检索结果-内蒙古大学图书馆

Specificity-preserving RGB-D saliency detection

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation 30

Few-shot Temporal Pruning Accelerates Diffusion Models for T...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Li, Bocheng Gao, Zhujin Zhu, Yongxin Yin, Kun Cao, Haoyu Jiang, Deqiang Xu, Linli School of Computer Science and Technology University of Science and Technology of China China School of Data Science University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tencent YouTu Lab China

ISBN: (纸本)9782493814104

Diffusion models have achieved significant success in computer vision and shown immense potential in natural language processing applications, particularly for text generation tasks. However, generating high-quality text using these models often necessitates thousands of iterations, leading to slow sampling rates. Existing acceleration methods either neglect the importance of the distribution of sampling steps, resulting in compromised performance with smaller number of iterations, or require additional training, introducing considerable computational overheads. In this paper, we present Few-shot Temporal Pruning, a novel technique designed to accelerate diffusion models for text generation without supplementary training while effectively leveraging limited data. Employing a Bayesian optimization approach, our method effectively eliminates redundant sampling steps during the sampling process, thereby enhancing the generation speed. A comprehensive evaluation of discrete and continuous diffusion models across various tasks, including machine translation, question generation, and paraphrasing, reveals that our approach achieves competitive performance even with minimal sampling steps after down to less than 1 minute of optimization, yielding a significant acceleration of up to 400x in text generation tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Clustering analysis for Pythagorean fuzzy sets and its application in multiple attribute decision making

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 7897-7907页

作者： Yang, Lei Li, Deqing Zeng, Wenyi Ma, Rong Xu, Zeshui Yu, Xianchuan School of Data Science and Intelligent Engineering Xiamen Institute of Technology Xiamen China Academy of Foundational Education Neusoft Institute Guangdong Foshan China School of Artificial Intelligence Beijing Normal University Beijing China Business School Sichuan University Chengdu China

Pythagorean fuzzy sets, as a generalization of intuitionistic fuzzy sets, have a wide range of applications in many fields including image recognition, data mining, decision making, etc. However, there is little research on clustering algorithms of Pythagorean fuzzy sets. In this paper, a novel clustering idea under Pythagorean fuzzy environment is presented. Firstly, the concept of feature vector of Pythagorean fuzzy number (PFN) is presented by taking into account five parameters of PFN, and some new methods to compute the similarity measure of PFNs by applying the feature vector are proposed. Furthermore, a fuzzy similarity matrix by utilizing similarity measure of PFNs is established. Later, the fuzzy similarity matrix is transformed into a fuzzy equivalent matrix which is utilized to establish a novel Pythagorean fuzzy clustering algorithm. Based on the proposed clustering algorithm, a novel multiple attribute decision making (MADM) method under Pythagorean fuzzy environment is presented. To illustrate the effectiveness and feasibility of the proposed technique, an application example is offered. © 2024 – IOS Press. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Machine Lerning-Based Analysis of Psychological Issues and Game Intervention for College Students 4

Machine Lerning-Based Analysis of Psychological Issues and G...

引用

4th International Conference on Educational technology, ICET 2024

作者： Guo, Tianhang Yan, Jiaxuan Cao, Can Xiong, Kang Chen, Peiwen Yang, Huali Wuhan Textile University School of Computer Science and Artificial Intelligence Wu Han China

ISBN: (纸本)9798350376944

This thesis explores the growing mental health problems of today's students, with a special focus on depression among college students. By analyzing relevant data and literature, the possibility of using games as an innovative psychological calming tool to alleviate students' psychological stress is proposed. The paper first introduces the background and severity of students' mental health problems, as well as the limitations of traditional psychological assessment and medication. Then, it elaborates on the game-based psychological assessment technology and the application of decision tree and random forest modeling in analyzing college students' psychological data. Subsequently, the thesis designs and realizes a driving game based on classical music and natural scenery, and verifies the effectiveness of the game in relieving stress through experiments. Finally, the importance and potential of the game for students' mental health are summarized, and future research directions are envisioned. The thesis provides new ideas and methods to improve students' mental health and provide better psychological support and assistance to students. © 2024 IEEE.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Wearable Location Tracker During Disaster using AI and IoT 3

Wearable Location Tracker During Disaster using AI and IoT

引用

3rd International Conference on Applied artificial intelligence and Computing, ICAAIC 2024

作者： Praveen, P. Kumar, K. Pranay Sr University School of Computer Science & Artificial Intelligence Telangana State Warangal India

ISBN: (纸本)9798350375190

The combination of artificial intelligence (AI) and the Internet of Things (IoT) has improved the capabilities of location trackers, especially in disaster management. This brief explores the collaboration between AI and the Internet of Things to improve the efficiency and effectiveness of tracking devices in the field in the event of an incident. Wearable location trackers equipped with IoT sensors collect real-time data on the wearer's movements, environmental conditions, and vital signs. AI algorithms process this data, enabling the device to distinguish between normal activities and emergency situations. Machine learning algorithms enable the device to learn from historical data, improving its predictive capabilities and reducing false alarms. This design of GPS location tracking is through a satellite. It includes AI and IoT for receiving the data in case of disaster. To view the location, the person can use any device connected to the Internet. The parameters we can find through this are the scalable map of the surrounding area, latitude, longitude, speed, and altitude. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Towards Safer Roads: A Comprehensive Review of Object Detection Techniques for Autonomous Vehicles

引用

SN computer science 2025年第5期6卷 1-20页

作者： Parisapogu, Samson Anosh Babu Narla, Nitya Juryala, Aarthi Ramavath, Siddhu Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham Amaravati Campus Andhra Pradesh Amaravati 522 503 India Department of Artificial Intelligence and Data Science Chaitanya Bharathi Institute of Technology Hyderabad 500075 India

Nowadays, people spend a lot of time in travel, and road safety has become an important area of research. As a result, self-driving cars have been gaining popularity in recent years because they have a lot of benefits in terms of reducing traffic congestion and improving road safety, thereby reducing accidents. They also have an environmental benefit as they reduce travel times and hence reduce the usage of fuel. Though a lot of research has already been done in this field, there are always new problems being created and new solutions being found. Apart from self-driving cars, automated navigation also has a huge number of applications. Therefore, it is important to stay up to date about the latest developments in this field. This research is a comprehensive survey that explores and evaluates the different object-detecting algorithms that have been used throughout the years, their advantages, disadvantages, and trade-offs. It also analyses the datasets and benchmarks that have been used for evaluating the models. It aims to identify the gaps in research in this growing field so that it can act as a roadmap for researchers to focus their study on. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning Object detection Road safety Self-driving YOLO

来源：评论

学校读者我要写书评

暂无评论

A New Method for Evaluating the Coverage Performance of LEO Satellite Constellations

A New Method for Evaluating the Coverage Performance of LEO ...

引用

2024 International Conference on Advanced Mechatronic Systems, ICAMechS 2024

作者： Li, Jianlin Zhang, XianFeng Lu, Yong Foshan University School of Computer Science and Artificial Intelligence Foshan China Guangzhou College of Technology and Business School of Engineering Guangzhou China

ISBN: (纸本)9798350366204

The paper proposes a new method to evaluate the coverage performance of Low Earth Orbit (LEO) constellations. Based on the Fibonacci grid, this method introduces the standard deviation of coverage multiplicity as a metric of global coverage uniformity. Moreover, according to the coverage demand deviation, this paper optimizes the allocation of satellite resources of different regions by considering the global population distribution. The simulations on some existing constellations including OneWeb, Kuiper, and Starlink demonstrate that the proposed method can effectively improves the coverage performance analysis of satellite constellation on coverage uniformity and resource utilization efficiency. © 2024 IEEE.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Exploring information hiding in images – problems and measures: a survey

引用

Multimedia Tools and Applications 2025年 1-63页

作者： Khan, Ahmed Sarfaraz, Aaliya School of Computer Science Taylor’s University Subang Jaya Malaysia School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Selangor Darul Ehsan Bandar Sunway47500 Malaysia

The widespread adoption of digital communication technologies across various domains has led to a significant shift towards digitalization. However, this evolution has also introduced vulnerabilities, including unauthorized access, data manipulation, and fabrication by malicious entities, which severely impact the confidentiality and integrity of information. The proliferation of digital images on the internet has facilitated the use of these media for embedding confidential data in a way that prevents detection or extraction by unauthorized third parties. Despite numerous efforts, existing image steganography and watermarking techniques often lack robustness. This paper proposes several novel strategies to enhance the dynamism and imperceptibility of these techniques, integrating cryptographic methods by manipulating the entropy of encrypted images using minimal pixel value differences and applying unique image transformations. Additionally, the study highlights that implementing multi-layered security mechanisms can protect confidential information from modern statistical steganalysis attacks, thereby preserving both the integrity of hidden data and image quality. A comprehensive review of information hiding, specifically focusing on image watermarking and steganography, is provided. Furthermore, this survey outlines key problem statements and offers quantitative metrics for future research in this area. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Titanic Survival Predictor Using Machine Learning Algorithms 4

Titanic Survival Predictor Using Machine Learning Algorithms

引用

4th IEEE Asian Conference on Innovation in technology, ASIANCON 2024

作者： Ali Shaik, Mohammed Sairam, P. Rahul, P. Sadhvik, T. Nithin, P. Sr University School of Computer Science & Artificial Intelligence Telangana State Warangal India

ISBN: (纸本)9798350354218

Presumably, one of the most notorious and catastrophic catastrophes in history is the sinking of the RMS Titanic. Unfortunately, the Titanic sank during her inaugural voyage on April 15, 1912, early in the morning after slamming into an iceberg. Out of 2224 passengers and crew, approximately 1502 perished. Social stratification is a situation where people within a society are separated into various ranking on a hierarchical basis. These groups, also known as social classes are ranked as a social order that is made up of a person's education level, income level Next similar models based on machine learning will be chosen to come to a conclusion whether some groups of individuals are candidates to survive the long space travel. The results of application of the distinct machine learning models were illustrated down one after the other and compared through a general viewpoint of precision. Initially, to get a better feeling of how the data is distributed and what the traits are, the datasets were first examined and prepared. Following that, we ran a variety of machine learning models including Logistic regression, decision trees, random forests, naive Bayes classifier and k nearest neighbors (kNN) for prediction. While conducting our research, we benchmarked the performance of each algorithm using strict assessment techniques like evaluation of variables like the required computational effort, accuracy, precision, recall, and F1 score. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Multi-domain Multi-scale DeepFake Detection for Generalization 4

Multi-domain Multi-scale DeepFake Detection for Generalizati...

引用

4th International Conference on Electronic Information Engineering and computer Communication, EIECC 2024

作者： Liu, Tianju Liu, Yuan Li, Ningyi Shi, Hui Liaoning Normal University School of Computer Science and Artificial Intelligence Liaoning Dalian China

ISBN: (纸本)9798331534622

As deepfake detection technology progresses and application scenarios broaden, it becomes challenging for detection models within a single domain or single scale to handle the complex application environments, leading to limited accuracy and generalization capabilities of the detection models. To address the above problems, we propose a Multi-domain Multi-scale DeepFake Detection model. First, we employ the RetinaFace framework to preprocess and augment the image data, which directs the model's attention to the relevant regions of the image. Next, we utilize the EfficientNet-B0 network for rapid coarse-grained feature extraction. Building on these coarse-grained features, we design two modules to capture forgery traces at multiple levels: a spatial-domain fine-grained feature extraction module based on multi-scale analysis and a frequency-domain fine-grained feature extraction module leveraging the Fast Fourier Transform. Finally, the dual-domain features are fused using a multi-channel attention mechanism, enabling the model to comprehensively analyze images from various perspectives. Additionally, we implement a Particle Swarm Optimization (PSO) strategy to optimize the hyper-parameters of the network model. The proposed model demonstrates significant advantages over other algorithms, particularly in cross-dataset detection, exhibiting strong generalization, robustness, and adaptability. When trained on the FF++ dataset and tested on the Celeb-DF dataset, it achieves an AUC of 91.7%. This represents a 14.8% improvement in cross-dataset performance compared to the best existing model. © 2024 IEEE.

关键词： Frequency domain analysis

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：