检索结果-内蒙古大学图书馆

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Saeed, Ahmad Atif, Haasha Bin Habib, Usman Bilal, Mohsin National University of Computer and Emerging Sciences Dept. of Ai & Data Science Islamabad Pakistan

ISBN: (纸本)9798350328172

Remote sensing imagery is challenging to analyze due to its diverse sources, object image variability and contextual backgrounds. In current era, Aviation Industry is continuously progressing from specific domain of aircraft classification to improving in its safety measures, maintenance procedures and diverse flight operations by utilizing the potential of satellite imagery and Deep Learning methods. This paper highlights and explores the potential of Transfer Learning with state-of-the-art Deep Learning architectures on publicly available Multi Type Aircraft Remote Sensing Imagery datasets. In the same context, our experiments and training mechanism on the state-of-the-art models, like Vision Transformers, ResNet50v2, EfficientNetB0 and InceptionNetV3 outperforms earlier methods on the benchmark remote sensing military aircraft dataset. Our experiments on mentioned Deep learning models yielded, 95%, 93.4%, 92% and 80% classification accuracy due to advance architecture design and fine tuning techniques by allowing them to capture more intricate features and patterns of multifaceted military platforms. This research will provide a valuable resource in the aviation industry in the perspective of aircraft recognition domain by utilizing the power of advance Deep Learning methods to handle the complexity and diversity of remote sensing imagery. © 2023 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical Imaging: Image Processing - From Augmenting Accuracy to Enhancing Efficiency 24

Deep Learning in Medical Imaging: Image Processing - From Au...

引用

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Lakshmi Vara Prasad, G. Murali, A. Bhaskar Reddy, Y.V. Marturi, Haribabu Paul, Valeru Vision Centre for Data Science AI and ML QIS College of Engineering and Technology Andhra Pradesh Ongole India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798400709586

Deep learning has transformed medical imaging by significantly improving accuracy and efficiency in image processing tasks such as disease detection, segmentation, and classification. This paper explores the role of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and other advanced architectures in enhancing image interpretation across various medical imaging modalities. By analyzing MRI, CT, and ultrasound data, this study demonstrates the efficacy of deep learning in automating critical diagnostic tasks, reducing human error, and improving patient outcomes. We propose a comprehensive framework for applying deep learning techniques in medical imaging, providing insights into future advancements in the field. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Partial Multi-View Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 11824-11841页

作者： Zhou, Yuan Guo, Yanrong Hao, Shijie Hong, Richang Luo, Jiebo Ministry of Education Hefei University of Technology The Key Laboratory of Knowledge Engineering with Big Data Hefei230009 China Hefei University of Technology The School of Computer Science and Information Engineering Hefei230009 China University of Rochester The Department of Computer Science RochesterNY14627 United States

It is often the case that data are with multiple views in real-world applications. Fully exploring the information of each view is significant for making data more representative. However, due to various limitations and failures in data collection and pre-processing, it is inevitable for real data to suffer from view missing and data scarcity. The coexistence of these two issues makes it more challenging to achieve the pattern classification task. Currently, to our best knowledge, few appropriate methods can well-handle these two issues simultaneously. Aiming to draw more attention from the community to this challenge, we propose a new task in this paper, called few-shot partial multi-view learning, which focuses on overcoming the negative impact of the view-missing issue in the low-data regime. The challenges of this task are twofold: (i) it is difficult to overcome the impact of data scarcity under the interference of missing views;(ii) the limited number of data exacerbates information scarcity, thus making it harder to address the view-missing issue in turn. To address these challenges, we propose a new unified Gaussian dense-anchoring method. The unified dense anchors are learned for the limited partial multi-view data, thereby anchoring them into a unified dense representation space where the influence of data scarcity and view missing can be alleviated. We conduct extensive experiments to evaluate our method. The results on Cub-googlenet-doc2vec, Handwritten, Caltech102, Scene15, Animal, ORL, tieredImagenet, and Birds-200-2011 datasets validate its effectiveness. The codes will be released at https://***/zhouyuan888888/UGDA. © 1979-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural Computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ASAnalyzer: Attention based Sentiment analyzer for Real-world Sentiment Analysis 20

ASAnalyzer: Attention based Sentiment analyzer for Real-worl...

引用

20th International Conference on Frontiers of Information Technology, FIT 2023

作者： Hussain, Khadim Azhar, Muhammad Lee, Bumshik Iqbal, Asma Affan, Muhammad Ullah Khan, Sajid Comsats University Islamabad Department of Computer Science Sahiwal Pakistan Hong Kong Shue Yan University Department of Applied Data Science Hong Kong Hong Kong Chosun University Department of Computer Science and Software Engineering Korea Republic of Tsinghua University Department of Computer Science China University of Lakki Marwat Department of Computer Science Pakistan

ISBN: (纸本)9798350395785

In this era of big data, a lot of data is produced in various forms every second through various sources. Text data is one of those types that is produced mainly through social media like Twitter, Facebook, YouTube comments, WhatsApp, etc. To know the public's point of view on a specific issue, we can perform sentiment analysis on the text data collected from the above sites. Even though various algorithms have been proposed for sentiment analysis, these algorithms have issues of high time complexity and low context awareness, leading to low classification accuracy. To resolve the above issues, we propose an attention-based sentiment analyzer for real-world sentiment analysis named 'ASAnalyzer', which uses CNN+Attention-Based BiGRU. CNN is used to extract local features from the tweets, and then these features are used by Attention-Based BiGRU to learn the contextual information of the tweets and the long-term dependencies in both directions of the text, which helps to improve accuracy. To validate our algorithm, we used tweet data about the anti-COVID-19 vaccine from Twitter, and the results have shown that our method outperformed other state-of-the-art methods. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Multi‐task framework of precipitation nowcasting

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1350-1363页

作者： Zheng Zhang Chuyao Luo Baoquan Zhang Hao Jiang Bowen Zhang Department of Computer Science Shenzhen Key Laboratory of Internet Information CollaborationHarbin Institute of TechnologyShenzhenChina College of Big Data and Internet Shenzhen Technology UniversityShenzhenChina

Precipitation forecasting plays an important role in disaster warning,agricultural production,and other *** solve this issue,some deep learning methods are proposed to forecast future radar echo images and convert them into rainfall *** spatiotemporal sequence prediction methods are usually based on a ConvRNN structure that combines a Convolutional Neural Network and Recurrent Neural ***,these existing methods ignore the image change prediction,which causes the coherence of the predicted image has ***,these approaches mainly focus on complicating model structure to exploit more historical spatiotemporal ***,they ignore introducing other valuable information to improve *** tackle these two issues,we propose GCMT‐ConvRNN,a multi‐ask framework of *** for precipitation nowcasting as the main task,it combines the motion field estimation and sub‐regression as auxiliary *** this framework,the motion field estimation task can provide motion information,and the sub‐regression task offers future ***,to reduce the negative transfer between the auxiliary tasks and the main task,we propose a new loss function based on the correlation of gradients in different *** experiments show that all models applied in our framework achieve stable and effective improvement.

关键词： deep neural networks motion estimation

来源：评论

学校读者我要写书评

暂无评论

Innovative Video Classification Method based on Deep Learning Approach

引用

Recent Patents on Engineering 2025年第2期19卷 95-107页

作者： Hemamalini, V. Jayasutha, D. Vinothini, V.R. Devi, R. Manjula Kumar, A. Anitha, E. Department of Networking and Communications School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Arjun College of Technology Coimbatore Thamaraikulam India Department of Mathematics Bannari Amman Institute of Technology Sathyamangalam Erode638401 India Department of Computer Science and Design Kongu Engineering College Perundurai Erode638060 India Department of Civil Engineering University Institute of Engineering & Technology Maharshi Dayanand University Rohtak124001 India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore641202 India

Background: The automated classification of videos through artificial neural networks is addressed in this work. To explore the concepts and measure the results, the data set UCF101 is used, consisting of video clips taken from YouTube to recognize actions. The study is carried out with the authors' resources to determine the feasibility of independent research in the area. Methods: This work was developed in the Python programming language using the Keras library with Tensorflow as the back-end. The objective is to develop a network that presents performance compatible with the state of the art in terms of classifying videos according to the actions taken. Results: Given the hardware limitations, there is considerable distance between the implementation possibilities in this work and what is known as the state-of-the-art. Conclusion: Throughout the work, some aspects in which this limitation influenced the development are presented, but it is shown that this realization is feasible and that obtaining expressive results is possible 98.6% accuracy is obtained in the UCF101 data set, compared to the 98 percentage points of the best result ever reported, using, however, considerably fewer resources. In addition, the importance of transfer learning in achieving expressive results as well as the different performances of each architecture are reviewed. Thus, this work may open doors to carry patent-based outcomes. © 2025 Bentham science Publishers.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CoordFlow: Coordinate Flow for Pixel-Wise Neural Video Representation

CoordFlow: Coordinate Flow for Pixel-Wise Neural Video Repre...

引用

data Compression Conference (DCC)

作者： Daniel Silver Ron Kimmel The Faculty of Data and Decisions Science The Taub Faculty of Computer Science

ISBN: (数字)9798331534714

ISBN: (纸本)9798331534721

CoordFlow is a pixel-wise Implicit Neural Representation (INR) framework for video compression, achieving state-of-the-art results among pixel-wise methods and rivaling both frame-wise and classic techniques. By segmenting videos into layers, each represented by specialized neural networks with built-in motion compensation, CoordFlow boosts performance and enables additional practical video tasks.

关键词： Motion segmentation Neural networks data compression Video compression Motion compensation

来源：评论

学校读者我要写书评

暂无评论

All-in-One Weather-Degraded Image Restoration Via Adaptive Degradation-Aware Self-Prompting Model

引用

IEEE Transactions on Multimedia 2025年 27卷 3343-3355页

作者： Wen, Yuanbo Gao, Tao Li, Ziqi Zhang, Jing Zhang, Kaihao Chen, Ting Chang'an University School of Information Engineering Xi'an710064 China Chang'an University School of Data Science and Artificial Intelligence Xi'an710064 China Australian National University School of Computing CanberraACT2601 Australia Harbin Institute of Technology School of Computer Science and Technology Shenzhen150001 China

Existing approaches for all-in-one weather-degraded image restoration suffer from inefficiencies in leveraging degradation-aware priors, resulting in sub-optimal performance in adapting to different weather conditions. To this end, we develop an adaptive degradation-aware self-prompting model (ADSM) for all-in-one weather-degraded image restoration. Specifically, our model employs the contrastive language-image pre-training model (CLIP) to facilitate the training of our proposed latent prompt generators (LPGs), which represent three types of latent prompts to characterize the degradation type, degradation property and image caption. Moreover, we integrate the acquired degradation-aware prompts into the time embedding of diffusion model to improve degradation perception. Meanwhile, we employ the latent caption prompt to guide the reverse sampling process using the cross-attention mechanism, thereby guiding the accurate image reconstruction. Furthermore, to accelerate the reverse sampling procedure of diffusion model and address the limitations of frequency perception, we introduce a wavelet-oriented noise estimating network (WNE-Net). Extensive experiments conducted on eight publicly available datasets demonstrate the effectiveness of our proposed approach in both task-specific and all-in-one applications. © 1999-2012 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Towards Better Accuracy-Efficiency Trade-Offs: Dynamic Activity Inference via Collaborative Learning From Various Width-Resolution Configurations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6723-6738页

作者： Qin, Lutong Zhang, Lei Li, Chengrun Song, Chaoda Cheng, Dongzhou Wang, Shuoyuan Wu, Hao Song, Aiguo Nanjing Normal University School of Electrical and Automation Engineering Nanjing210023 China Shanghai200240 China Case Western Reserve University Department of Computer and Data Sciences ClevelandOH44106 United States University of Macau Department of Computer and Information Science Taipa999078 China Yunnan University School of Information Science and Engineering Kunming650500 China Southeast University Department of Instrument Science and Engineering Nanjing210096 China

Recently, deep neural networks have triumphed over a large variety of human activity recognition (HAR) applications on resource-constrained mobile devices. However, most existing works are static and ignore the fact that the computational budget usually changes drastically across various devices, which prevent real-world HAR deployment. It still remains a major challenge: how to adaptively and instantly tradeoff accuracy and latency at runtime for on-device activity inference using time series sensor data? To address this issue, this article introduces a new collaborative learning scheme by training a set of subnetworks executed at varying network widths when fueled with different sensor input resolutions as data augmentation, which can instantly switch on-the-fly at different width-resolution configurations for flexible and dynamic activity inference under varying resource budgets. Particularly, it offers a promising performance-boosting solution by utilizing self-distillation to transfer the unique knowledge among multiple width-resolution configuration, which can capture stronger feature representations for activity recognition. Extensive experiments and ablation studies on three public HAR benchmark datasets validate the effectiveness and efficiency of our approach. A real implementation is evaluated on a mobile device. This discovery opens up the possibility to directly access accuracy-latency spectrum of deep learning models in versatile real-world HAR deployments. © 2020 IEEE.

关键词： Budget control

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：