检索结果-内蒙古大学图书馆

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Ajith, Anirudh Pan, Chris Xia, Mengzhou Deshpande, Ameet Narasimhan, Karthik Department of Computer Science Princeton University United States

ISBN: (纸本)9798891761193

In-context learning (ICL) performs tasks by prompting a large language model (LLM) using an instruction and a small set of annotated examples called demonstrations. Recent work has shown that precise details of the inputs used in the ICL prompt significantly impact performance, which has incentivized instruction selection algorithms. The effect of instruction-choice however is severely underexplored, with existing analyses restricted to shallow subsets of models and tasks, limiting the generalizability of their insights. We develop InstructEval, an ICL evaluation suite to conduct a thorough assessment of these techniques. The suite includes 13 open-sourced LLMs of varying scales from four model families, and covers nine tasks across three categories. Using the suite, we evaluate the relative performance of seven popular instruction selection methods over five metrics relevant to ICL. Our experiments reveal that using curated manually-written instructions or simple instructions without any task-specific descriptions often elicits superior ICL performance overall than that of automatic instruction-induction methods, pointing to a lack of generalizability among the latter. We release our evaluation suite for benchmarking instruction selection approaches and enabling more generalizable methods in this space. © 2024 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

Comparison of Two Novel Environmental Manipulation Methods for Rotating VR Users 10

Comparison of Two Novel Environmental Manipulation Methods f...

引用

10th International Conference on Virtual Reality, ICVR 2024

作者： Krueger, Linda Markham, Charles Bierig, Ralf Maynooth University Computer Science Department Maynooth Ireland

ISBN: (纸本)9798350364231

Redirected walking lets users walk around a small tracking space to move inside a larger virtual world. Segment Addition is a new technique for manipulating the virtual environment to redirect the user inside the tracking space. Segment Addition adds slices to the virtual environment as the user turns in the tracking space, changing the real rotation a user has to complete to reach their goal in the virtual world. Our user study compares Segment Addition to a simpler technique called Moving Goalposts. Moving Goalposts moves the goals inside the environment while keeping the rest of the environment static. It was developed to provide a straightforward means of evaluating Segment *** analysis of the experimental results indicates that users do not notice changes associated with the addition or subtraction of a small number of extra slices. Users' naturalness, comfort and usability scores remained high even after they noticed the change in rotation amount. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Diversity-Optimized Group Extraction in Social Networks

引用

IEEE Transactions on Computational Social Systems 2024年第1期11卷 756-769页

作者： Hsu, Bay-Yuan Chen, Yi-Ling Ho, Ya-Chi Chang, Po-Yuan Chang, Chih-Chieh Shia, Ben-Chang Shen, Chih-Ya National Tsing Hua University Department of Industrial Engineering and Engineering Management Hsinchu30013 Taiwan National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei10607 Taiwan Hsinchu31040 Taiwan Fu Jen Catholic University Department of Business Administration New Taipei City24205 Taiwan National Taiwan University of Science and Technology Management Undergraduate Program Taipei10607 Taiwan National Tsing Hua University Department of Computer Science Hsinchu30013 Taiwan

In this article, we propose to study a novel research problem to boost group performance, that is, social-aware diversity-optimized group extraction (SDGE), which takes into consideration the two important factors: 1) group diversity and 2) social tightness. We prove the NP-hardness of SDGE and propose an effective algorithm, named group shrinking for diversity maximization (GSDM) with a performance guarantee, that is, GSDM is a three-approximation algorithm to the SDGE problem studied in this article. We further propose three effective pruning strategies that are able to boost the efficiency of GSDM but do not deteriorate its performance. We conduct extensive experiments on multiple large-scale real datasets to evaluate the performance of GSDM. The experimental results show that our proposed GSDM outperforms the other baseline approaches significantly, in terms of solution quality and efficiency. Moreover, the experimental results also confirm that our proposed pruning strategies indeed boost the efficiency of the algorithm. © 2014 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Unveiling computer Chess Evolution: Can Machine Learning Detect Historical Trends? 23rd

Unveiling Computer Chess Evolution: Can Machine Learning Det...

引用

23rd IFIP TC 14 International Conference on Entertainment Computing, ICEC 2024

作者： Borghesi, Andrea Ciancarini, Paolo Di Iorio, Angelo Moro, Gianluca Department of Computer Science and Engineering University of Bologna Bologna Italy

ISBN: (纸本)9783031743528

computer Chess and AI are deeply intertwined, addressing similar research issues and proposing solutions that intersect. Even from a historical viewpoint, these two areas are strongly connected. This article presents a historical overview of computer Chess research segmented in four seasons. Our research goal is to report an experiment of using cutting-edge machine learning tools to extract keywords and topics from a large set of scientific articles on computer Chess, aiming at singling out the characterizing differences among the seasons. Moreover, we investigate the relationships between topics across seasons and their evolution. Although the seasons can be identified by clear milestones, we observed a lack of distinct boundaries between their topics. Instead, some issues recur across different seasons, albeit adjusted to new contexts, tools, and technologies. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Document Classification and Data Extraction 3

Document Classification and Data Extraction

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Khurana, Madhav Chaturvedi, Ravi Prakash Mishra, Annu Gupta, Devika Negi, Ishika Mishra, Ambuj Sharma, Hirdesh Jemtec Department of Computer Science & Engineering Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Applications Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350384598

T- Data classification and extraction are fundamental tasks in the field of computer vision and data analysis. This abstract presents an overview of these concepts along with the utilization of Python and OpenCV, a popular computer vision library, in building data extraction tools. Data classification involves organizing data into categories or classes based on certain characteristics or features. It enables efficient data management and analysis by grouping similar data together. In the context of computer vision, data classification often involves categorizing images or videos based on their content, such as identifying objects, scenes, or patterns within them. Data extraction, on the other hand, involves retrieving specific information or features from a dataset. This process is crucial for tasks like data mining, information retrieval, and automated document processing. In computer vision applications, data extraction often entails locating and extracting relevant information from images or videos, such as text, objects, or numerical data. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

CryptStego: Powerful Blend of Cryptography and Steganography for Securing Communications

CryptStego: Powerful Blend of Cryptography and Steganography...

引用

International Conference on Emerging Trends and Applications in Artificial Intelligence, ICETAI 2023

作者： Pandey, Shraiyash Baniya, Pashupati Nand, Parma Hameed, Alaa Ali Bhushan, Bharat Jamil, Akhtar Department of Computer Science and Engineering School of Engineering and Technology Sharda University Greater Noida India Department of Computer Engineering Istinye University Istanbul Turkey Department of Computer Science National University of Computer and Emerging Sciences Islamabad Pakistan

ISBN: (纸本)9783031567278

In today’s era, security is one of the most critical issues in the development of electronic communications applications, especially when sending private data. The data may be encrypted with several algorithms;however, an extra layer of security can improve protection by a significant amount. Therefore, in this paper, we have developed an application, CryptStego, to secure data using two techniques, cryptography and steganography, to transmit data securely. The encryption of original data is executed using Blowfish algorithm, a cryptographic technique. Additionally, the encrypted data is hidden through using Least Significant Bit (LSB), a steganography technique. The implementation of both techniques offers an extensive level of security, since an intruder must firstly identify the encrypted text within the image to attain the encrypted text, then secondly to decrypt using the algorithm to obtain the original message. Therefore, any intruder must encounter multiple levels of security to obtain the original message from the cipher image. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Classification of Millet Cultivars Using Image Processing and Machine Learning Techniques

Classification of Millet Cultivars Using Image Processing an...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Bharambe, Dewendra Aher, Pushpalata Sandip University Department of Computer Science and Engineering Nashik India

ISBN: (纸本)9798331512965

India is one of the leading producers of various millet cultivars. Indian millets are a class of highly nutritious, drought-resistant crops that are mostly cultivated in the country's semi-arid and drought-prone regions. The most popularly cultivated millet varieties in India are Sorghum (Jowar), Pearl millet (Bajra), Barnyard Millet (Bhagar), Foxtail millet (Kangi), Amaranth (Rajgira), Red sorghum (Chikani), Finger millet (Nachani), and White sorghum (Dadar). In addition to being a wholesome dietary source, millets offer several health advantages. Since they don't contain gluten, they're an excellent alternative for anyone with gluten sensitivity or coeliac disease. Additionally low in glycemic index;millets are a great meal choice for diabetics. Each cultivar has a different nutritional composition and uses. Also, the majority of the time the farmers adapted the millet seeds obtained from their crop hence to preserve the purity of seeds and quality of produce it is very important to classify different millet cultivars. However, the classification of millet cultivars is a complex and time-consuming process. Automation in millet cultivar classification becomes greatly beneficial with improved accuracy and efficiency. This study presents the effective classification of eight different millet cultivars using different machine-learning classifiers along with image processing techniques, based on the derived color features. © 2025 IEEE.

关键词： Seed

来源：评论

学校读者我要写书评

暂无评论

MMD-ERE: Multi-Agent Multi-Sided Debate for Event Relation Extraction 31

MMD-ERE: Multi-Agent Multi-Sided Debate for Event Relation E...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Guan, Yong Peng, Hao Hou, Lei Li, Juanzi Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9798891761964

Event relation extraction (ERE) is becoming increasingly important in the era of large language models. An extensive body of research has explored how performance can be further enhanced by the emergence of exciting technologies like chain-of-thought and self-refinement. In this paper, we introduce MMD-ERE, a Multi-agent Multi-sided Debate approach for Event Relation Extraction, which explores the understanding of event relations among different participants before and after debate. Specifically, for organizing the debate, participants are divided into multiple groups, each assigned its own debate topic, and the process effectively integrates both cooperation and confrontation. We also regard the audience as a crucial participant, as their conclusions from an observer's perspective tend to be more objective. In the end, we explore the understanding of event relations among different participants before and after the debate. Experiments across various ERE tasks and LLMs demonstrate that MMD-ERE outperforms established baselines. Further analysis shows that debates can effectively enhance participants' understanding of event relations. © 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

Syncing Music with Emotions Using computer Vision 7

Syncing Music with Emotions Using Computer Vision

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Shekhawat, Raman Tedla, Sai Harshith Peter, J. Selvin Paul Priya Esther, B. SRMIST Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350372816

With more consumers turning to digital platforms to find new music, music recommendation engines have become popular in recent years. Nevertheless, most recommendation engines rely on collaborative filtering methods or a user's historical listening habits, which might not fully represent the user's emotional state or mood. This study suggests a music recommendation engine integrating emotion recognition to deliver more individualized recommendations. The proposed system analyzes the user's tone of voice and facial expressions using machine-learning algorithms to identify enthusiasm, rage, sadness, and happiness. A playlist is then generated by mapping the user's emotional state to a series of musical parameters, such as key, pace, and rhythm. When the system was tested with a dataset of user-generated music playlists, it could predict the user's emotional state with more than 60% accuracy. Additionally, consumers expressed a generally favorable opinion of the suggested playlists, saying they had been introduced to new music they enjoyed and that the playlists had appropriately mirrored their current emotional state. The future scope of this study is to cater to diverse audiences with varying tastes in music and language. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DeepFeatureX Net: Deep Features eXtractors Based Network for Discriminating Synthetic from Real Images 27th

DeepFeatureX Net: Deep Features eXtractors Based Network for...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Pontorno, Orazio Guarnera, Luca Battiato, Sebastiano Department of Mathematics and Computer Science University of Catania Catania Italy

ISBN: (纸本)9783031783043

Deepfakes, synthetic images generated by deep learning algorithms, represent one of the biggest challenges in the field of Digital Forensics. The scientific community is working to develop approaches that can discriminate the origin of digital images (real or AI-generated). However, these methodologies face the challenge of generalization, that is, the ability to discern the nature of an image even if it is generated by an architecture not seen during training. This usually leads to a drop in performance. In this context, we propose a novel approach based on three blocks called Base Models, each of which is responsible for extracting the discriminative features of a specific image class (Diffusion Model-generated, GAN-generated, or REAL) as it is trained by exploiting deliberately unbalanced datasets. The features extracted from each block are then concatenated and processed to discriminate the origin of the input image. Experimental results showed that this approach not only demonstrates good robust capabilities to JPEG compression and other various attacks but also outperforms state-of-the-art methods in several generalization tests. Code, models and dataset are available at https://***/opontorno/block-based_deepfake-detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

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：