检索结果-内蒙古大学图书馆

International Electrical engineering Congress (iEECON)

作者： Ian Grout Lenore Mullin Department of Electronic and Computer Engineering Faculty of Science and Engineering University of Limerick Limerick Ireland Department of Computer Science College of Nanotechnology Science and Engineering University at Albany SUNY Albany U.S.A.

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

Small size, hardware-only, custom data processing cores connected to a host processor are increasingly considered in digital systems design to provide the ability for accelerating data processing operations through hardware acceleration and parallel processing. These can be realized in different forms such as a custom core connected to a host processor on the same die as the processor, as a separate die (e.g., a chiplet) within the same package as the processor or as a separate Integrated Circuit. These require advanced design flows, low-geometry fabrication processes, and suitable test circuit insertion to implement a suitable test strategy. In this paper, the testability of custom hardware cores is considered through test circuit insertion based on the IJTAG standard. The core is to perform data processing operations based on the Mathematics of Arrays and serial communications is based on the Serial Peripheral Interface. This interface is used for both normal operating mode and the IJTAG based test mode. The system design is considered at the pre-synthesis design development stage and identifies architectural considerations for such system designs.

关键词： Fabrication Electrical engineering Memory management Parallel processing Data processing Mathematics Arrays System analysis and design Standards Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Contextual Aligned Tamil Sign Language Retrieval System with Semantic Masked Transformer

Contextual Aligned Tamil Sign Language Retrieval System with...

引用

Visual Analytics and Data Visualization (ICVADV), International Conference on

作者： S Thillai Sivakavi R I Minu Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

The sign language retrieval system, while similar to conventional video retrieval systems, faces distinct challenges that require a thorough understanding of the meanings conveyed through human actions depicted in the videos. Typically, meaningful information is extracted using RGB feature extraction techniques. However, this method can lead to redundancy, as it often fails to capture the global contextual information inherent in each video frame. Additionally, the reliance on RGB features can present significant memory challenges due to the large data requirements associated with processing and storing this information. Consequently, a more efficient approach is necessary to enhance both the accuracy and effectiveness of sign language retrieval. To address these issues, we have implemented a semantic masked transformer architecture specifically tailored for the sign language retrieval task. This innovative system not only incorporates RGB features but also integrates pose features, which are derived from the movements and positions of the signer. By fusing these two types of features based on their similarity, the system can provide a more refined and pertinent retrieval of textual information related to the video frames. Our extensive experiments conducted on a custom dataset designed for Tamil Sign Language demonstrate that this framework significantly outperforms current state-of-the-art methods. These results underscore the effectiveness of combining semantic understanding with advanced feature extraction techniques, ultimately leading to improved accuracy and efficiency in sign language retrieval.

关键词： Training Sign language Accuracy Visual analytics Semantics Redundancy Assistive technologies Feature extraction Transformers Faces

来源：评论

学校读者我要写书评

暂无评论

MCFTNet: Multimodal Cross-layer Fusion Transformer Network for Hyperspectral and LiDAR Data Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12803-12818页

作者： Huang, Wei Wu, Tianren Zhang, Xueyu Li, Liangliang Lv, Ming Jia, Zhenhong Zhao, Xiaobin Ma, Hongbing Vivone, Gemine Xinjiang University School of Computer Science and Technology Urumqi830017 China Xinjiang University Key Laboratory of Signal Detection and Processing Urumqi830017 China Guangxi University School of Computer and Electronic Information Nanning530004 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China Beijing Institute of Technology School of Information and Electronics Beijing100081 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Tsinghua University Department of Electronic Engineering Beijing100084 China National Research Council Tito85050 Italy NBFC National Biodiversity Future Center Palermo90133 Italy

Remote sensing image classification is a popular yet challenging field. Many researchers have combined convolutional neural networks (CNNs) and Transformers for hyperspectral image (HSI) classification tasks. However, in traditional Transformers, shallow-level information does not propagate well to deeper layers, which can lead to spatial variations and overfitting. Moreover, traditional Transformer models use an external classification (CLS) token that is randomly initialized and often struggles to generalize effectively. In this paper, we combine the strengths of HSI and light detection and ranging (LiDAR) data, using LiDAR as an external CLS token, which significantly enhances classification accuracy and reliability. We propose a new multimodal cross-layer fusion transformer network (MCFTNet), integrating CNNs with the latest Transformer networks. It includes a CNN for extracting spatial features and a hybrid cross-patch attention mechanism (HyCrossAttention) for land cover classification, leveraging LiDAR data to generate CLS and HSI patch tokens. More importantly, to reduce the loss of valuable information during the layer-by-layer propagation, we designed cross-layer skip connections. Through adaptive learning, these cross-layer fusions help address the gradient vanishing problem in deep networks while preserving early-layer features. This enables the model to better integrate information from different layers, enhancing both its stability and performance. We carried out in - depth experiments on commonly - used benchmark datasets, specifically, the University of Houston dataset, the Trento dataset, and the University of Southern Mississippi Gulf Park (MUUFL) dataset. We compared the results of the proposed MCFTNet model with those obtained from state-of-the-art Transformer models, classical CNNs, and traditional classifiers. As a result, the MCFTNet model outshone them all in terms of performance. © 2008-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Survey on Video Search Engine Technology: Advances in Video Processing, Speech Recognition, and Indexing

A Survey on Video Search Engine Technology: Advances in Vide...

引用

Advanced Computing Technologies (ICoACT), International Conference on

作者： Vishwa Kumar S K Karunya Surya K Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

This paper is a comprehensive review of recent video search engine technology, focusing on three main areas: video processing, speech recognition, and indexing. With the rise of multimedia in various fields, there is a growing need to process, index, and retrieve video content based on user queries. This paper covers key advancements, including enhanced video frame extraction, natural language processing (NLP) for speech-to-text and indexing strategies for video search. It also discusses current challenges, existing solutions, and future directions and highlights the rapid evolution of video search technology.

关键词： Surveys Reviews Semantics Multimedia computing Search engines Streaming media Natural language processing Video signal processing Indexing Speech to text

来源：评论

学校读者我要写书评

暂无评论

Smart Interaction: Merging Augmented Reality and Internet of Things for Seamless Device Control

Smart Interaction: Merging Augmented Reality and Internet of...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： J. R. V. Jeny B. Sai Mahitha M. Shashank N. Vamsi Krishna Department of Computer Science and Engineering(AI & ML) Vignan Institute of Technology and Science

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

The combination of Augmented Reality (AR) and Internet of Things (IoT), often referred to as AR + IoT, offers exciting possibilities for future research and development. IoT serves as a platform for communication and remote control of connected devices, while AR provides an intuitive interface for visualizing and managing these devices through enhanced, information-rich displays. This research aims to develop an interactive and accessible home automation system that integrates IoT and AR technologies, enabling seamless remote control of electrical devices. Utilizing an ESP32/NodeMCU board interfaced with the Blynk IoT platform, the system supports device management through a mobile application and an AR interface designed in Unity. The AR interface facilitates intuitive interactions via URL-based signals, which are transmitted to the IoT hardware for execution. This dual-control mechanism enhances user flexibility and convenience, making smart home automation more accessible to users with varying technical expertise. The proposed system not only improves user interaction and control efficiency but also demonstrates the potential of AR in augmenting IoT applications, bridging the gap between physical and virtual control environments. Future enhancements could include advanced AR features, voice control, and cloud-based analytics to further optimize system performance and scalability.

关键词： Visualization System performance Scalability Smart homes Systems support Internet of Things Augmented reality Remote control Wireless fidelity Research and development

来源：评论

学校读者我要写书评

暂无评论

BERTing Emotions: Exploring Textual Emotion Recognition using NLP

BERTing Emotions: Exploring Textual Emotion Recognition usin...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： R. Praveen Kumar Pannala Ramya G.Sai Teja V.Rama Krishna Department of Computer Science and Engineering(AI & ML) Vignan Institute of Technology and Science

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Emotion recognition in text is a crucial area within Natural Language Processing (NLP), serving diverse applications such as sentiment analysis, mental health assessment, and human-computer interaction. This study explores the use of Bidirectional Encoder Representations from Transformers (BERT) for this purpose, capitalizing on its bidirectional transformer architecture to grasp intricate contextual relationships in text. By fine tuning a pretrained BERT model on a dataset annotated with emotional categories like happiness, sadness, anger, surprise, and fear, the model achieves precise emotion classification. BERT's pre-trained linguistic knowledge and ability to interpret complex semantic and syntactic patterns provide a strong foundation for this task. Experimental results demonstrate that BERT surpasses traditional machine learning approaches, including Support Vector Machines (SVM) and logistic regression, in terms of accuracy, owing to its advanced contextual embeddings. Additionally, the model exhibits excellent generalization capabilities across diverse emotional expressions, highlighting its effectiveness for emotion-aware NLP applications. This project also leverages Streamlit to develop interactive web applications that integrate NLP-based emotion detection, showcasing its practicality and accessibility for real-world use cases.

关键词： Support vector machines Emotion recognition Sentiment analysis Semantics Bidirectional control Mental health Syntactics Transformers Encoding Tuning

来源：评论

学校读者我要写书评

暂无评论

Novel Deep Learning Architecture for Automated Identification of Obstructive Sleep Apnea from Polysomnographic Data

Novel Deep Learning Architecture for Automated Identificatio...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： S.L. Jany Shabu Indhuja V Jeevitha R J. Refonaa S. Dhamodaran D. Poornima Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Sleep apnea disorder manifests as obstructive sleep apnea, which affects immense portions of society because it causes life-threatening health problems that include cardiovascular disease alongside diabetes and decreased productivity. The diagnosis of OSA through manual methods is both time demanding and expensive and contains a significant potential for human errors while requiring heavy resources. This research presents deep learning automation as the novel approach for automatic OSA detection through polysomnographic assessments. Our proposed system implements Genetics Algorithm optimized machine learning algorithms which include Logistic Regression, Support Vector Machines, Random Forests, Artificial Neural Networks and more. The analysis utilizes data from the Sleep Health and Lifestyle Dataset for preprocessing operations and features extraction that leads to better sleep disorder and stage classification accuracy. Through hyperparameter adjustment the Random Forest predictive model reached 95% F1 score which proved most effective for OSA detection. Through automation the classification process benefits from reliability with scalability and efficiency and produces better patient outcomes.

关键词： Deep learning Support vector machines Productivity Automation Scalability Predictive models Sleep apnea Reliability Random forests Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection

Exploiting VLM Localizability and Semantics for Open Vocabul...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Wentao Bao Kai Li Yuxiao Chen Deep Patel Martin Renqiang Min Yu Kong Department of Computer Science and Engineering Michigan State University Machine Learning Department NEC Laboratories America Departruent of Computer Science Rutgers University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Action detection aims to detect (recognize and localize) human actions spatially and temporally in videos. Existing approaches focus on the closed-set setting where an action detector is trained and tested on videos from a fixed set of action categories. However, this constrained setting is not viable in an open world where test videos inevitably come beyond the trained action categories. In this paper, we address the practical yet challenging Open-Vocabulary Action Detection (OVAD) problem. It aims to detect any action in test videos while training a model on a fixed set of action categories. To achieve such an open-vocabulary capability, we propose a novel method OpenMixer that exploits the inherent semantics and localizability of large vision-language models (VLM) within the family of query-based detection transformers (DETR). Specifically, the OpenMixer is developed by spatial and temporal OpertMixer blocks (S-OMB and T-OMB), and a dynamically fused alignment (DFA) module. The three components collectively enjoy the merits of strong generalization from pretrained VLMs and end-to-end learning from DETR design. Moreover, we established OVAD benchmarks under various settings, and the experimental results show that the OpenMixer performs the best over baselines for detecting seen and unseen actions. We release the codes, models, and dataset splits at https://***/Cogito2012/0penMixer.

关键词： Training Vocabulary computer vision Codes Computational modeling Semantics Detectors Benchmark testing Transformers Videos

来源：评论

学校读者我要写书评

暂无评论

A Diffusion Model Translator for Efficient Image-to-Image Translation

arXiv

引用

arXiv 2025年

作者： Xia, Mengfei Zhou, Yu Yi, Ran Liu, Yong-Jin Wang, Wenping MOE-Key Laboratory of Pervasive Computing Department of Computer Science and Technology Tsinghua University Beijing100084 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Department of Computer Science and Computer Engineering Texas A&M University TX United States

Applying diffusion models to image-to-image translation (I2I) has recently received increasing attention due to its practical applications. Previous attempts inject information from the source image into each denoising step for an iterative refinement, thus resulting in a time-consuming implementation. We propose an efficient method that equips a diffusion model with a lightweight translator, dubbed a Diffusion Model Translator (DMT), to accomplish I2I. Specifically, we first offer theoretical justification that in employing the pioneering DDPM work for the I2I task, it is both feasible and sufficient to transfer the distribution from one domain to another only at some intermediate step. We further observe that the translation performance highly depends on the chosen timestep for domain transfer, and therefore propose a practical strategy to automatically select an appropriate timestep for a given task. We evaluate our approach on a range of I2I applications, including image stylization, image colorization, segmentation to image, and sketch to image, to validate its efficacy and general utility. The comparisons show that our DMT surpasses existing methods in both quality and efficiency. Code will be made publicly available. Copyright © 2025, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

DMWM: Dual-Mind World Model with Long-Term Imagination

arXiv

引用

arXiv 2025年

作者： Wang, Lingyi Shelim, Rashed Saad, Walid Ramakrishnan, Naren Department of Electrical and Computer Engineering Virginia Tech United States Department of Computer Science Virginia Tech United States

Imagination in world models is crucial for enabling agents to learn long-horizon policy in a sample-efficient manner. Existing recurrent state-space model (RSSM)-based world models depend on single-step statistical inference to capture the environment dynamics, and, hence, they are unable to perform long-term imagination tasks due to the accumulation of prediction errors. Inspired by the dual-process theory of human cognition, we propose a novel dual-mind world model (DMWM) framework that integrates logical reasoning to enable imagination with logical consistency. DMWM is composed of two components: an RSSM-based System 1 (RSSM-S1) component that handles state transitions in an intuitive manner and a logic-integrated neural network-based System 2 (LINN-S2) component that guides the imagination process through hierarchical deep logical reasoning. The inter-system feedback mechanism is designed to ensure that the imagination process follows the logical rules of the real environment. The proposed framework is evaluated on benchmark tasks that require long-term planning from the DMControl suite. Extensive experimental results demonstrate that the proposed framework yields significant improvements in terms of logical coherence, trial efficiency, data efficiency and long-term imagination over the state-of-the-art world models. © 2025, CC BY.

关键词： Efficiency

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：