检索结果-内蒙古大学图书馆

2025 ieee symposium on computational intelligence in Natural Language processing and Social Media, CI-NLPSoMe 2025

作者： Pereira, Ingryd V. S. T. Cavalcanti, George D. C. Cruz, Rafael M. O. Universidade Federal de Pernambuco Centro de Informática Recife-Pe Brazil Université du Québec École de technologie supérieure Montreal Canada

ISBN: (纸本)9798331508418

Given the volume and speed at which fake news spreads across social media, automatic fake news detection has become a highly important task. However, this task presents several challenges, including extracting textual features that contain relevant information about fake news. Research about fake news detection shows that no single feature extraction technique consistently outperforms the others across all scenarios. Nevertheless, different feature extraction techniques can provide complementary information about the textual data and enable a more comprehensive representation of the content. This paper proposes using multi-view autoencoders to generate a joint feature representation for fake news detection by integrating several feature extraction techniques commonly used in the literature. Experiments on fake news datasets show a significant improvement in classification performance compared to individual views (feature representations). We also observed that selecting a subset of the views instead of composing a latent space with all the views can be advantageous in terms of accuracy and computational effort. © 2025 ieee.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Frequency Analysis for image Denoising Network Pruning

引用

ieee TRANSACTIONS ON image processing 2025年 34卷 1660-1671页

作者： Ren, Dongdong Li, Wenbin Huo, Jing Wang, Lei Pan, Hongbing Gao, Yang Nanjing Univ Sch Elect Sci & Engn Nanjing 210093 Peoples R China Nanjing Univ State Key Lab Novel Software Technol Suzhou Campus Suzhou 215163 Peoples R China Nanjing Univ Sch Intelligence Sci & Technol Suzhou Campus Suzhou 215163 Peoples R China Univ Wollongong Sch Comp & Informat Technol Wollongong NSW 2522 Australia

As a common model compression technique, network pruning is widely used to reduce storage and computational cost of deep models in the resource-constrained regime. However, most current pruning methods are designed for high-level vision tasks, with few developed for low-level vision tasks. We observed that the norm-based pruning criterion, originally designed for high-level vision tasks, is highly unsuitable for low-level image denoising networks. This difference arises because image denoising networks pursue distinct feature granularities and goals compared to typical high-level vision tasks. To address this issue, we propose a novel filter evaluation method, termed High-Frequency Components Pruning (HFCP), specifically tailored for image denoising network pruning. HFCP assesses filter importance based on high-frequency components. To the best of our knowledge, this is the first pruning method designed specifically for image denoising tasks, straightforward and applicable to various types of noise. Furthermore, HFCP enhances the pruned model's high-frequency information content with high reliability and interpretability. This facilitates the network's ability to distinguish high-frequency signals from noise. We comprehensively analyzed multiple image denoising networks and validated HFCP's effectiveness across four mainstream networks.

关键词： image denoising Training Information filters Noise reduction Noise Feature extraction Superresolution image coding Hardware Standards High-frequency components image denoising network pruning low-level vision tasks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Feature Self-Attention in Spiking Neural Networks for Hyperspectral Classification

引用

ieee TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Li, Heng Tu, Bing Liu, Bo Li, Jun Plaza, Antonio Nanjing Univ Informat Sci & Technol Inst Opt & Elect Jiangsu Engn Res Ctr Intelligent Optoelect Sensing Sch Phys & Optoelect EngnState Key Lab Cultivat B Nanjing 210044 Jiangsu Peoples R China China Univ Geosci Fac Comp Sci Wuhan 430074 Peoples R China Univ Extremadura Escuela Politecn Dept Technol Comp & Commun Hyperspectral Comp Lab Caceres 10003 Spain

Hyperspectral image (HSI) classification is crucial for remote sensing research, while its high-dimensional features make traditional algorithms difficult to cope with. Despite the breakthroughs in deep learning, the high computational complexity and energy consumption limit its application in resource-limited environments. Spiking neural networks (SNNs), mimicking the brain's information processing with low power consumption, have emerged as a promising alternative for edge computing. However, SNNs struggle with complex tasks due to the nondifferentiability of spike signals, which complicates training and exhibits limitations in extracting deep features and modeling long-range dependencies. In this article, we propose a novel SNN framework that addresses these challenges by enhancing feature extraction and efficiently capturing dependencies in hyperspectral data. Our framework integrates an adaptive refocusing convolutional layer with a spike self-attention (SSA) mechanism. The adaptive refocusing convolutional layer employs learnable parameters to dynamically adjust the convolutional kernel's response to input spike data, improving feature representation. The adaptive refocusing convolutional layer uses learnable parameters to dynamically adjust kernel responses to input spike data, enhancing feature representation. Experimental results show that this model achieves over 96% classification accuracy in a single time step, significantly surpassing current methods and effectively solving the problem of low accuracy at short time steps in SNNs. Additionally, this framework reduces computational energy consumption by approximately 12.5x compared to similar, offering new potential for edge intelligence applications.

关键词： Hyperspectral imaging Accuracy Feature extraction Convolution computational modeling Spiking neural networks Training image classification Energy consumption Adaptation models Convolutional neural networks (CNNs) hyperspectral image (HSI) classification spike self-attention (SSA) spiking neural networks (SNNs)

来源：评论

学校读者我要写书评

暂无评论

Real-Time Pothole Detection With Edge intelligence and Digital Twin in Internet of Vehicles

引用

ieee INTERNET OF THINGS JOURNAL 2025年第5期12卷 4852-4859页

作者： Saleh, Sana Jolfaei, Alireza Tariq, Muhammad Natl Univ Comp & Emerging Sci Sch Engn Islamabad 44000 Pakistan Flinders Univ S Australia Coll Sci & Engn Adelaide SA 5045 Australia

In intelligent transportation systems (ITSs), computer vision and digital twin (DT) technologies are crucial for enhancing safety and efficiency. High-speed vehicles require timely alert systems to prevent collisions with other vehicles and infrastructure, as even a single misjudgment can lead to severe road accident. Advanced driver-assistance systems (ADASs) and vehicular ad-hoc networks (VANETs) enable vehicle-to-vehicle cooperation, facilitating the exchange of critical alerts. By deploying time-sensitive processing techniques at the edge and utilizing DTs for comprehensive analysis, vehicles can take preemptive actions to avoid accidents. Road potholes contribute to traffic disruptions, the accordion effect, and vehicle damage, making their detection essential. This work explores advanced computer vision techniques implemented at the edge, specifically on vehicles. Roadside units (RSUs) offload DT data, and edge detection results are updated on the DT, providing a control center with accurate road condition information and maintaining a precise virtual replica of the environment. This distributed edge intelligence (DEI) enables rapid decision making with reduced latency while offering a comprehensive view of vehicle lifecycle management through DT data. The proposed algorithm, tested in real time, achieves mean average precision of 85% using YOLOv9t with minimal latency of 3 ms, ensuring effective pothole detection and seamless communication among nearby vehicles.

关键词： image edge detection Real-time systems Computer vision Accuracy YOLO Monitoring computational modeling Cloud computing Automobiles Security digital twin (DT) edge computing intelligent transportation system (ITS) Internet of Vehicles (IoV)

来源：评论

学校读者我要写书评

暂无评论

PEDSA: High-Throughput Pipeline-Based FPGA Accelerator for Convolutional Encoder-Decoder Segmentation Networks

引用

ieee TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2025年第4期44卷 1326-1339页

作者： Jiang, Yuxian Li, Zhan Zhang, Zhihan Wang, Hao Chang, Sheng Wuhan Univ Hongyi Honor Coll Wuhan 430072 Hubei Peoples R China Wuhan Univ Sch Phys & Technol Wuhan 430072 Hubei Peoples R China Wuhan Univ Sch Microelect Wuhan 430072 Hubei Peoples R China

In the era of artificial intelligence (AI), rapidly growing data and computing demands stimulate a shift toward more intelligent processing at the edge in the Internet of Things (IoT). AI application scenarios, such as image segmentation, pose new challenges to the computing capability of edge hardware, which cannot be solved by traditional AI accelerators with the traditional processing element (PE) architecture. Recently, the streaming architecture has received more attention due to its higher performance. To improve the throughput of edge platforms for segmentation tasks, customizing streaming accelerators for segmentation models is now necessary. Based on these motivations, we proposed pipelined encoder-decoder segmentation model accelerator (PEDSA), a fully pipelined streaming accelerator for convolutional encoder-decoder segmentation networks. PEDSA maps all the layers in the network into a pixel-level pipeline. All operations, especially upsampling (unpooling, deconvolution, etc.) which involves complex data rearrangement, are integrated into a regular, concise, and fully on-chip data flow. On Xilinx field-programmable gate arrays (FPGAs), our acceleration of SegNet-Basic and U-Net reached performances of 2676.47 and 7646.29 GOPS, respectively, outperforming previous accelerators for this kind of network. This work provides new ideas for the deployment of segmentation algorithms at the edge.

关键词： Computer architecture Pipelines Streaming media image segmentation System-on-chip Convolution Hardware computational modeling Deconvolution Convolutional neural networks Convolutional neural network (CNN) edge computing hardware accelerator Internet of Things (IoT) pipeline semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Synthetic Feature Augmentation Improves Generalization Performance of Language Models

Synthetic Feature Augmentation Improves Generalization Perfo...

引用

2025 ieee symposium on computational intelligence in Natural Language processing and Social Media, CI-NLPSoMe Companion 2025

作者： Choudhary, Ashok Thiels, Cornelius Salehinejad, Hojjat Mayo Clinic Department of Surgery RochesterMN United States Mayo Clinic Kern Center for the Science of Health Care Delivery RochesterMN United States Mayo Clinic Department of Artificial Intelligence and Informatics RochesterMN United States

ISBN: (纸本)9798331519742

Training and fine-tuning deep learning models, especially large language models (LLMs), on limited and imbalanced datasets poses substantial challenges. These issues often result in poor generalization, where models overfit to dominant classes and underperform on minority classes, leading to biased predictions and reduced robustness in real-world applications. To overcome these challenges, we propose augmenting features in the embedding space by generating synthetic samples using a range of techniques. By upsampling underrepresented classes, this method improves model performance and alleviates data imbalance. We validate the effectiveness of this approach across multiple open-source text classification benchmarks, demonstrating its potential to enhance model robustness and generalization in imbalanced data scenarios. © 2025 ieee.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

S²Mamba: A Spatial-Spectral State Space Model for Hyperspectral image Classification

引用

ieee TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Wang, Guanchun Zhang, Xiangrong Peng, Zelin Zhang, Tianyang Jiao, Licheng Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai 200240 Peoples R China

The land cover analysis using hyperspectral images (HSIs) remains an open problem due to their low spatial resolution and complex spectral information. Recent studies are primarily dedicated to designing Transformer-based architectures for spatial-spectral long-range dependencies modeling, which is computationally expensive with quadratic complexity. Selective structured state space model (SSM;Mamba), which is efficient for modeling long-range dependencies with linear complexity, has recently shown promising progress. However, its potential in HSI processing that requires handling numerous spectral bands has not yet been explored. In this article, we innovatively propose S(2)Mamba, a spatial-spectral SSM for HSI classification, to excavate spatial-spectral contextual features, resulting in more efficient and accurate land cover analysis. In S(2)Mamba, two selective structured SSMs through different dimensions are designed for feature extraction, one for spatial, and the other for spectral, along with a spatial-spectral mixture gate (SMG) for optimal fusion. More specifically, S(2)Mamba first captures spatial contextual relations by interacting each pixel with its adjacent through a patch cross scanning (PCS) module and then explores semantic information from continuous spectral bands through a bidirectional spectral scanning (BSS) module. Considering the distinct expertise of the two attributes in homogenous and complicated texture scenes, we realize the SMG by a group of learnable matrices, allowing for the adaptive incorporation of representations learned across different dimensions. Extensive experiments conducted on HSI classification benchmarks demonstrate the superiority and prospect of S(2)Mamba. The code will be made available at: https://***/PURE-melo/S(2)Mamba.

关键词： Hyperspectral imaging computational modeling Transformers image classification Feature extraction Analytical models Logic gates Data models Data mining Bidirectional control Hyperspectral image (HSI) classification linear complexity spatial-spectral feature fusion spatial-spectral state space model (SSM)

来源：评论

学校读者我要写书评

暂无评论

A Stacked Multi-Layered Perceptron - LLM Model for Extracting the Relations in Textual Descriptions

A Stacked Multi-Layered Perceptron - LLM Model for Extractin...

引用

2025 ieee symposium on computational intelligence in Natural Language processing and Social Media, CI-NLPSoMe Companion 2025

作者： Villuri, Gnaneswar Shaik, Hashmath Doboli, Alex Doboli, Simona Stony Brook University Department of Ece Stony BrookNY United States Hofstra University Department of Cs HempsteadNY United States

ISBN: (纸本)9798331519742

The automated extraction of the relations among the concepts in textual descriptions is important for problems that require creating implementations of those descriptions, e.g., synthesizing engineering designs and computer code. However, relation extraction remains challenging despite significant recent progress in Natural Language processing. This paper proposes a novel, two-layered method to create structural representations of the relations in a text. Inspired by work in neuroscience, an upper layer implemented as a multi-layer perceptron models the behavior of closed class words (words with a fixed meaning), like prepositions and conjunctions. The lower layer prompts a Large Language Model to extract the nouns and verbs, which are then introduced into the structural representation produced by the upper layer. Experiments show an average improvement of 13.6% as compared to using only LLMs. © 2025 ieee.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

From Body Parts to Holistic Action: A Fine-Grained Teacher-Student CLIP for Action Recognition

引用

ieee SIGNAL processing LETTERS 2025年 32卷 1336-1340页

作者： Ou, Yangjun Shi, Xiao Chen, Jia He, Ruhan Liu, Chi Wuhan Text Univ Sch Comp Sci & Artificial Intelligence Wuhan 430200 Peoples R China TCL Corp Res Wuhan 430000 Peoples R China

Action recognition in dynamic video remains challenging, particularly when distinguishing between visually similar actions. While existing methods often rely on holistic representations, they overlook the fine-grained details that are significant for accurate classification. We propose a novel Fine-grained Teacher-student CLIP (FT-CLIP) that integrates body part analysis with holistic action recognition through a teacher-student architecture, bridging the gap between fine-grained action parsing and overall action understanding. The teacher model processes individual body parts alongside specialized description to generate part-specific features, which are then aggregated and distilled into the student model. Through knowledge distillation with learnable prompts, the student model effectively learns to capture subtle action distinctions while maintaining efficient inference. FT-CLIP achieves a more nuanced understanding of complex actions by progressing from detailed body part analysis to comprehensive action recognition. Experiments on Kinetics-TPS under a fully-supervised setting and on HMDB51 and UCF101 under a zero-shot setting demonstrate the effectiveness of our method.

关键词： Training Accuracy computational modeling Motion segmentation image segmentation image recognition Artificial intelligence Visualization Textiles Head Action recognition vision-language learning knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Low Light image Enhancement: A Special Click 2

Low Light Image Enhancement: A Special Click

引用

2nd International Conference on computational intelligence, Communication Technology and Networking, CICTN 2025

作者： Kapoor, Shalini Arora, Yojna Bansal, Nidhi Virdi, Khushwant Ismail, Firdous Sadaf M. Malik, Suraj School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India Department of Computer Science and Engineering Sharda University Uttar Pradesh Greater Noida India Haryana Faridabad India Department of Computer Science and Applications School of Engineering and Technology Sharda University Uttar Pradesh Greater Noida India Nagpur Campus Pune India Department of Computer Science & Engineering IIMT University Uttar Pradesh Meerut India

ISBN: (纸本)9798331530389

Photography and images are an important and integral part of today's world, resulting in the development of multimedia and many other subjects comparable to image processing. The specifications of the camera and camera lens are just not enough hence image processing is always required. Low light photography, the problem gets even bigger because the camera lens fails to capture enough light and hence low light photography depends mostly upon image processing algorithms which help to reduce noise in the image, brighten the image for better overall visual quality and enlighten the hidden dark areas. Many efforts have been put into advancing image quality in little light, but none have given satisfactory results. This research report aims to analyses the techniques used for low-light image improvement and what advancements can be made to advance the image condition further. © 2025 ieee.

关键词： Camera lenses

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：