检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ye, Yiwen Xie, Yutong Zhang, Jianpeng Chen, Ziyang Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China The University of Adelaide Australia DAMO Academy Alibaba Group China

The universal model emerges as a promising trend for medical image segmentation, paving up the way to build medical imaging large model (MILM). One popular strategy to build universal models is to encode each task as a one-hot vector and generate dynamic convolutional layers at the end of the decoder to extract the interested target. Although successful, it ignores the correlations among tasks and meanwhile is too late to make the model ‘aware’ of the ongoing task. To address both issues, we propose a prompt-driven Universal Segmentation model (UniSeg) for multi-task medical image segmentation using diverse modalities and domains. We first devise a learnable universal prompt to describe the correlations among all tasks and then convert this prompt and image features into a task-specific prompt, which is fed to the decoder as a part of its input. Thus, we make the model ‘aware’ of the ongoing task early and boost the task-specific training of the whole decoder. Our results indicate that the proposed UniSeg outperforms other universal models and single-task models on 11 upstream tasks. Moreover, UniSeg also beats other pre-trained models on two downstream datasets, providing the community with a high-quality pre-trained model for 3D medical image segmentation. Code and model are available at https://***/yeerwen/UniSeg. Copyright © 2023, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on 360° Omnidirectional Image and Video Super-Resolution: Datasets, Methods and Results

NTIRE 2023 Challenge on 360° Omnidirectional Image and Vide...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Cao, Mingdeng Mou, Chong Yu, Fanghua Wang, Xintao Zheng, Yinqiang Zhang, Jian Dong, Chao Li, Gen Shan, Ying Timofte, Radu Sun, Xiaopeng Li, Weiqi Sheng, Xuhan Chen, Bin Ma, Haoyu Cheng, Ming Zhao, Shijie Huang, Huaibo Zhou, Xiaoqiang Ai, Yuang He, Ran Wu, Renlong Yang, Yi Zhang, Zhilu Zhang, Shuohao Li, Junyi Chen, Yunjin Ren, Dongwei Zuo, Wangmeng Yang, Hao-Hsiang Chen, Yi-Chung Huang, Zhi-Kai Chen, Wei-Ting Chiang, Yuan-Chun Chang, Hua-En Chen, I.-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Zhang, Zebin Zhang, Jiaqi Wang, Yuhui Cui, Shuhao Huang, Junshi Zhu, Li Tian, Shuman Yu, Wei Luo, Bingchun Cui, Wanwan Xu, Tianyu Li, Chunyang Bao, Long Sun, Heng Zhang, Zhenyu Wang, Qian The University of Tokyo Japan Arc Lab Tencent Pcg China Peking University China Shenzhen Institute of Advanced Technology Cas China Platform Technologies Tencent Online Video China Computer Vision Lab Ifi & Caidas University of Würzburg Germany ByteDance China Peking University Shenzhen Graduate School China Mais&cripac Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China University of Science and Technology of China China Beijing Institute of Technology China School of Information Science and Technology ShanghaiTech University China Harbin Institute of Technology China Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States ShanghaiTech University China Meituan China Xiaomi Inc

ISBN: (纸本)9798350302493

This report introduces two high-quality datasets Flickr360 and ODV360 for omnidirectional image and video super-resolution, respectively, and reports the NTIRE 2023 challenge on 360° omnidirectional image and video super-resolution. Unlike ordinary 2D images/videos with a narrow field of view, omnidirectional images/videos can represent the whole scene from all directions in one shot. There exists a large gap between omnidirectional image/video and ordinary 2D image/video in both the degradation and restoration processes. The challenge is held to facilitate the development of omnidirectional image/video super-resolution by considering their special characteristics. In this challenge, two tracks are provided: one is the omnidirectional image super-resolution and the other is the omnidirectional video super-resolution. The task of the challenge is to super-resolve an input omnidirectional image/video with a magnification factor of ×4. Realistic omnidirectional downsampling is applied to construct the datasets. Some general degradation(e.g., video compression) is also considered for the video track. The challenge has 100 and 56 registered participants for those two tracks. In the final testing stage, 7 and 3 participating teams submitted their results, source codes, and fact sheets. Almost all teams achieved better performance than baseline models by integrating omnidirectional characteristics, reaching compelling performance on our newly collected Flickr360 and ODV360 datasets. © 2023 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

TemPrompt: Multi-Task Prompt Learning for Temporal Relation Extraction in RAG-based Crowdsourcing Systems

arXiv

引用

arXiv 2024年

作者： Yang, Jing Zhao, Yu Yang, Linyao Wang, Xiao Chen, Long Wang, Fei-Yue Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha410000 China Zhejiang Lab Hangzhou311121 China School of Artificial Intelligence Anhui University Hefei266114 China Department of Computer and Information Science University of Macau 999078 China Faculty of Innovation Engineering Macau University of Science and Technology 999078 China

Temporal relation extraction (TRE) aims to grasp the evolution of events or actions, and thus shape the workflow of associated tasks, so it holds promise in helping understand task requests initiated by requesters in crowdsourcing systems. However, existing methods still struggle with limited and unevenly distributed annotated data. Therefore, inspired by the abundant global knowledge stored within pre-trained language models (PLMs), we propose a multi-task prompt learning framework for TRE (TemPrompt), incorporating prompt tuning and contrastive learning to tackle these issues. To elicit more effective prompts for PLMs, we introduce a task-oriented prompt construction approach that thoroughly takes the myriad factors of TRE into consideration for automatic prompt generation. In addition, we design temporal event reasoning in the form of masked language modeling as auxiliary tasks to bolster the model’s focus on events and temporal cues. The experimental results demonstrate that TemPrompt outperforms all compared baselines across the majority of metrics under both standard and few-shot settings. A case study on designing and manufacturing printed circuit boards is provided to validate its effectiveness in crowdsourcing scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Streaming Algorithms for Graph k-Matching with Optimal or Near-Optimal Update Time

arXiv

引用

arXiv 2023年

作者： Chen, Jianer Huang, Qin Kanj, Iyad Li, Qian Xia, Ge Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States School of Computing DePaul University ChicagoIL60604 United States Institute of Computing Technology Chinese Academy of Sciences Beijing China Department of Computer Science Lafayette College EastonPA18042 United States

We present streaming algorithms for the graph k-matching problem in both the insert-only and dynamic models. Our algorithms, with space complexity matching the best upper bounds, have optimal or near-optimal update time, significantly improving on previous results. More specifically, for the insert-only streaming model, we present a one-pass algorithm with optimal space complexity O(k2) and optimal update time O(1), that w.h.p. (with high probability) computes a maximum weighted k-matching of a given weighted graph. The update time of our algorithm significantly improves the previous upper bound of O(log k), which was derived only for k-matching on unweighted graphs. For the dynamic streaming model, we present a one-pass algorithm that w.h.p. computes a maximum weighted k-matching in O(W k2 · polylog(n)) space1 and with O(polylog(n)) update time, where W is the number of distinct edge weights. Again the update time of our algorithm improves the previous upper bound of O(k2 · polylog(n)). This algorithm, when applied to unweighted graphs, gives a streaming algorithm on the dynamic model whose space and update time complexities are both near-optimal. Our results also imply a streaming approximation algorithm for maximum weighted k-matching whose space complexity matches the best known upper bound with a significantly improved update time. © 2023, CC BY.

关键词： Dynamic models

来源：评论

学校读者我要写书评

暂无评论

Referring Flexible Image Restoration

arXiv

引用

arXiv 2024年

作者： Guan, Runwei Hu, Rongsheng Zhou, Zhuhao Xue, Tianlang Man, Ka Lok Smith, Jeremy Lim, Eng Gee Ding, Weiping Yue, Yutao Institute of Deep Perception Technology JITRI Wuxi214000 China Faculty of Science and Engineering University of Liverpool LiverpoolL69 3BX United Kingdom XJTLU-JITRI Academy of Technology Xi’an Jiaotong-Liverpool University Suzhou215123 China School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou215123 China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom Guangzhou511400 China School of Information Science and Technology Nantong University Nantong226019 China

In reality, images often exhibit multiple degradations, such as rain and fog at night (triple degradations). However, in many cases, individuals may not want to remove all degradations, for instance, a blurry lens revealing a beautiful snowy landscape (double degradations). In such scenarios, people may only desire to deblur. These situations and requirements shed light on a new challenge in image restoration, where a model must perceive and remove specific degradation types specified by human commands in images with multiple degradations. We term this task Referring Flexible Image Restoration (RFIR). To address this, we first construct a large-scale synthetic dataset called RFIR, comprising 153,423 samples with the degraded image, text prompt for specific degradation removal and restored image. RFIR consists of five basic degradation types: blur, rain, haze, low light and snow while six main sub-categories are included for varying degrees of degradation removal. To tackle the challenge, we propose a novel transformer-based multi-task model named TransRFIR, which simultaneously perceives degradation types in the degraded image and removes specific degradation upon text prompt. TransRFIR is based on two devised attention modules, Multi-Head Agent Self-Attention (MHASA) and Multi-Head Agent Cross Attention (MHACA), where MHASA and MHACA introduce the agent token and reach the linear complexity, achieving lower computation cost than vanilla self-attention and cross-attention and obtaining competitive performances. Our TransRFIR achieves state-of-the-art performances compared with other counterparts and is proved as an effective architecture for image restoration. We release our project at https://***/GuanRunwei/FIR-CP. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Application of Soft Computing Techniques for Predictive Analytics in Financial Markets 6

Application of Soft Computing Techniques for Predictive Anal...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Bhavya, K.R. Dharmaraj, A. Pareek, Prakash Ashok Sathe, Manoj Tiwari, Mohit Manoharan, Geetha Dr. N.S.A.M First Grade College Commerce and Management Karnataka Bangalore India Karpagam Academy of Higher Education Coimbatore Department of Management Tamil Nadu India Vishnu Institute of Technology Department of ECE A.P. Bhimavaram India PES Modern Institute of Business Studies Pune India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering Delhi India School of Business SR University Telanagana Warangal India

ISBN: (纸本)9798350304480

Successful applications of predictive analysis can be found in finance. For these goals, modern soft computing theories are applied. In contrast to other apps, financial applications have unique characteristics. Forecasting is crucial, particularly in the financial industry because it lowers expenses, which can increase revenues and help businesses win the competition. Due to inescapable changes and expansion in every aspect of life, almost every organization on earth is operating in an unpredictable environment. Forecasting becomes increasingly difficult as a result of these developments, which either directly or indirectly affect stock market values. The demand for trustworthy, economical, and efficient forecasting models is therefore great in order to reduce uncertainty as well as risk in investing in the stock market. Academics and information researchers have developed a variety of time series models for the most precise and perfect future prediction. Financial autoregressive time series models have produced precise prediction-capable predictive models like the autoregressive moving average and autoregressive integrated moving average. To predict the closing value of the BSE100 S&P Sensex record every week and every day, discrete wavelet change and wavelet denoising soft computing models are combined with autoregressive models in the continuing work. © 2023 IEEE.

关键词： finance forecasting prediction analysis stock market

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of the Use of Machine Learning Techniques to Optimize the Information Retrieval Process

A Comprehensive Analysis of the Use of Machine Learning Tech...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： S. Hemelatha Kalanandhini. G Prasad B. Chaudhari Rajeev Sharma Jambi Ratna Raja Kumar Dipannita Mondal Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Management Mangalayatan University Aligarh India Department of Computer Engineering Genba Sopanrao Moze College of Engineering Balewadi Pune Maharashtra India Artificial Intelligence And Data Science Department Dr. D.Y.Patil College Of Engineering And Innovation Talegaon

This explores using a system to gain knowledge of strategies that allow you to optimize the facts retrieval manner. Facts retrieval is a complicated technique; it is becoming even more complicated as advancements in generation have furnished tools to make the gathering, employing, and evaluating information less complicated and faster. Research techniques, including artificial intelligence, neural networks, and machine learning, can speed up records retrieval and improve outcomes' accuracy. This look examines the different machine learning techniques to optimize the facts retrieval process and the advantages and downsides of each technique. Furthermore, this study looks at how gadgetstudying algorithms improve a person's enjoyment of retrieval systems and how their use can be integrated into cutting-edge practices. Subsequently, methods for improving the performance of machine learning algorithms are discussed in addition to capacity destiny directions inside the use of gadget studying to optimize statistics retrieval.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of Lung Cancer Model Characteristics on Nanodrugs Tumor Targeting Behavior Based on Convolutional Kernel Extreme Learning Machine Model

Influence of Lung Cancer Model Characteristics on Nanodrugs ...

引用

Advancement in technology (ICONAT), International Conference for

作者： Manthan S. Manavadaria Srikanth Chintakindi Rajasree Rajamohanan S Krishna Prasad P. Janardhan Saikumar Neerav Nishant EC Department CSPIT CHARUSAT Changa Petlad Gujarat India Associate Project Manager Cloud Software Group Department of Computer Science (Artificial intelligence and Data Science) Karpagam Academy of Higher Education Coimbatore India Department of Mechanical Engineering Nitte (Deemed to be University) NMAM Institute of Technology Nitte Udupi India Department of ECE Audisankara College of Engineering and Technology Gudur India Department of CSE School of Engineering Babu Banarasi Das University Lucknow India

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

One of the main killers on a worldwide basis is cancer. In terms of global persistence, lung cancer stands out among the most frequent cancers. For lung cancer, the standard medical approach includes chemotherapy, surgical removal, and radiation therapy. When compared to other methods, this one isn’t extremely targeted and may even damage surrounding healthy cells. There has been recent recognition of nanotechnology as a possible tool for the treatment and management of lung cancer. Preprocessing, feature selection, segmentation, and model training must be executed in this precise sequence to ensure accuracy. As part of the preprocessing, the proposed approach employ the kernel correlation approach. Splitting the input image into smaller pieces with the goal of reducing the overall representation of the image is called image segmentation. To find features with high predictive power and remove redundant ones, feature selection was done in the training cohort. The model was trained using a Convolutional-KELM. As compared to CNN and ELM, the suggested approach performs better. Following implementation of the technique, the accuracy increased by 94.25%.

关键词： Training Image segmentation Accuracy Lungs Lung cancer Feature extraction Convolutional neural networks Kernel Medical diagnostic imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Talent Acquisition in Human Resources with Advanced Deep Learning-Based Resume Screening and Candidate Matching Algorithms

Revolutionizing Talent Acquisition in Human Resources with A...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Dilli Ganesh V Tulovov Erkinjon Laith H. Alzubaidi K. Vijayakumar K. Ranjith Singh A. Kaleel Rahuman Department of Mechanical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences- (SIMATS) Chennai India Department of Audit Tashkent State University of Economics Tashkent Republic of Uzbekistan Department of Computer Techniques Engineering College of technical engineering The Islamic University Najaf Iraq Flextronics Technologies India Pvt.Ltd. Department of Computer Science Karpagam Academy of Higher Education Coimbatore India Department of Electronics and Communication Engineering PSNA College of Engineering and Technology India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

In general, this paper outlines a research agenda to transform the approach to talent management in HR using deep learning strategies for enhanced resume analysis and candidate matching. The above work proposed and developed a system that exploits the most advanced tools of natural language processing, and recent advances in neural networks to correctly parse resumes and the candidates to jobs descriptions. The system deals with the issues of unstructured resume data, the efficient extraction of the required data, and assessment of the candidate on his/her fitness in the given company in terms of his/her technical competencies and compatibility with the company's work culture. Substantial real life data analysis presented in the paper proves high efficiency and equity of the applications. This research also incorporates the ethical questions as well as the ways of dealing with data privacy regulations and the biases in the historical data by applying the explainable AI methods. A questionnaire to the users of the system, which are the HR professionals further verifies the real-world application and usability of the system based on concepts such as ease of use, precision and time economy. In conclusion, the study adds knowledge to the process of establishing ethical and optimal AI implementations in the field of HRM and results in the improvement of talent recruitment strategies and practices promoting fair hiring decisions.

关键词： Deep learning Surveys Ethics Explainable AI Resumes Neural networks Companies Transforms Natural language processing Usability

来源：评论

学校读者我要写书评

暂无评论

Noncontact Doppler Radar-based Heart Rate Detection on the SVD and ANC

Noncontact Doppler Radar-based Heart Rate Detection on the S...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Shi, Qiuxia Hu, Bin Tian, Fuze Zhao, Qinglin Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou University China School of Computer and Communication Lanzhou University of Technology China Key Laboratory of Special Functional Materials and Structural Design Lanzhou University Ministry of Education Lanzhou China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences China Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University Institute of Semiconductors Chinese Academy of Sciences China Engineering Research Center of Open Source Software and Real-Time System Lanzhou University Ministry of Education China

ISBN: (纸本)9781665468190

In the Doppler biological radar-based applications of noncontact measurement of vital signs, effectively extracting heartbeat information from weak thoracic mechanical motion is an important problem to be solved. This study is aimed at extracting heartbeat signal via the technology combined with Short Time Fourier Transform (STFT), Singular Value Decomposition (SVD) and Adaptive Noise Canceller (ANC) from radar recording. The simulated data and the data collected by Doppler radar biosensor realized in laboratory are employed to validate the proposed method. The results show that the proposed method has the ability of detection for the heart rate and heart rate variability indexes in rest state, it has certain advantages in time-consuming and detection accuracy. Therefore, the current method provides another way to process vital sign signals recorded by Doppler radar. © 2022 IEEE.

关键词： Singular value decomposition

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：