Search Results for author: Sheng Xu

Found 31 papers, 5 papers with code

An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection

no code implementations30 Mar 2022 Sheng Xu

However, existing deep learning based models struggle to simultaneously achieve the requirements of both high precision and real-time performance.

Data Augmentation

TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping

1 code implementation17 Feb 2022 Hongjie Fang, Hao-Shu Fang, Sheng Xu, Cewu Lu

However, the majority of current grasping algorithms would fail in this case since they heavily rely on the depth image, while ordinary depth sensors usually fail to produce accurate depth information for transparent objects owing to the reflection and refraction of light.

Depth Completion Robotic Grasping +2

TerViT: An Efficient Ternary Vision Transformer

no code implementations20 Jan 2022 Sheng Xu, Yanjing Li, Teli Ma, Bohan Zeng, Baochang Zhang, Peng Gao, Jinhu Lv

Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices.

Neural Content Extraction for Poster Generation of Scientific Papers

no code implementations16 Dec 2021 Sheng Xu, Xiaojun Wan

Then we propose a three-step framework to tackle this task and focus on the content extraction step in this study.

Document Summarization

POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing

no code implementations26 Nov 2021 Sheng Xu, Yanjing Li, Junhe Zhao, Baochang Zhang, Guodong Guo

Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices.

Collage: Automated Integration of Deep Learning Backends

no code implementations1 Nov 2021 Byungsoo Jeon, Sunghyun Park, Peiyuan Liao, Sheng Xu, Tianqi Chen, Zhihao Jia

Strong demands for efficient deployment of Deep Learning (DL) applications prompt the rapid development of a rich DL ecosystem.

End-to-end Ultrasound Frame to Volume Registration

1 code implementation14 Jul 2021 Hengtao Guo, Xuanang Xu, Sheng Xu, Bradford J. Wood, Pingkun Yan

Fusing intra-operative 2D transrectal ultrasound (TRUS) image with pre-operative 3D magnetic resonance (MR) volume to guide prostate biopsy can significantly increase the yield.

Frame

Cross-modal Attention for MRI and Ultrasound Volume Registration

1 code implementation9 Jul 2021 Xinrui Song, Hengtao Guo, Xuanang Xu, Hanqing Chao, Sheng Xu, Baris Turkbey, Bradford J. Wood, Ge Wang, Pingkun Yan

In the past few years, convolutional neural networks (CNNs) have been proved powerful in extracting image features crucial for image registration.

Image Registration

Layer-Wise Searching for 1-Bit Detectors

no code implementations CVPR 2021 Sheng Xu, Junhe Zhao, Jinhu Lu, Baochang Zhang, Shumin Han, David Doermann

At each layer, it exploits a differentiable binarization search (DBS) to minimize the angular error in a student-teacher framework.

Binarization

RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images

no code implementations3 Mar 2021 Minghao Gou, Hao-Shu Fang, Zhanda Zhu, Sheng Xu, Chenxi Wang, Cewu Lu

In the first stage, an encoder-decoder like convolutional neural network Angle-View Net(AVN) is proposed to predict the SO(3) orientation of the gripper at every location of the image.

FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data

no code implementations9 Jan 2021 Shuyuan Yan, Bolin Ding, Wei Guo, Jingren Zhou, Zhewei Wei, Xiaowei Jiang, Sheng Xu

Our scalable real-time forecasting system FlashP (Flash Prediction) is built based on this idea, with two major challenges to be resolved in this paper: first, we need to figure out how approximate aggregations affect the fitting of forecasting models, and forecasting results; and second, accordingly, what sampling algorithms we should use to obtain these approximate aggregations and how large the samples are.

Time Series

A Neural Local Coherence Analysis Model for Clarity Text Scoring

no code implementations COLING 2020 Panitan Muangkammuen, Sheng Xu, Fumiyo Fukumoto, Kanda Runapongsa Saikaew, Jiyi Li

Local coherence relation between two phrases/sentences such as cause-effect and contrast gives a strong influence of whether a text is well-structured or not.

Language Modelling

Transducer Adaptive Ultrasound Volume Reconstruction

no code implementations17 Nov 2020 Hengtao Guo, Sheng Xu, Bradford J. Wood, Pingkun Yan

However, such algorithms are specific to particular transducers and scanning trajectories associated with the training data, which may not be generalized to other image acquisition settings.

Domain Adaptation Frame

Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS

no code implementations ICLR 2021 Lin Chen, Sheng Xu

We prove that the reproducing kernel Hilbert spaces (RKHS) of a deep neural tangent kernel and the Laplace kernel include the same set of functions, when both kernels are restricted to the sphere $\mathbb{S}^{d-1}$.

The 1st Tiny Object Detection Challenge:Methods and Results

1 code implementation16 Sep 2020 Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi

The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.

Human Detection Object Detection

Two-Stage Maximum Score Estimator

no code implementations7 Sep 2020 Wayne Yuan Gao, Sheng Xu

We characterize the asymptotic distribution of the TSMS estimator, which features phase transitions depending on the dimension and thus the convergence rate of the first-stage estimation.

Sensorless Freehand 3D Ultrasound Reconstruction via Deep Contextual Learning

1 code implementation13 Jun 2020 Hengtao Guo, Sheng Xu, Bradford Wood, Pingkun Yan

Transrectal ultrasound (US) is the most commonly used imaging modality to guide prostate biopsy and its 3D volume provides even richer context information.

Frame

Tree-Projected Gradient Descent for Estimating Gradient-Sparse Parameters on Graphs

no code implementations31 May 2020 Sheng Xu, Zhou Fan, Sahand Negahban

We study estimation of a gradient-sparse parameter vector $\boldsymbol{\theta}^* \in \mathbb{R}^p$, having strong gradient-sparsity $s^*:=\|\nabla_G \boldsymbol{\theta}^*\|_0$ on an underlying graph $G$.

Logical Differencing in Dyadic Network Formation Models with Nontransferable Utilities

no code implementations3 Jan 2020 Wayne Yuan Gao, Ming Li, Sheng Xu

This paper considers a semiparametric model of dyadic network formation under nontransferable utilities (NTU).

Unified Multi-scale Feature Abstraction for Medical Image Segmentation

no code implementations24 Oct 2019 Xi Fang, Bo Du, Sheng Xu, Bradford J. Wood, Pingkun Yan

Automatic medical image segmentation, an essential component of medical image analysis, plays an importantrole in computer-aided diagnosis.

Medical Image Segmentation Semantic Segmentation

Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese

no code implementations ACL 2019 Sheng Xu, Peifeng Li, Fang Kong, Qiaoming Zhu, Guodong Zhou

In the literature, most of the previous studies on English implicit discourse relation recognition only use sentence-level representations, which cannot provide enough semantic information in Chinese due to its unique paratactic characteristics.

Tensor Networks

Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurements

no code implementations15 May 2019 Sheng Xu, Zhou Fan

We consider estimating a piecewise-constant image, or a gradient-sparse signal on a general graph, from noisy linear measurements.

Shubnikov-de Haas and de Haas-van Alphen oscillations in topological semimetal CaAl4

no code implementations15 Nov 2018 Sheng Xu, Jian-Feng Zhang, Yi-Yan Wang, Lin-Lin Sun, Huan Wang, Yuan Su, Xiao-Yan Wang, Kai Liu, Tian-Long Xia

An electron-type quasi-2D Fermi surface is found by the angle-dependent Shubnikov-de Haas oscillations, de Haas-van Alphen oscillations and the first-principles calculations.

Materials Science Mesoscale and Nanoscale Physics

Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse

no code implementations COLING 2018 Sheng Xu, Peifeng Li, Guodong Zhou, Qiaoming Zhu

The task of nuclearity recognition in Chinese discourse remains challenging due to the demand for more deep semantic information.

Question Answering Text Matching

MCDTB: A Macro-level Chinese Discourse TreeBank

no code implementations COLING 2018 Feng Jiang, Sheng Xu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Guodong Zhou

In view of the differences between the annotations of micro and macro discourse rela-tionships, this paper describes the relevant experiments on the construction of the Macro Chinese Discourse Treebank (MCDTB), a higher-level Chinese discourse corpus.

Reading Comprehension

Learning Deep Similarity Metric for 3D MR-TRUS Registration

no code implementations12 Jun 2018 Grant Haskins, Jochen Kruecker, Uwe Kruger, Sheng Xu, Peter A. Pinto, Brad J. Wood, Pingkun Yan

Conclusion: A similarity metric that is learned using a deep neural network can be used to assess the quality of any given image registration and can be used in conjunction with the aforementioned optimization framework to perform automatic registration that is robust to poor initialization.

Image Registration

Adversarial Image Registration with Application for MR and TRUS Image Fusion

no code implementations30 Apr 2018 Pingkun Yan, Sheng Xu, Ardeshir R. Rastinehad, Brad J. Wood

Robust and accurate alignment of multimodal medical images is a very challenging task, which however is very useful for many clinical applications.

Image Registration

An optimal hierarchical clustering approach to segmentation of mobile LiDAR point clouds

no code implementations6 Mar 2017 Sheng Xu, Ruisheng Wang, Han Zheng

The main contribution of this paper is that we succeed to optimize the combination of clusters in the hierarchical clustering.

Point Cloud Segmentation

Road Curb Extraction from Mobile LiDAR Point Clouds

no code implementations15 Oct 2016 Sheng Xu, Ruisheng Wang, Han Zheng

Automatic extraction of road curbs from uneven, unorganized, noisy and massive 3D point clouds is a challenging task.

Cannot find the paper you are looking for? You can Submit a new open access paper.