and learns transferable latent representations for users, items and their interactions.
no code implementations • 25 Jan 2019 • Cheng Wang, Mathias Niepert
We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.
1 code implementation • 22 Jan 2019 • Zhou Tang, Zhangsheng Yu, Cheng Wang
Differential network is an important tool to capture the changes of conditional correlations under two sample cases.
Computation
1 code implementation • 22 Jan 2019 • Cheng Wang, Binyan Jiang, Liping Zhu
In this article we introduce a novel method which allows us to estimate the main effects and interactions separately.
Methodology
1 code implementation • 15 Jan 2019 • Rahul Anand, Hye-Young Paik, Cheng Wang
Tabular data extraction from reports and other published data in PDF format is of interest for various data consolidation purposes such as analysing and aggregating financial reports of a company.
no code implementations • 3 Jan 2019 • Jianning Li, Long Cao, Yangyang Ge, Bowen Meng, Cheng Wang, Wei Guo
The database contains 274 CT angiography (CTA) scans from 274 unique TBAD patients and is split into a training set(254 cases including 210 preoperative and 44 postoperative scans ) and a test set(20 cases). Based on STENT, we develop a series of methods including automated TBAD segmentation and automated measurement of TBAD parameters that facilitate personalized and precise management of the disease.
no code implementations • 22 Nov 2018 • Shenlong Lou, Yan Luo, Qiancong Fan, Feng Chen, Yiping Chen, Cheng Wang, Jonathan Li
It is widely recognized that the deeper networks or networks with more feature maps have better performance.
1 code implementation • 12 Nov 2018 • Cheng Wang, Binyan Jiang
The estimation of high dimensional precision matrices has been a central topic in statistical learning.
Computation Methodology
no code implementations • 27 Sep 2018 • Cheng Wang, Mathias Niepert
We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.
no code implementations • 27 Sep 2018 • Peize Zhao, Danfeng Cai, Shaokun Zhang, Feng Chen, Zhemin Zhang, Cheng Wang, Jonathan Li
To forecast the traffic flow across a wide area and overcome the mentioned challenges, we design and propose a promising forecasting model called Layerwise Recurrent Autoencoder (LRA), in which a three-layer stacked autoencoder (SAE) architecture is used to obtain temporal traffic correlations and a recurrent neural networks (RNNs) model for prediction.
no code implementations • 22 Sep 2018 • Zongliang Zhang, Hongbin Zeng, Jonathan Li, Yiping Chen, Chenhui Yang, Cheng Wang
This paper deals with the geometric multi-model fitting from noisy, unstructured point set data (e. g., laser scanned point clouds).
1 code implementation • 8 Sep 2018 • Yan Xia, Yang Zhang, Dingfu Zhou, Xinyu Huang, Cheng Wang, Ruigang Yang
Then, the image together with the retrieved shape model is fed into the proposed network to generate the fine-grained 3D point cloud.
no code implementations • ECCV 2018 • Cheng Wang, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang
We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.
no code implementations • EMNLP 2018 • Cheng Wang, Mathias Niepert, Hui Li
More importantly, LRMM is more robust to previous methods in alleviating data-sparsity and the cold-start problem.
3 code implementations • 30 Jul 2018 • Liangchen Song, Cheng Wang, Lefei Zhang, Bo Du, Qian Zhang, Chang Huang, Xinggang Wang
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation.
Ranked #15 on
Unsupervised Domain Adaptation
on Market to Duke
no code implementations • CVPR 2018 • Yiping Chen, Jingkang Wang, Jonathan Li, Cewu Lu, Zhipeng Luo, Han Xue, Cheng Wang
Learning autonomous-driving policies is one of the most challenging but promising tasks for computer vision.
no code implementations • 10 Oct 2017 • Shanxin Zhang, Cheng Wang, Zhuang Yang, Chenglu Wen, Jonathan Li, Chenhui Yang
Then, based on the VEM, we proposed the concept of the Visual Recognizability Field (VRF) to reflect the visual recognizability distribution in 3D space and established a Visual Recognizability Evaluation Model (VREM) to measure a traffic sign visual recognizability for a given viewpoint.
1 code implementation • 12 Sep 2017 • Cheng Wang
In this paper, we propose a recurrent neural network (RNN) with residual attention (RRA) to learn long-range dependencies from sequential data.
1 code implementation • 17 Oct 2016 • Zongliang Zhang, Jonathan Li, Yulan Guo, Yangbin Lin, Ming Cheng, Cheng Wang
However, most geometric model fitting methods are unable to fit an arbitrary geometric model (e. g. a surface with holes) to incomplete data, due to that the similarity metrics used in these methods are unable to measure the rigid partial similarity between arbitrary models.
no code implementations • LREC 2016 • Xiaoyin Che, Cheng Wang, Haojin Yang, Christoph Meinel
In this paper we propose an approach to predict punctuation marks for unsegmented speech transcript.
1 code implementation • 4 Apr 2016 • Cheng Wang, Haojin Yang, Christian Bartz, Christoph Meinel
This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning.