检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zou, Ke Bai, Yang Chen, Zhihao Zhou, Yang Chen, Yidi Ren, Kai Wang, Meng Yuan, Xuedong Shen, Xiaojing Fu, Huazhu National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Sichuan China College of Computer Science Sichuan University Sichuan China Institute of High Performance Computing A*STAR Singapore College of Intelligence and Computing Tianjin University Tianjin China Department of Radiology West China Hospital Sichuan University China Beth Israel Deaconess Medical Center Harvard Medical School Boston United States College of Mathematics Sichuan University Sichuan China

Medical Report Grounding is pivotal in identifying the most relevant regions in medical images based on a given phrase query, a critical aspect in medical image analysis and radiological diagnosis. However, prevailing visual grounding approaches necessitate the manual extraction of key phrases from medical reports, imposing substantial burdens on both system efficiency and physicians. In this paper, we introduce a novel framework—Medical Report Grounding (MedRG)—an end-to-end solution for utilizing a multi-modal Large Language Model to predict key phrase by incorporating a unique token, , into the vocabulary to serve as an embedding for unlocking detection capabilities. Subsequently, the vision encoder-decoder jointly decodes the hidden embedding and the input medical image, generating the corresponding grounding box. The experimental results validate the effectiveness of MedRG, surpassing the performance of the existing state-of-the-art medical phrase grounding methods. This study represents a pioneering exploration of the medical report grounding task, marking the first-ever endeavor in this domain. © 2024, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Synthesis of a Quaternary Ammonium-Halamine and Preparation on the Modified Nanofibrous Filter with Superior Sterilization, Air Filtration and Biodegradability

SSRN

引用

SSRN 2024年

作者： Tang, Xin Zhang, Zaixing Jing, Lingxiao Luan, Kun Zhang, Tonghua Zhou, Sha Zhu, Yifan Chemistry and Material Engineering School of Huaihua University Huaihua418008 China College of Sericulture Textiles and Biomass Sciences Chongqing Biomass Fiber Materials and Modern Textile Engineering Technology Research Center State Key Laboratory of Silkworm Genome Biology Southwest University Chongqing400715 China Yibin Pingshan Fanglian Technology Development Co. Ltd Yibin645350 China Jiangsu Ruilante New Materials Co. Ltd. Yangzhou211400 China State Key Lab of High-Performance Ceramics and Superfine Microstructures Shanghai Institute of Ceramics Shanghai200050 China School of Computing College of Engineering Computing and Cybernetics The Australian National University Canberra2601 Australia

The health and environmental concerns raised by the emerging coronavirus epidemic, the non-biodegradable nature of filters, and the contamination of the air with particles, have led to an increasing demand for biodegradable, highly efficient, low-resistance filters, but there are currently few commercial filters that meet these needs. Therefore, a novel quaternary ammonium-halamine compound containing Schiff base and sandwich-structure preparation strategy was developed for the construction of a new multifunctional filter. The filter consists of a PLA fleece for support, an antimicrobial coating for bactericidal action and a nanofibrous membrane for particle removal. The resultant filter demonstrates strong bactericidal properties, killing 97% of E. coli and S. aureus at a biocide concentration of only 1 mg/mL. Additionally, it rapidly kills bacteria within 5 minutes of contact without leaching of the antimicrobial substance. Furthermore, it boasts a filtration performance that surpasses that of commercial N95 filters for PM0.3, with a success rate of over 99.99% and a pressure drop of 45Pa. Even in humid conditions, it maintains excellent filtration performance, and the filter can naturally degrade in soil. The successful development of this filter offers new design ideas for high performance air filters that protect public health. © 2024, The Authors. All rights reserved.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video

Real-time Multi-person Eyeblink Detection in the Wild for Un...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wenzheng Zeng Yang Xiao Sicheng Wei Jinfang Gan Xintao Zhang Zhiguo Cao Zhiwen Fang Joey Tianyi Zhou Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Biomedical Engineering Southern Medical University Guangzhou China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou China Centre for Frontier AI Research Agency for Science Technology and Research (A*STAR) Singapore Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

Real-time eyeblink detection in the wild can widely serve for fatigue detection, face anti-spoofing, emotion analysis, etc. The existing research efforts generally focus on single-person cases towards trimmed video. However, multi-person scenario within untrimmed videos is also important for practical applications, which has not been well concerned yet. To address this, we shed light on this research field for the first time with essential contributions on dataset, theory, and practices. In particular, a large-scale dataset termed MPEblink that involves 686 untrimmed videos with 8748 eyeblink events is proposed under multi-person conditions. The samples are captured from uncon-strainedfilms to reveal “in the wild“ characteristics. Meanwhile, a real-time multi-person eyeblink detection method is also proposed. Being different from the existing counter-parts, our proposition runs in a one-stage spatio-temporal way with end-to-end learning capacity. Specifically, it simultaneously addresses the sub-tasks of face detection, face tracking, and human instance-level eyeblink detection. This paradigm holds 2 main advantages: (1) eyeblink features can be facilitated via the face's global context (e.g., head pose and illumination condition) with joint optimization and interaction, and (2) addressing these sub-tasks in parallel instead of sequential manner can save time remarkably to meet the real-time running requirement. Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video. Our method also outperforms existing approaches by large margins and with a high inference speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AN EFFICIENT NUMERICAL APPROACH FOR STOCHASTIC EVOLUTION PDES DRIVEN BY RANDOM DIFFUSION COEFFICIENTS AND MULTIPLICATIVE NOISE∗

arXiv

引用

arXiv 2022年

作者： Xiao, Q.I. Azaiez, Mejdi Huang, Can Chuanju, X.U. School of Mathematical Sciences Fujian Provincial Key Laboratory of Mathematical Modeling and High Performance Scientific Computing Xiamen University Xiamen361005 China Bordeaux INP Laboratoire I2M UMR 5295 Pessac33607 France

In this paper, we investigate the stochastic evolution equations (SEEs) driven by log-Whittle-Matérn (W-M) random diffusion coefficient field and Q-Wiener multiplicative force noise. First, the well-posedness of the underlying equations is established by proving the existence, uniqueness, and stability of the mild solution. A sampling approach called approximation circulant embedding with padding is proposed to sample the random coefficient field. Then a spatio-temporal discretization method based on semi-implicit Euler-Maruyama scheme and finite element method is constructed and analyzed. An estimate for the strong convergence rate is derived. Numerical experiments are finally reported to confirm the theoretical result. Copyright © 2022, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

ReSLB: Load Balanced Workflow for Distributed Deep Learning Mass Spectrometry Database

ReSLB: Load Balanced Workflow for Distributed Deep Learning ...

引用

IEEE International Conference on high performance computing and Communications (HPCC)

作者： Li Mocheng Liu Yang Ou Yang Chen Zhiguang Xiao Nong Chen Tao Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China School of Computer Sun Yat-sen University Guangzhou China State Key Laboratory of Proteomics Beijing Proteome Research Center National Center for Protein Sciences(Beijing) Beijing Institute of Lifeomics Beijing China

The proteomics data analysis pipeline based on the shotgun method requires efficient data processing methods. The parallel algorithm of mass spectrometry database search faces the problems of rapidly expanding database size but low scalability. The heterogeneous database search algorithm based on deep learning is an effective way to solve this problem. Still, the deep learning-based distributed parallel database search algorithm is lacking. This paper analyzes the database searching computational load using a neural network and designs ReSLB, a workflow for the restricted search of mass spectrometry data based on GPU cluster and neural network scoring algorithm. This work aims to ensure the high scalability of future deep learning-based mass spectrometry distributed databases. In the performance estimation of 256 GPUs, the load imbalance of less than 30% and the parallel efficiency of 60% are achieved. Compared with state-of-the-art, the time cost is reduced by 75%, and the parallel efficiency from 1 to 256 GPUs is 3.6x higher than that.

关键词： Deep learning Scalability Neural networks Data preprocessing Distributed databases Graphics processing units Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

HeadCap: A Hierarchical Encoder-And-Decoder Image Captioning Model

HeadCap: A Hierarchical Encoder-And-Decoder Image Captioning...

引用

2020 International Conference on Intelligent computing, Automation and Systems, ICICAS 2020

作者： Yang, Wenjing Wang, Shiwei Lan, Long Institute for Quantum Information State Key Laboratory of High Performance Computing National University of Defense Technology Changsha410073 China Yunnan North Optical Electronic Instrument Co. Ltd Kunming650000 China

ISBN: (纸本)9781728191461

Image captioning achieves its goal by two steps traditionally, it first extracts image features using deep networks, and then translates the features into correct text descriptions. Though recent compelling captioning results have surged continuously, the bridge between visual cues and texts is usually limited by weak single-layer CNN features and one-word one-attention strategy. In this paper, we propose a simple yet effective Hierarchical Encoder-And-Decoder image CAPtioning model (HeadCap) to capture visual cues across different levels whilst conducting one-word multi-attention scheme in a unified hierarchical architecture. In specific, we collect multi-layer features from feature pyramid network (FPN), which allows stringing visual features across different levels hierarchically. More importantly, a multi-attention LSTM module (mLSTM) is established on such hierarchical features, which performs multiple attentions over hierarchical features progressively when predicting a word. This provides LSTM more attention chance to reduce the risk of the mismatch between visual cues and texts, and further to bridge the gap between each other. Experiments on MSCOCO image captioning dataset show that HeadCap yields favorable performance against several well-behaved deep captioning models. © 2020 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Precise and scalable evaluation on the robustness metric of neural networks as classifiers

Precise and scalable evaluation on the robustness metric of ...

引用

International Conference on Electronics, Communications and Information technology (CECIT)

作者： Yangyi Hu College of Computer Science and Technology Institute for Quantum Information & State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China College of Computer Science National University of Defense Technology Changsha China

ISBN: (纸本)9781665437585

It is well known that the minimum adversarial distortion associated with a specific sample x 0 reflects the local robustness of neural networks. However, it is intractable to solve the optimization problem related to the minimum adversarial distortion for general neural network cause it is non-convex. Works have studied the lower bound or upper bound of the minimum adversarial distortion to give a robustness metrics for neural networks, such as CLEVER score and CW attack. In this paper, we provide a formal robustness guarantee to transform the robustness analysis into two sub-problems: (1), compute out the maximum of the objective function g t * (r t ); (2), generate a sequence {r t h } s.t. limn→∞ r t h is the minimum adversarial distortion for targeted attack. Based on this transformation, we propose an efficient and effective algorithm to directly estimate the instance-specific minimum adversarial distortion on the norm of the input manipulation required to change the classifier decision. Experimental results on two data-sets, MNIST and CIFAR, show that our measure of robustness is between the lower bound given by CLEVER and the upper bound by CW, indicating our approach gives a precise measure of the robustness of neural network. In addition, the powerful mathematical technique Extreme Value Estimation enables our algorithm computationally feasible for large neural networks. To the best of our knowledge, our algorithm is the first attack-independent approach to directly evaluate the minimum adversarial distortion as a robustness metric for neural network.

关键词： Knowledge engineering Upper bound Neural networks Transforms Distortion Linear programming Robustness

来源：评论

学校读者我要写书评

暂无评论

lunule: An Agile and Judicious Metadata Load Balancer for CephFS

lunule: An Agile and Judicious Metadata Load Balancer for Ce...

引用

Supercomputing Conference

作者： Yiduo Wang Cheng Li Xinyang Shao Youxu Chen Feng Yan Yinlong Xu University of Science and Technology of China Hefei Anhui China Anhui Province Key Laboratory of High Performance Computing USTC Hefei Anhui China University of Nevada Reno Reno Nevada USA

ISBN: (数字)9781450384421

ISBN: (纸本)9781665483902

For a decade, the Ceph distributed file system (CephFS) has been widely used to serve the ever-growing big data in many key fields ranging from Internet services to AI computing. To scale out the massive metadata access, CephFS adopts a dynamic subtree partitioning method, splitting the hierarchical namespace and distributing subtrees across multiple metadata servers. However, this method suffers from a severe imbalance problem that may result in poor performance due to its inaccurate imbalance prediction, ignorance of workload characteristics, and unnecessary/invalid migration ac-tivities. To eliminate these inefficiencies, we propose Lunule, a novel CephFS metadata load balancer, which employs an imbalance fac-tor model for accurately determining when to trigger re-balance and tolerate benign imbalanced situations. Lunule further adopts a workload-aware migration planner to appropriately select sub-tree migration candidates. Compared to baselines, Lunule achieves better load balance, increases the metadata throughput by up to 315.8%, and shortens the tail job completion time by up to 64.6% for five real-world workloads and their mixture, respectively. Be-sides, Lunule is capable of handling the metadata cluster expansion and the client workload growth, and scales linearly on a cluster of 16 MDSs.

关键词： File systems System performance high performance computing Web and internet services Tail Metadata Throughput

来源：评论

学校读者我要写书评

暂无评论

One-shot video-based person re-identification with variance subsampling algorithm

One-shot video-based person re-identification with variance ...

引用

作者： Zhao, Jing Yang, Wenjing Yang, Mingliang Huang, Wanrong Yang, Qiong Zhang, Hongguang Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology ChangshaHunan410073 China Artificial Intelligence Research Center National Innovation Institute of Defense Technology Beijing China

Previous works propose the distance-based sampling for unlabeled datapoints to address the few-shot person re-identification task, however, many selected samples may be assigned with wrong labels due to poor feature quality in these works, which negatively affects the learning procedure. In this article, we propose a novel sampling strategy to improve the quality of assigned pseudo-labels, thus promoting the final performance. To illustrate, we first propose the concept of variance confidence to measure the credibility of pseudo-labels, then we apply a novel variance subsampling algorithm to improve the accuracy of the selected sample labels. Our method combines distance confidence and variance confidence as a two-round sampling criterion. Meanwhile, a variation decay strategy is used in our sampling process in combination with the actual distribution of features. We evaluate our approach on two publicly available datasets, MARS and DukeMTMC-VideoReID, and achieve state-of-the-art one-shot performance. © 2020 John Wiley & Sons, Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

UCTB: An Urban computing Tool Box for Building Spatiotemporal Prediction Services

arXiv

引用

arXiv 2023年

作者： Fang, Jiangyi Chen, Liyue Chai, Di Hong, Yayao Xie, Xiuhuai Chen, Longbiao Wang, Leye Key Lab of High Confidence Software Technologies Ministry of Education China Hong Kong University of Science and Technology Hong Kong Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen China School of Informatics Xiamen University Xiamen China School of Computer Science Peking University Beijing China

Spatiotemporal prediction (STP) service is one of the key infrastructure applications in smart cities. Currently, most of the existing STP services are constructed following the workflow of building deep learning (DL) applications while neglecting the importance of domain knowledge and region partition. However, the performance and interpretability of STP are highly related to them. As a result, there is an urgent requirement to develop a thorough and tailored workflow for STP services. To address this gap, we propose a novel workflow including two factors above as intermediate procedures. Based on the workflow, we design and implement an STP toolbox called UCTB (Urban computing Tool Box) assisting practitioners in the rapid construction of STP services, which can manage multiple spatiotemporal domain knowledge, support various region partition algorithms, and possess state-of-the-art models simultaneously. The relevant code and supporting documents have been open-sourced at https://***/uctb/UCTB. Copyright © 2023, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：