检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jiang, Xin Li, Xiang Ma, Wenjia Fang, Xuezhi Yao, Yiqun Yu, Naitong Meng, Xuying Han, Peng Li, Jing Sun, Aixin Wang, Yequan Beijing Academy of Artificial Intelligence Beijing China AstralForge AI Lab Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Electronic Science and Technology of China Chengdu China Harbin Institute of Technology Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore

Large language models (LLMs) represented by GPT family have achieved remarkable success. The characteristics of LLMs lie in their ability to accommodate a wide range of tasks through a generative approach. However, the flexibility of their output format poses challenges in controlling and harnessing the model's outputs, thereby constraining the application of LLMs in various domains. In this work, we present Sketch, an innovative toolkit designed to streamline LLM operations across diverse fields. Sketch comprises the following components: (1) a suite of task description schemas and prompt templates encompassing various NLP tasks;(2) a user-friendly, interactive process for building structured output LLM services tailored to various NLP tasks;(3) an open-source dataset for output format control, along with tools for dataset construction;and (4) an open-source model based on LLaMA3-8B-Instruct that adeptly comprehends and adheres to output formatting instructions. We anticipate this initiative to bring considerable convenience to LLM users, achieving the goal of "plug-and-play" for various applications. The components of Sketch will be progressively open-sourced at https://***/cofe-ai/Sketch. Copyright © 2024, The Authors. All rights reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Learnable Queries for Image Aesthetics Assessment

arXiv

引用

arXiv 2024年

作者： Xiong, Zhiwei Zhang, Yunfan Shen, Zhiqi Ren, Peiran Yu, Han College of Computing and Data Science Nanyang Technological University Singapore Alibaba-NTU Singapore Joint Research Institute Nanyang Technological University Singapore Alibaba Group Hangzhou China

Image aesthetics assessment (IAA) is attracting wide interest with the prevalence of social media. The problem is challenging due to its subjective and ambiguous nature. Instead of directly extracting aesthetic features solely from the image, user comments associated with an image could potentially provide complementary knowledge that is useful for IAA. With existing large-scale pre-trained models demonstrating strong capabilities in extracting high-quality transferable visual and textual features, learnable queries are shown to be effective in extracting useful features from the pre-trained visual features. Therefore, in this paper, we propose MMLQ, which utilizes multi-modal learnable queries to extract aesthetics-related features from multi-modal pre-trained features. Extensive experimental results demonstrate that MMLQ achieves new state-of-the-art performance on multimodal IAA, beating previous methods by 7.7% and 8.3% in terms of SRCC and PLCC, respectively. © 2024, CC BY.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Expanding and Squeezing Differential Expressed Genes for Insect Fitness Prediction 34

Expanding and Squeezing Differential Expressed Genes for Ins...

引用

34th Australasian Conference on Information Systems, ACIS 2023

作者： Sun, Zhiyong Khan, Md Ayshik Rahman Yang, Yan Ahmed, Khandaker Asif Hossain, Md Zakir Biological Data Science Institute Australian National University Canberra Australia La Trobe University Melbourne Australia Australian Centre for Disease Preparedness Commonwealth Scientific and Industrial Research Organisation Melbourne Australia School of Electrical Electrical Engineering Computing and Mathematical Sciences Curtin University Perth Australia

The study of differential expressed genes (DEG) and making predictions from it is crucial for the advancements in numerous domains such as medical diagnostics and pharmaceutical and agricultural developments as it provides valuable insights into the underlying mechanisms of these sectors. Despite machine learning being one of the most indispensable tools for this, a persistent challenge arises from the high dimensionality of DEG data, where the number of features was notably larger than the number of available samples which would lead to overfitting. Therefore, to combat this critical issue we designed a data dimension adjustment method for DEG data called (DDA-DEG) which selects the important features and resamples the data to improve model generalization. The DDA-DEG method utilizes a GA-based (genetic algorithm) method for feature selection and a CVAE-based (conditional variational autoencoder) method for resampling. In our comprehensive evaluation, we compare the performance of DDA-DEG against four machine learning methods - Random Forest (RF), Support Vector Regression (SVR), Single Layer Feed-forward Neural Network (SLFN), and Extreme Learning Machine (ELM). Alongside GA and CVAE, PCC, PIMP and Robust Regression was also used for feature selection and RO, SMOTER and SMOGN for resampling. But as, GA and CVAE came out on top, the further experiments were continued with them. The results of our extensive experiments reveal that RF exhibits the best RMSE amongst the four methods with raw data (RMSE = 0.1509). Furthermore, applying DDA-DEG leads to a significant improvement in SVR’s performance, reducing its RMSE from 0.1576 with raw data to 0.095 with feature selection and 0.093 with resampling. This significant improvement in results with DDA-DEG undeniably demonstrates the effectiveness of our proposed method in overcoming overfitting and improving predictive performance. Copyright © 2023 Sun, Khan, Yang, Ahmed and Hossain.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Frequency Diverse Array-enabled RIS-aided Integrated Sensing and Communication

引用

IEEE Transactions on Wireless Communications 2025年

作者： Yang, Hanyu Gong, Shiqi Liu, Heng Xing, Chengwen Zhao, Nan Niyato, Dusit Beijing Institute of Technology School of Information and Electronics Beijing100081 China Dalian University of Technology School of Information and Communication Engineering Dalian116024 China Nanyang Technological University College of Computing and Data Science 639798 Singapore

Integrated sensing and communication (ISAC) has been envisioned as a prospective technology to enable ubiquitous sensing and communications in next-generation wireless networks. In contrast to existing works on reconfigurable intelligent surface (RIS) aided ISAC systems using conventional phased arrays (PAs), this paper investigates a frequency diverse array (FDA)-enabled RIS-aided ISAC system, where the FDA aims to provide a distance-angle-dependent beampattern to effectively suppress the clutter, and RIS is employed to establish high-quality links between the BS and users/target. We aim to maximize sum rate by jointly optimizing the BS transmit beamforming vectors, the covariance matrix of the dedicated radar signal, the RIS phase shift matrix, the FDA frequency offsets and the radar receive equalizer, while guaranteeing the required signal-to-clutter-plus-noise ratio (SCNR) of the radar echo signal. To tackle this challenging problem, we first theoretically prove that the dedicated radar signal is unnecessary for enhancing target sensing performance, based on which the original problem is much simplified. Then, we turn our attention to the single-user single-target (SUST) scenario to demonstrate that the FDA-RIS-aided ISAC system always achieves a higher SCNR than its PA-RIS-aided counterpart. Moreover, it is revealed that the SCNR increment exhibits linear growth with the BS transmit power and the number of BS receive antennas. In order to effectively solve this simplified problem, we leverage the fractional programming (FP) theory and subsequently develop an efficient alternating optimization (AO) algorithm based on symmetric alternating direction method of multipliers (SADMM) and successive convex approximation (SCA) techniques. Numerical results demonstrate the superior performance of our proposed algorithm in terms of sum rate and radar SCNR. © 2002-2012 IEEE.

关键词： Beam forming networks

来源：评论

学校读者我要写书评

暂无评论

Predicting Microsatellite Instability from Histology Images with Dilated Neighborhood Attention Transformer in Colorectal Cancer 24

Predicting Microsatellite Instability from Histology Images ...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Chen, Yun-Chi Chao, Tung Phandita, Wimaya Nitya Sun, Tzu-Yu Wang, Huai-Zhi Hsieh, Yi-Hsien Hsu, Le-Yin Lin, Che Taipei Taiwan College of Bioresources and Agriculture NTU Taipei Taiwan National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei Taiwan Graduate Institute of Communication Engineering NTU Taipei Taiwan NTU Data Science Degree Program Taipei Taiwan NTU Department of Electrical Engineering Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan NTU Smart Medicine and Health Informatics Program Taipei Taiwan

ISBN: (纸本)9798331518622

Microsatellite instability (MSI) is a pivotal genetic marker influencing the efficacy of immunotherapy in colorectal cancer. Traditional MSI examination often requires additional genetic or immunohistochemical tests, whereas histology images, widely available in colorectal cancer diagnosis, offer a valuable alternative for MSI prediction. Although Transformer-based models have demonstrated promising outcomes in predicting MSI from histology images, they are hampered by traditional local attention mechanisms that struggle to capture long-range interdependencies and establish a comprehensive global receptive field. In this study, we introduce DiNAT-MSI, a novel framework for histology-based MSI prediction that incorporates the Dilated Neighborhood Attention Transformer (DiNAT). This model enhances global context recognition and substantially expands receptive fields, all without additional computational burden. Our results demonstrate that DiNAT-MSI achieves a superior patientwise AUROC compared to ResNet18 and Swin Transformer, along with commendable explainability. Our work not only illustrates a more accessible diagnostic tool for leveraging histological data but also underscores the potential of Transformerbased models with sophisticated attention designs in advancing precision medicine for colorectal cancer patients. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Multi-video Moment Ranking with Multimodal Clue

arXiv

引用

arXiv 2023年

作者： Hou, Danyang Pang, Liang Lan, Yanyan Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology CAS Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Institute for AI Industry Research Tsinghua University Beijing China

Video corpus moment retrieval (VCMR) is the task of retrieving a relevant video moment from a large corpus of untrimmed videos via a natural language query. State-of-the-art work for VCMR is based on two-stage method. In this paper, we focus on improving two problems of two-stage method: (1) Moment prediction bias: The predicted moments for most queries come from the top retrieved videos, ignoring the possibility that the target moment is in the bottom retrieved videos, which is caused by the inconsistency of Shared Normalization during training and inference. (2) Latent key content: Different modalities of video have different key information for moment localization. To this end, we propose a two-stage model MultI-video raNking with mUlTimodal cluE (MINUTE). MINUTE uses Shared Normalization during both training and inference to rank candidate moments from multiple videos to solve moment predict bias, making it more efficient to predict target moment. In addition, Mutilmdaol Clue Mining (MCM) of MINUTE can discover key content of different modalities in video to localize moment more accurately. MINUTE outperforms the baselines on TVR and DiDeMo datasets, achieving a new state-of-the-art of VCMR. Our code will be available at GitHub. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Imaging: Network Exudate Detection to Classify Abnormalities

Diabetic Retinopathy Imaging: Network Exudate Detection to C...

引用

Intelligent computing and Control for Engineering and Business Systems (ICCEBS)

作者： A. Chinnasamy P. Selvakumari Department of Data Science and Business Systems school of computing SRMIST kattankulathur campus Chennai Department of Computer Science and Engineering Chennai Institute of Technology Chennai Anna University

The DR becomes increasingly common, there is a need to automatically extract and classify disease severity. Due to diabetes problems, about 2% of people with this disease become completely blind, and DR complications make him 10% visually impaired if he has diabetes for 15 years. Furthermore, it plays an important role in the progression of blindness in middle-aged and older adults. If the disease is not recognized as soon as possible, patients can experience a severe stage of irreversible blindness. The shortage of ophthalmologists is a serious problem for the growing number of diabetic patients. Hard exudates must be found to screen and assist in disease monitoring and diagnosis. Therefore, Lloyd's clustering technique was used in this work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Learnable Queries for Image Aesthetics Assessment

Multi-modal Learnable Queries for Image Aesthetics Assessmen...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhiwei Xiong Yunfan Zhang Zhiqi Shen Peiran Ren Han Yu College of Computing and Data Science Nanyang Technological University Singapore Alibaba-NTU Singapore Joint Research Institute Nanyang Technological University Singapore Alibaba Group Hangzhou China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

关键词： Visualization Social networking (online) Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Expanding and Squeezing Differential Expressed Genes for Insect Fitness Prediction 44

Expanding and Squeezing Differential Expressed Genes for Ins...

引用

44th International Conference on Information Systems: Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies, ICIS 2023

作者： Sun, Zhiyong Khan, Ayshik Rahman Yang, Yan Ahmed, Khandaker Asif Hossain, Md Zakir Biological Data Science Institute Australian National University Canberra Australia La Trobe University Melbourne Australia Australian Centre for Disease Preparedness Commonwealth Scientific and Industrial Research Organisation Melbourne Australia School of Electrical Electrical Engineering Computing and Mathematical Sciences Curtin University Perth Australia

ISBN: (纸本)9781713893622

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

CSAKD: Knowledge Distillation with Cross Self-Attention for Hyperspectral and Multispectral Image Fusion

arXiv

引用

arXiv 2024年

作者： Hsu, Chih-Chung Ni, Chih-Chien Lee, Chia-Ming Kang, Li-Wei Institute of Data Science Miin Wu School of Computing National Cheng Kung University Tainan Taiwan Department of Electrical Engineering National Taiwan Normal University Taipei Taiwan

Hyperspectral imaging, capturing detailed spectral information for each pixel, is pivotal in diverse scientific and industrial applications. Yet, the acquisition of high-resolution (HR) hyperspectral images (HSIs) often needs to be addressed due to the hardware limitations of existing imaging systems. A prevalent workaround involves capturing both a high-resolution multispectral image (HR-MSI) and a low-resolution (LR) HSI, subsequently fusing them to yield the desired HR-HSI. Although deep learning-based methods have shown promising in HR-MSI/LR-HSI fusion and LR-HSI super-resolution (SR), their substantial model complexities hinder deployment on resource-constrained imaging devices. This paper introduces a novel knowledge distillation (KD) framework for HR-MSI/LR-HSI fusion to achieve SR of LR-HSI. Our KD framework integrates the proposed Cross-Layer Residual Aggregation (CLRA) block to enhance efficiency for constructing Dual Two-Streamed (DTS) network structure, designed to extract joint and distinct features from LR-HSI and HR-MSI simultaneously. To fully exploit the spatial and spectral feature representations of LR-HSI and HR-MSI, we propose a novel Cross Self-Attention (CSA) fusion module to adaptively fuse those features to improve the spatial and spectral quality of the reconstructed HR-HSI. Finally, the proposed KD-based joint loss function is employed to co-train the teacher and student networks. Our experimental results demonstrate that the student model not only achieves comparable or superior LR-HSI SR performance but also significantly reduces the model-size and computational requirements. This marks a substantial advancement over existing state-of-the-art methods. The source code is available at https://***/ming053l/CSAKD. © 2024, CC BY.

关键词： Image fusion

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：