检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hong, Lingyi Liu, Zhongying Chen, Wenchao Tan, Chenzhi Feng, Yuang Zhou, Xinyu Guo, Pinxue Li, Jinglun Chen, Zhaoyu Gao, Shuyong Zhang, Wei Zhang, Wenqiang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Shanghai Engineering Research Center of AI&Robotics Academy for Engineering&Technology Fudan University Shanghai China Engineering Research Center of AI&Robotics Ministry of Education Academy for Engineering&Technology Fudan University Shanghai China The Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shell VOS models, existing VOS benchmarks mainly focus on short-term videos lasting about 5 seconds, where objects remain visible most of the time. However, these benchmarks poorly represent practical applications, and the absence of long-term datasets restricts further investigation of VOS in realistic scenarios. Thus, we propose a novel benchmark named LVOS, comprising 720 videos with 296,401 frames and 407,945 high-quality annotations. Videos in LVOS last 1.14 minutes on average, approximately 5 times longer than videos in existing datasets. Each video includes various attributes, especially challenges deriving from the wild, such as long-term reappearing and cross-temporal similar objects. Compared to previous benchmarks, our LVOS better reflects VOS models' performance in real scenarios. Based on LVOS, we evaluate 20 existing VOS models under 4 different settings and conduct a comprehensive analysis. On LVOS, these models suffer a large performance drop, highlighting the challenge of achieving precise tracking and segmentation in real-world scenarios. Attribute-based analysis indicates that key factor to accuracy decline is the increased video length, emphasizing LVOS's crucial role. We hope our LVOS can advance development of VOS in real scenes. Data and code are available at https://***/lvos. ***/. © 2024, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Pushing the Boundaries of ai Chips: From Monolithic 3D CMOS to Cryogenic Computing

Pushing the Boundaries of AI Chips: From Monolithic 3D CMOS ...

引用

2025 Design, Automation and Test in Europe Conference, DATE 2025

作者： Benkhelifa, Mahdi Parihar, Shivendra S. Kar, Anirban Pahwa, Girish Chauhan, Yogesh S. Amrouch, Hussam Technical University of Munich Tum School of Computation Information and Technology Munich Institute of Robotics and Machine Intelligence Ai Processor Design Munich Germany University of California Department of Electrical Engineering and Computer Sciences Berkeley United States National Yang Ming Chiao Tung University International College of Semiconductor Technology Taiwan Indian Institute of Technology Kanpur India

ISBN: (纸本)9783982674100

As CMOS scaling approaches its fundamental limits, the explosive rise of ai and LLMs has unveiled profound bottlenecks in computing architectures. This paper presents two groundbreaking paradigms poised to reshape the landscape of high-performance computing and meet the surging demands of ai-driven workloads. The first paradigm is 3D monolithic integration, a revolutionary approach that achieves unprecedented logic density through Complementary FETs (CFETs), where pMOS and nMOS transistors are vertically stacked, and a dramatic expansion of on-chip memory capacity by integrating memory layers atop logic transistors. The second paradigm leverages the transformative potential of operating chips at cryogenic temperatures where transistors exhibit enhanced performance, and parasitic resistances are substantially minimized. These advancements hold the promise of redefining computing efficiency and performance for the ai era. © 2025 EDAA.

关键词： BiCMOS technology

来源：评论

学校读者我要写书评

暂无评论

D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.

arXiv

引用

arXiv 2024年

作者： Wang, Haoran Mai, Xinji Tao, Zeng Tong, Xuan Lin, Junxiong Wang, Yan Yu, Jiawen Wang, Boyang Yan, Shaoqi Zhao, Qing Zhou, Ziheng Gao, Shuyong Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China School of Information Science and Technology Fudan University Shanghai China Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

The contemporary state-of-the-art of Dynamic Facial Expression Recognition (DFER) technology facilitates remarkable progress by deriving emotional mappings of facial expressions from video content, underpinned by training on voluminous datasets. Yet, the DFER datasets encompass a substantial volume of noise data. Noise arises from low-quality captures that defy logical labeling, and instances that suffer from mislabeling due to annotation bias, engendering two principal types of uncertainty: the uncertainty regarding data usability and the uncertainty concerning label reliability. Addressing the two types of uncertainty, we have meticulously crafted a two-stage framework aiming at Seeking Certain data In extensive Uncertain data (SCIU). This initiative aims to purge the DFER datasets of these uncertainties, thereby ensuring that only clean, verified data is employed in training processes. To mitigate the issue of low-quality samples, we introduce the Coarse-Grained Pruning (CGP) stage, which assesses sample weights and prunes those deemed unusable due to their low weight. For samples with incorrect annotations, the Fine-Grained Correction (FGC) stage evaluates prediction stability to rectify mislabeled data. Moreover, SCIU is conceived as a universally compatible, plug-and-play framework, tailored to integrate seamlessly with prevailing DFER methodologies. Rigorous experiments across prevalent DFER datasets and against numerous benchmark methods substantiates SCIU’s capacity to markedly elevate performance metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Security and Privacy Concerns in “Communication Systems” Blockchain Technology and the Internet of Things

Security and Privacy Concerns in “Communication Systems” B...

引用

Advancement in Electronics & Communication engineering (AECE), International Conference on

作者： Ramiz Salama Sinem Al-Turjman Chadi Altrjman Fadi Al-Turjman R.Om Prakash Satya Prakash Yadav Satvik Vats Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia TURKIYE Artificial Intelligence Engineering Dept AI and Robotics Institute Near East University Nicosia Turkey Department of Chemical Engineering Waterloo University ON Canada Noida Instue Engineering and Technology Greator Noida U.P India Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management(GLBITM) Greater Noida India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

This article examines the security and privacy concerns associated with the integration of blockchain technology and the Internet of Things (IoT) in communication systems. As the IoT continues to grow and evolve, there is an increasing need to ensure the security and privacy of the vast amounts of data generated and exchanged between connected devices. Blockchain technology offers promising solutions for enhancing security and privacy in communication systems; however, it also presents its own set of challenges and vulnerabilities. This article explores the existing literature on the topic and analyzes the materials and methods used in previous studies. The results and discussions delve into the key security and privacy concerns in communication systems with blockchain and IoT, including data integrity, authentication, and confidentiality, scalability, and consensus mechanisms. Finally, the article concludes with recommendations and future directions for addressing these concerns and advancing the security and privacy of communication systems in the context of blockchain technology and the IoT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computational Modeling of Multilevel Organizational Learning: From Conceptual to Computational Mechanisms 1

引用

2nd International Conference on Information Technology, InCITe 2022

作者： Canbaloğlu, Gülay Treur, Jan Wiewiora, Anna Department of Computer Engineering Koç University Istanbul Turkey Social AI Group Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands Center for Safety in Healthcare Delft University of Technology Delft Netherlands School of Management QUT Business School Queensland University of Technology Brisbane Australia

ISBN: (数字)9789811973468

ISBN: (纸本)9789811973451

This paper addresses formalization and computational modeling of multilevel organizational learning, which is one of the major challenges for the area of organizational learning. It is discussed how various conceptual mechanisms in multilevel organizational learning as identified in the literature, can be formalized by computational mechanisms which provide mathematical formalizations that enable computer simulation. The formalizations have been expressed using a self-modeling network modeling approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Indoor 3D Visible Light Positioning Analysis with Channel Estimation Errors 30

Indoor 3D Visible Light Positioning Analysis with Channel Es...

引用

30th International Conference on Systems, Signals and Image Processing, IWSSIP 2023

作者： Bozanis, Dimitrios Evgenidis, Nikos G. Papanikolaou, Vasilis K. Bouzinis, Pavlos S. Tegos, Sotiris A. Dowhuszko, Alexis A. Diamantoulakis, Panagiotis D. Karagiannidis, George K. Department of Electrical and Computer Engineering Thessaloniki54124 Greece Germany University of Macedonia Department of Applied Informatics Thessaloniki54636 Greece Aalto University Department of Communications and Networking Espoo02150 Finland Cyber Security Systems and Applied Ai Research Center Lebanon

ISBN: (纸本)9798350337297

Since radio-frequency signals are affected signifi-cantly by multipath fading, the localization accuracy they offer cannot meet the sixth generations (6G) demanding specifications. On the other hand, visible light positioning (VLP) has emerged as a low cost alternative that takes into account the highly deterministic channel characteristics of visible light communications to provide cm-level accuracy provided that the investigated spaces are adequately covered by LEDs. However, imperfect channel state information and modeling can lead to positioning errors. In this paper, localization accuracy is quantified in terms of channel estimation errors via low complexity lateration algorithm. The channel estimation errors can be caused by a variety of issues and the provided analysis is general so that it can be easily applied to a plethora of applications. Finally, Monte Carlo simulations validate the proposed method and offer valuable insights for the design and performance bounds of VLP systems. © 2023 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Analysis of A Mixed Neural Network Based on CNN and RNN for Computational Model of Sensory Cortex

Analysis of A Mixed Neural Network Based on CNN and RNN for ...

引用

2021 International Conference on Electronics, Circuits and Information engineering, ECIE 2021

作者： Yan, Haoyue Wu, Chenwei University of Toronto Department of Electrical and Computer Engineering Toronto Canada Institute of Ai and Robotics Fudan University Academy for Engineering and Technology Shanghai China

ISBN: (纸本)9781665418690

Under the limitation of modern science, Anatomy is not able to discover the extremely complicated organ - brain's working activities. Along with the development of machine learning and its subset - neural network, named by nearly implementing neurons' connection, scientists found an efficient way to represent brain as a visible approach. Therefore, a new discipline has been created under biology, named as computational neuroscience. Most scientists focus on finding computational models that are closed to fit the specific or general areas of the cortex. Convolutional neural network (CNN) and Recurrent neural network (RNN) are two of them. By taking advantages of those two most popular networks, in this study, a mixed computational model with CNN and RNN might be the best computational model for analogizing brain's activities so far. © 2021 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Brain-computer Interfaces: a New Perspective on the Assessment and Classification of Individuals with Methamphetamine Addiction

引用

SN Comprehensive Clinical Medicine 2023年第1期5卷 1-12页

作者： Zhan, Gege Su, Haolong Wang, Pengchao Wang, Junkongshuai Jiang, Haifeng Zhang, Lihua Kang, Xiaoyang Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Shanghai Mental Center Shanghai Jiao Tong University School of Medicine Shanghai China CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) Chinese Academy of Sciences Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Yiwu Research Institute of Fudan University Yiwu City China

Methamphetamine addiction is a brain disease that causes abnormalities in the structure and function of the brain. EEG, a common signal acquired based on the noninvasive brain-computer interface, can reflect the altered brain activity associated with methamphetamine addiction. EEG-based analysis methods provide a perspective to explore the neural mechanisms of methamphetamine addiction and the effects on brain activity. This paper reports the results of a review of EEG-based assessment and classification of methamphetamine addiction. Current methods commonly used in EEG-based methamphetamine addiction research include traditional resting-state EEG analysis, brain network analysis, and analysis of event-related potentials. A small number of studies have classified methamphetamine addiction and healthy individuals based on resting state EEG features or event-related potentials. EEG is one of the common tools used to examine the effects of methamphetamine on brain function. In follow-up studies, new methods for analyzing resting-state EEG and event-related potentials may help to investigate the neural mechanisms of methamphetamine addiction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Creation of a Mobile App for engineering Students' Online Lab

Creation of a Mobile App for Engineering Students' Online La...

引用

2022 International Conference on Artificial Intelligence of Things and Crowdsensing (aioTCs)

作者： Ramiz Salama Fadi Al-Turjman Department of Computer Engineering Research Center for AI and IoT AI and Robotics Institute Near East University Mersin Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Mersin Turkey Research Center for AI and IoT Faculty of Engineering University of Kyrenia Mersin Turkey

This app helps you access your study materials on your mobile phone. It is an application that allows you to easily communicate with the instructor. Instructors can provide reading materials such as text, images, videos, and links to other sources such as YouTube. It can also be an online video session between instructor and student. Furthermore, this app is a miniature/similar app that adds a laboratory simulation to the university's current online education system (UZEM SYSTEM). This is because the app is aimed at engineering students, and most engineering courses require practicality, so lab internships are required. This allows students to perform laboratory simulations with the help of instructors. The student will need to connect into the app in order to access the contents. Both the teacher and the student will need to select a course from a selection of courses after logging into the site. The chosen course will offer a list of alternatives for learning/teaching techniques, including face-to-face instruction, lab simulations, presentations on a screen, messaging, etc.

关键词： Productivity Video on demand Education Transportation Software Mobile handsets Mobile applications

来源：评论

学校读者我要写书评

暂无评论

Identity-Aware Semi-Supervised Learning for Comic Character Re-Identification

arXiv

引用

arXiv 2023年

作者： Soykan, Gürkan Yuret, Deniz Sezgin, Tevfik Metin Koç University KUIS AI Center Turkey Koç University Computer Engineering Department Turkey

Character re-identification, recognizing characters consistently across different panels in comics, presents significant challenges due to limited annotated data and complex variations in character appearances. To tackle this issue, we introduce a robust semi-supervised framework that combines metric learning with a novel’Identity-Aware’ self-supervision method by contrastive learning of face and body pairs of characters. Our approach involves processing both facial and bodily features within a unified network architecture, facilitating the extraction of identity-aligned character embeddings that capture individual identities while preserving the effectiveness of face and body features. This integrated character representation enhances feature extraction and improves character re-identification compared to re-identification by face or body independently, offering a parameter-efficient solution. By extensively validating our method using in-series and inter-series evaluation metrics, we demonstrate its effectiveness in consistently re-identifying comic characters. Compared to existing methods, our approach not only addresses the challenge of character re-identification but also serves as a foundation for downstream tasks since it can produce character embeddings without restrictions of face and body availability, enriching the comprehension of comic books. In our experiments, we leverage two newly curated datasets: the’Comic Character Instances Dataset’, comprising over a million character instances and the’Comic Sequence Identity Dataset’, containing annotations of identities within more than 3000 sets of four consecutive comic panels that we collected. © 2023, CC BY-NC-SA.

关键词： Embeddings

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：