检索结果-内蒙古大学图书馆

PVT v2:Improved baselines with Pyramid Vision Transformer

Computational Visual Media 2022年第3期8卷 415-424页

作者： Wenhai Wang Enze Xie Xiang Li Deng-Ping Fan Kaitao Song Ding Liang Tong Lu Ping Luo Ling Shao Shanghai AI Laboratory Shanghai 200232China Department of Computer Science and Technology NanjingUniversityNanjing 210023China Department of Computer Science the University ofHong KongHong Kong 999077China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210014China Computer Vision Lab ETH ZurichZurich 8092Switzerland SenseTime Beijing 100080China Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Transformers have recently lead to encouraging progress in computer *** this work,we present new baselines by improving the original Pyramid Vision Transformer(PVT v1)by adding three designs:(i)a linear complexity attention layer,(ii)an overlapping patch embedding,and(iii)a convolutional feed-forward *** these modifications,PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification,detection,and *** particular,PVT v2 achieves comparable or better performance than recent work such as the Swin *** hope this work will facilitate state-ofthe-art transformer research in computer *** is available at https://***/whai362/PVT.

关键词： transformers dense prediction image classification object detection semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence Enabled Student Performance Estimation in the Age of COVID-19

引用

SN computer science 2022年第1期3卷 41页

作者： Bansal, Vipul Buckchash, Himanshu Raman, Balasubramanian Machine Vision Lab Department of Computer Science and Engineering Indian Institute of Technology Roorkee India

The sudden advent of COVID-19 pandemic left educational institutions in a difficult situation for the semester evaluation of students;especially where the online participation was difficult for the students. Such a situation may also happen during a similar disaster in the future. Through this work, we want to study the question: can the deep learning methods be leveraged to predict student grades based on the available performance of students. To this end, this paper presents an in-depth analysis of deep learning and machine learning approaches for the formulation of an automated students’ performance estimation system that works on partially available students’ academic records. Our main contributions are: (a) a large dataset with 15 courses (shared publicly for academic research);(b) statistical analysis and ablations on the estimation problem for this dataset;(c) predictive analysis through deep learning approaches and comparison with other arts and machine learning algorithms. Unlike previous approaches that rely on feature engineering or logical function deduction, our approach is fully data-driven and thus highly generic with better performance across different prediction tasks. The main takeaways from this study are: (a) for better prediction rates, it is desirable to have multiple low weightage tests than few very high weightage exams;(b) the latent space models are better estimators than sequential models;(c) deep learning models have the potential to very accurately estimate the student performance and their accuracy only improves as the training data are increased. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2021.

关键词： COVID-19 Deep neural network Educational institutions Variational auto-encoder

来源：评论

学校读者我要写书评

暂无评论

A Constructivism-based Approach to Treemap Literacy in the Classroom

A Constructivism-based Approach to Treemap Literacy in the C...

引用

44th Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2023

作者： Firat, Elif E. Lang, Colm Srinivas, Bhumika Peng, Ilena Laramee, Robert S. Joshi, Alark Department of Computer Engineering Cukurova University Turkey Visualization and Graphics Lab Department of Computer Science University of San Francisco CA United States School of Computer Science University of Nottingham United Kingdom

ISBN: (纸本)9783038682103

Treemaps are a popular representation to show hierarchical as well as part-to-whole relationships in data. While most students are aware of node-link representations/network diagrams based on their K-12 education, treemaps are often a novel representation to them. We present our experience of developing a software using principles from constructivism to help students understand treemaps using linked, side-by-side views of a node-link diagram and a treemap of the same data. Based on the qualitative survey conducted at the end of the intervention, students found the linked views to be beneficial for understanding hierarchical representation of data using treemaps. © 2023 The Authors.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Design of a LiFi System for Short-Distance Communications 14

Design of a LiFi System for Short-Distance Communications

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Devrani, Ashutaosh Darshan, Divya Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350335095

LiFi technology introduces Visible Light communication that uses light as a source to deliver high data speed, which is much greater than that of Wi-Fi. The research paper proposes a communication system that utilizes Light-Fidelity (Li-Fi) technology for short-range wireless communication. The article begins with an introduction to Li-Fi technology and its advantages over traditional wireless communication systems. The paper also highlights the limitations of Li-Fi, including its short range. The authors then present their proposed approach, which includes a transmitter section, a receiver section, and two modes of operation (text and audio). Additionally, the system consists of two applications to demonstrate its functionality: an SOS application and a device on/off application. The paper concludes with a detailed explanation of how the proposed system works and its potential applications in various fields. © 2023 IEEE.

关键词： Visible light communication

来源：评论

学校读者我要写书评

暂无评论

A novel approach to deriving adaboost classifier weights using squared loss function for overlapping speech detection

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Asbai, Nassim Bounazou, Hadjer Zitouni, Sihem Department of Electronics Faculty of Sciences and Technology Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj City34030 Algeria Speech Com. & Signal Proc. Lab. Faculty of Electrical Engineering USTHB Bab Ezzouar City16111 Algeria Department of Computer Science Faculty of Mathematics and Computer Science Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj City34030 Algeria

In this paper, we address the complex problem of detecting overlapping speech segments, a key challenge in speech processing with applications in speaker diarization, automatic transcription, and multi-speaker recognition systems. Traditional approaches, often relying on exponential loss functions within the AdaBoost framework, struggle to maintain robustness in noisy or imbalanced data environments. To enhance detection accuracy, we propose a novel AdaBoost variant—SLFAdaBoost—utilizing a squared loss function specifically tailored for overlapping speech detection. This model demonstrates superior stability and convergence, significantly outperforming conventional methods. Experimental evaluation on the NIST 2005 corpus revealed that SLFAdaBoost achieves an accuracy range of 92.5% to 98.6%, with F1 scores between 95.4% and 99.2%, notably surpassing standard AdaBoost and Random Forest classifiers. Additionally, our model shows resilience in noisy conditions, maintaining precision and recall metrics at higher noise levels than other classifiers. These results underscore SLFAdaBoost's capacity to handle intricate data patterns, offering a more robust solution for real-world speech processing applications where overlapping segments are prevalent. This contribution provides an efficient, high-performing model, advancing the capabilities of ensemble methods in complex audio environments. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models 31

Converging to a Lingua Franca: Evolution of Linguistic Regio...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zeng, Hongchuan Han, Senyu Chen, Lu Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9798891761964

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this ability remain unclear. We observed that the neuron activation patterns of LLMs exhibit similarities when processing the same language, revealing the existence and location of key linguistic regions. Additionally, we found that neuron activation patterns are similar when processing sentences with the same semantic meaning in different languages. This indicates that LLMs map semantically identical inputs from different languages into a "Lingua Franca", a common semantic latent space that allows for consistent processing across languages. This semantic alignment becomes more pronounced with training and increased model size, resulting in a more language-agnostic activation pattern. Moreover, we found that key linguistic neurons are concentrated in the first and last layers of LLMs, becoming denser in the first layers as training progresses. Experiments on BLOOM and LLaMA2 support these findings, highlighting the structural evolution of multilingual LLMs during training and scaling up. This paper provides insights into the internal workings of LLMs, offering a foundation for future improvements in their cross-lingual capabilities. The codes are available at: https://***/X-LANCE/LinguaFranca. © 2025 Association for Computational Linguistics.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

From Generalist to Specialist: A Survey of Large Language Models for Chemistry 31

From Generalist to Specialist: A Survey of Large Language Mo...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Han, Yang Wan, Ziping Chen, Lu Yu, Kai Chen, Xin X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9798891761964

Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP). However, the predominant pretraining of LLMs on extensive web-based texts remains insufficient for advanced scientific discovery, particularly in chemistry. The scarcity of specialized chemistry data, coupled with the complexity of multi-modal data such as 2D graph, 3D structure and spectrum, present distinct challenges. Although several studies have reviewed Pretrained Language Models (PLMs) in chemistry, there is a conspicuous absence of a systematic survey specifically focused on chemistry-oriented LLMs. In this paper, we outline methodologies for incorporating domain-specific chemistry knowledge and multi-modal information into LLMs, we also conceptualize chemistry LLMs as agents using chemistry tools and investigate their potential to accelerate scientific research. Additionally, we conclude the existing benchmarks to evaluate chemistry ability of LLMs. Finally, we critically examine the current challenges and identify promising directions for future research. Through this comprehensive survey, we aim to assist researchers in staying at the forefront of developments in chemistry LLMs and to inspire innovative applications in the field. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Collaborative Deadline-sensitive Multi-task Offloading in Vehicular-Cloud Networks 17

Collaborative Deadline-sensitive Multi-task Offloading in Ve...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Kumar, Prasanna Sushma, S.A. Chandrasekaran, K. Addya, Sourav Kanti National Institute of Technology Karnataka Cloud and Smart System Services Lab Department of Computer Science and Engineering Surathkal India Siddaganga Institute of Technology Cloud and Smart System Services Lab Tumakuru India

ISBN: (纸本)9798331531195

With the growing technological advancements in the Internet and advanced functionalities in vehicular networks, it becomes crucial to execute tasks quickly and efficiently. However, the limited onboard computational capacity and vehicle mobility make it challenging to accomplish latency-sensitive tasks efficiently. Task offloading provides a promising solution to overcome these challenges. Cloud data centers provide efficient solutions, but returning the results to the vehicles takes longer due to the large physical distance. Leveraging edge servers to execute latency-sensitive tasks provides a fast, interactive response and less transmission cost. However, in a dynamic network, vehicles will be in constant motion with varying speeds, resulting in frequent handoffs from one base station to another. Our proposed work aims to select the optimal nodes to perform binary offloading with minimum cost using the collaborative vehicular network. We use a greedy-based offloading approach to address these challenges and achieve better quality-of-service and quality-of-experience in a dynamic environment to minimize costs, delay reduction ratio, and satisfaction ratio. The proposed work outperforms the baseline by 60.44%, 53.43% in reducing total system cost, delay reduction ratio, and 36% improvement in the satisfaction ratio compared to baseline algorithms. © 2025 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Optimal Control Problem and Its Application in COVID-19 Transmission Dynamics

Optimal Control Problem and Its Application in COVID-19 Tran...

引用

International Conference on Advanced engineering, Technology and Applications, ICAETA 2024

作者： Rahman, Md. Habibur Uddin, Mahtab Hossain, Yamin Sarkar, Nijam Uddin Islam, Md Aminul Siddique, Nafees Ahmed, Ashek Birahim, Shaikh Afnan Department of Mathematics University of Chittagong Chittagong Bangladesh Institute of Natural Sciences United International University Dhaka Bangladesh Department of Computer Science and Engineering VIT-AP University Andhra Pradesh India Institute of Statistical Research and Training University of Dhaka Dhaka Bangladesh Lead Researcher RNB Lab Dhaka Bangladesh Department of Computer Science American International University Dhaka Bangladesh Department of Computer Science and Engineering Royal University of Dhaka Dhaka Bangladesh

ISBN: (纸本)9783031709234

Optimal control techniques are among the most significant technical concepts that can be applied to medical concerns. Establishing a control law for a particular system mathematical model under specified restrictions to meet a specific optimality criterion is known as optimal control. To evaluate the effect of vaccination on the spread of infectious disease and try to decrease the infected group, an optimal control strategy known as Pontryagin’s principle applied in this project. This work develops and thoroughly analyzes and assesses two crucial COVID-19 therapeutic interventions: immunizing susceptible individuals and treating infected individuals under quarantine. A relevant set of conditions is met by proving the presence, distinctiveness, positivity, and unchanging domain of response, among other essential aspects of the model system. The model shows two equilibrium points: one is disease-free and the other that, under some circumstances, is endemic. The fundamental reproduction number R0 is obtained using the next-generation matrix technique, and the model’s dynamic behavior is thoroughly examined. When the corresponding primary reproduction number is smaller than unity, the analytical study shows that the unaffected-by-illness balance approach is both globally and locally stable over time, indicating that COVID-19 has died out in the population. Additionally, anytime the corresponding primary reproduction number surpasses a unity, suggesting that COVID-19 becomes established among the population. The primary reproduction number is subjected to a sensitivity analysis to determine the most critical factors that influence the spread of infection and its control. These are factors that intervention efforts should focus on. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Personal and ubiquitous computing, special issue: "Sonic experiences: interaction, connectivity, and multi-sensory technologies"

引用

Personal and Ubiquitous Computing 2023年第5期27卷 1779-1781页

作者： Turchet, Luca Chamberlain, Alan Kallionpää, Maria Department of Information Engineering and Computer Science University of Trento Trento Italy Mixed Reality Lab School of Computer Science University of Nottingham Nottingham United Kingdom KreativInstitut.OWL Hochschule Für Musik Detmold Detmold Germany

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：