检索结果-内蒙古大学图书馆

STViT+: improving self-supervised multi-camera depth estimation with spatial-temporal context and adversarial geometry regularization

引用

Applied Intelligence 2025年第5期55卷 1-20页

作者： Chen, Zhuo Zhao, Haimei Hao, Xiaoshuai Yuan, Bo Li, Xiu Shenzhen International Graduate School Tsinghua University Guangdong Shenzhen518055 China School of Computer Science The University of Sydney SydneyNSW2008 Australia Beijing Academy of Artificial Intelligence Beijing China School of Electrical Engineering and Computer Science The University of Queensland BrisbaneQLD4072 Australia

Multi-camera depth estimation has gained significant attention in autonomous driving due to its importance in perceiving complex environments. However, extending monocular self-supervised methods to multi-camera setups introduces unique challenges that existing techniques often fail to address. In this paper, we propose STViT+, a novel Transformer-based framework for self-supervised multi-camera depth estimation. Our key contributions include: 1) the Spatial-Temporal Transformer (STTrans), which integrates local spatial connectivity and global context to capture enriched spatial-temporal cross-view correlations, resulting in more accurate 3D geometry reconstruction;2) the Spatial-Temporal Photometric Consistency Correction (STPCC) strategy that mitigates the impact of varying illumination, ensuring brightness consistency across frames during photometric loss calculation;3) the Adversarial Geometry Regularization (AGR) module, which employs Generative Adversarial Networks to impose spatial constraints by using unpaired depth maps, enhancing performance under adverse conditions such as rain and nighttime driving. Extensive evaluations on large-scale autonomous driving datasets, including Nuscenes and DDAD, confirm that STViT+ sets a new benchmark for multi-camera depth estimation. © The Author(s) 2025.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

A Survey on Hypergraph Mining: Patterns, Tools, and Generators

引用

ACM Computing Surveys 2025年第8期57卷 1-36页

作者： Lee, Geon Bu, Fanchen Eliassi-Rad, Tina Shin, Kijung Kim Jaechul Graduate School of Ai Korea Advanced Institute of Science and Technology Seoul Korea Republic of School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Republic of Khoury College of Computer Sciences Northeastern University Boston United States

Hypergraphs, which belong to the family of higher-order networks, are a natural and powerful choice for modeling group interactions in the real world. For example, when modeling collaboration networks, which may involve not just two but three or more people, the use of hypergraphs allows us to explore beyond pairwise (dyadic) patterns and capture groupwise (polyadic) patterns. The mathematical complexity of hypergraphs offers both opportunities and challenges for hypergraph mining. The goal of hypergraph mining is to find structural properties recurring in real-world hypergraphs across different domains, which we call patterns. To find patterns, we need tools. We divide hypergraph mining tools into three categories: (1) null models (which help test the significance of observed patterns), (2) structural elements (i.e., substructures in a hypergraph such as open and closed triangles), and (3) structural quantities (i.e., numerical tools for computing hypergraph patterns such as transitivity). There are also hypergraph generators, whose objective is to produce synthetic hypergraphs that are a faithful representation of real-world hypergraphs. In this survey, we provide a comprehensive overview of the current landscape of hypergraph mining, covering patterns, tools, and generators. We provide comprehensive taxonomies for each and offer in-depth discussions for future research on hypergraph mining. © 2025 Copyright held by the owner/author(s).

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Damage-Free Neutral Beam Etching for Gate Recess in E-Mode AlGaN/GaN HEMTs

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2025年第5期46卷 705-708页

作者： Chen, Yi-Ho Chu, Fu-Chuan Aslam, Muhammad Lee, Yao-Jen Li, Yiming Samukawa, Seiji National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Graduate Degree Program of College of Electrical and Computer Engineering Hsinchu300093 Taiwan National Chung-Shan Institute of Science and Technology Solid State Devices Section Electronic System Research Division Taoyuan325 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Communications Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

Recess gate etching is a critical technique for achieving enhancement-mode (E-mode) AlGaN/GaN high-electron mobility transistors (HEMTs) because the interface is susceptible to the etching damage. This study fabricates recess gates using the neutral beam etching (NBE) technique. By adjusting the aperture thickness in the NBE apparatus, we simulate both NB-mode and plasma-mode etching. The electrical characteristics of E-mode HEMTs fabricated using these two modes are analyzed and compared through DC, noise, and pulsed IV measurements. The results demonstrate that NB-recessed HEMTs exhibit superior performance. © 1980-2012 IEEE.

关键词： Aluminum gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Two Generic Constructions of MDS Array Codes With Optimal Repair Bandwidth From Two Special Sets

引用

IEEE Transactions on Information Theory 2025年第5期71卷 3582-3601页

作者： Zhu, Hongwei Lv, Jingjie Xia, Shu-Tao Hou, Hanxu Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518055 China Dongguan University of Technology School of Electrical Engineering and Intelligentization Dongguan523808 China City University of Hong Kong Department of Computer Science Hong Kong

The maximum distance separable (MDS) codes are the optimal codes to achieve Singleton bound, providing maximum error tolerance under a given number of parity nodes. Ye and Barg leveraged permutation matrices and Reed-Solomon type codes to devise 7 explicit constructions for constructing MDS array codes with optimal repair property (as known as MSR codes) or even optimal access property. Drawing inspiration from these explicit constructions, we provide two generic constructions for constructing MSR codes from high-rate MDS codes or MDS array codes. In this paper, we introduce the concepts of s-pairwise MDS codes sets and s-pairwise MDS array codes sets. Two generic constructions (Generic Constructions I and II) for constructing the MSR code using the s-pairwise MDS codes sets or the s-pairwise MDS array codes sets are given. Constructions 1 to 3 proposed by Ye and Barg can be regarded as some special cases of Generic Construction I, and Constructions 1 to 3 proposed by Li et al., can be regarded as some special cases of Generic Construction II. It is worth mentioning that Generic Construction II can be applied to any finite field, including the binary field. We also demonstrate how to obtain the s-pairwise MDS code sets and the s-pairwise MDS array code sets from a high-rate MDS code or MDS array code over Fq . We obtain a novel class of MSR codes by utilizing the MDS array codes provided by Lv et al., as component codes according to Generic Construction II. As a byproduct of Constructions 4 to 7, we obtain a new class of MSR codes with optimal access property. Using two types of sets Γ1 and Γ2 with the property that matrices commute, we present several new constructions for MSR codes with the optimal access property over any finite field. In this paper, compared with the constructions over binary field proposed by Li et al., the sub-packetization of our constructions applicable to the binary field is significantly reduced. © 1963-2012 IEEE.

关键词： Reed-Solomon codes

来源：评论

学校读者我要写书评

暂无评论

ML-Driven Compact Models for RRAMs: Addressing Variability and Simulation Efficiency

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2025年第5期46卷 876-879页

作者： Hong, Giyong Huh, In Hyung You, Joo Myung Choe, Jae Kim, Younggu Jeong, Changwook Graduate School of Semiconductor Materials and Devices Engineering Ulsan44919 Korea Republic of Purdue University Elmore Family School of Electrical and Computer Engineering West LafayetteIN47907 United States Innovation Center Samsung Electronics Computational Science and Engineering Team Hwaseong-si18448 Korea Republic of Graduate School of Semiconductor Materials and Devices Engineering The Artificial Intelligence Graduate School Ulsan44919 Korea Republic of

Machine Learning (ML)-based compact modeling provides a promising alternative to traditional physics-based methods, enabling faster development of compact models for novel devices while offering improved predictive performance. For Resistive Random Access Memory (RRAM) devices, several ML-based compact models have been developed. However, these models often face two key challenges: they fail to capture stochastic cycle-to-cycle variations effectively, and they are difficult to accurately convert into Verilog-A models for SPICE simulations. To address these challenges, we propose a novel variation-aware ML-based compact model for RRAM, using modified deep ensemble techniques to account for cycle-to-cycle variations and model uncertainty, along with a newly designed state determination function to accurately capture resistive switching characteristics. Furthermore, by introducing knowledge distillation combined with a pruning-retraining process, the proposed model achieves a 67% reduction in simulation turnaround time while maintaining predictive accuracy, ensuring strong compatibility with SPICE simulations. © 1980-2012 IEEE.

关键词： SPICE

来源：评论

学校读者我要写书评

暂无评论

Unveiling cognitive processes in digital reading through behavioural cues: A hybrid intelligence (HI) approach

引用

British Journal of Educational Technology 2025年第2期56卷 678-711页

作者： Lee, Yoon Migut, Gosia Specht, Marcus Industrial Design Graduate School of Design University of Seoul Seoul Korea Republic of Research Lab Faculty of Education and Psychology University of Oulu Oulu Finland Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands

Learner behaviours often provide critical clues about learners' cognitive processes. However, the capacity of human intelligence to comprehend and intervene in learners' cognitive processes is often constrained by the subjective nature of human evaluation and the challenges of maintaining consistency and scalability. The recent widespread AI technology has been applied to learning analytics (LA), aiming at a more accurate, consistent and scalable understanding of learning to compensate for challenges that human intelligence faces. However, machine intelligence has been criticized for lacking contextual understanding and difficulties dealing with complex human emotions and social cues. In this work, we aim to understand learners' internal cognitive processes based on the external behavioural cues of learners in a digital reading context, using a hybrid intelligence (HI) approach, bridging human and machine intelligence. Based on the behavioural frameworks and the insights from human experts, we scope specific behavioural cues that are known to be relevant to learners' attention regulation, which is highly relevant for learners' cognitive processes. We utilize the public WEDAR dataset with 30 subjects' video data, behaviour annotation and pre–post tests on multiple choice and summarization tasks. We apply the explainable AI (XAI) approach to train the machine learning model so that human evaluators can also understand which behavioural features were essential for predicting the usage of the cognitive processes (ie, higher-order thinking skills [HOTS] and lower-order thinking skills [LOTS]) of learners, providing insights for the next-round feature engineering and intervention design. The result indicates that the dominant use of attention regulation behaviours is a reliable indicator of low use of LOTS with 79.33% prediction accuracy, while reading speed is a valuable indicator for predicting the overall usage of HOTS and LOTS, ranging from 60.66% to 78.66% accuracy,

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Extended Euclidean Algorithm Implementation over Ciphertext Space 2nd

An Extended Euclidean Algorithm Implementation over Ciphert...

引用

2nd International Conference on Security and Information Technologies with AI, Internet Computing and Big-data Applications, SITAIBA 2023

作者： Chi, Po-Wen Lin, Yuan-Pang Wang, Ming-Hung Chuang, Yun-Hsin Department of Computer Science and Information Engineering National Taiwan Normal University Taiwan Taipei Taiwan Department of Computer Science and Information Engineering National Chung Cheng University Taiwan Chiayi Taiwan Engineering Management Graduate Program College of Engineering National Cheng Kung University Taiwan Tainan Taiwan

ISBN: (纸本)9789819777853

Fully homomorphic encryption (FHE) is a useful cryptographic primitive. It makes a third-party manipulate data in the ciphertext space and therefore is a key technology for privacy-preserving outsourcing services. Theoretically, FHE can evaluate any circuits. However, the implementation is not trivial. The reason it lacks lots of basic operations like conditional check and branch control. In this paper, we focus on extended Euclidean algorithm operation over FHE. We introduce the problems we encounter and show how we solve these issues. We implement our design and evaluate its performance on a real computer. Finally, we propose some research directions for our future work. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

A Multifunctional Hydrogel with Multimodal Self-Powered Sensing Capability and Stable Direct Current Output for Outdoor Plant Monitoring Systems

引用

Nano-Micro Letters 2025年第4期17卷 1-24页

作者： Xinge Guo Luwei Wang Zhenyang Jin Chengkuo Lee Department of Electrical&Computer Engineering National University of Singapore4 Engineering Drive 3Singapore 117576Singapore Center for Intelligent Sensors and MEMS(CISM) National University of Singapore5 Engineering Drive 1Singapore 117608Singapore NUS Graduate School-Integrative Sciences and Engineering Program(ISEP) National University of SingaporeSingapore 119077Singapore Research Center for Sustainable Urban Farming(SUrF) National University of SingaporeSingapore 117558Singapore

Smart farming with outdoor monitoring systems is critical to address food shortages and sustainability *** systems facilitate informed decisions that enhance efficiency in broader environmental *** outdoor systems equipped with energy harvesters and self-powered sensors often struggle with fluctuating energy sources,low durability under harsh conditions,non-transparent or non-biocompatible materials,and complex ***,a multifunctional hydrogel is developed,which can fulfill all the above requirements and build selfsustainable outdoor monitoring systems solely by *** can serve as a stable energy harvester that continuously generates direct current output with an average power density of 1.9 W m^(-3)for nearly 60 days of operation in normal environments(24℃,60%RH),with an energy density of around 1.36×10^(7)J m^(-3).It also shows good self-recoverability in severe environments(45℃,30%RH)in nearly 40 days of continuous ***,this hydrogel enables noninvasive and self-powered monitoring of leaf relative water content,providing critical data on evaluating plant health,previously obtainable only through invasive or high-power consumption *** potential extends to acting as other self-powered environmental *** multifunctional hydrogel enables self-sustainable outdoor systems with scalable and low-cost production,paving the way for future agriculture.

关键词： Self-powered sensor Hydrogel Energy harvester Outdoor farming Self-sustainable IoT

来源：评论

学校读者我要写书评

暂无评论

Object-Centric World Model for Language-Guided Manipulation

arXiv

引用

arXiv 2025年

作者： Jeong, Youngjoon Chun, Junha Cha, Soonwoo Kim, Taesup Graduate School of Data Science Department of Electrical and Computer Engineering

A world model is essential for an agent to predict the future and plan in domains such as autonomous driving and robotics. To achieve this, recent advancements have focused on video generation, which has gained significant attention due to the impressive success of diffusion models. However, these models require substantial computational resources. To address these challenges, we propose a world model leveraging object-centric representation space using slot attention, guided by language instructions. Our model perceives the current state as an object-centric representation and predicts future states in this representation space conditioned on natural language instructions. This approach results in a more compact and computationally efficient model compared to diffusion-based generative alternatives. Furthermore, it flexibly predicts future states based on language instructions, and offers a significant advantage in manipulation tasks where object recognition is crucial. In this paper, we demonstrate that our latent predictive world model surpasses generative world models in visuo-linguo-motor control tasks, achieving superior sample and computation efficiency. We also investigate the generalization performance of the proposed method and explore various strategies for predicting actions using object-centric representations. Copyright © 2025, The Authors. All rights reserved.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Trapping-Set-Assisted Decoding for Short-Length Low-Density Parity-Check Codes

引用

IEEE Internet of Things Journal 2025年第9期12卷 11539-11552页

作者： Zamzami, Asif Ali Yu, Zhu-En Wu, Yuh-Tser Lin, Shih-Chun National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei106 Taiwan Universitas Airlangga Department of Robotics and Artificial Intelligence Engineering Surabaya60115 Indonesia National Taiwan University Department of Electrical Engineering Taipei10617 Taiwan Institute of Communications Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan National Taiwan University Department of Electrical Engineering Graduate Institute of Communication Engineering Taipei10617 Taiwan

To guarantee that every device in industrial Internet of Things (IoT) is reliable for fast data exchange, ultrareliable and low-latency communication (URLLC) technology from 5G is crucial. To reduce latency, typically, only up to 1000 code blocklength is allowed. Indeed, a block error rate (BLER) of less than 10-5 and latency of less than 1 ms are achievable in 5G URLLC. The short code blocklength feature is also required in satellite IoT. Though low-density parity-check (LDPC) decoding via belief propagation (BP) shows promise for achieving low BLER with long blocklength, its BLER is high in short LDPC codes due to error-prone patterns, with the trapping set (TS) being one of the most significant patterns. To alleviate the damage of TS, which can be identified offline, we propose two decoding algorithms named dynamic TS-assisted reinforced BP (DTS-RBP) and TS-assisted relaxation for neural-network BP (TSR-NNBP), respectively. Compared with previous works, only proposed TS assisted decoders can meet URLLC requirements under 308 code blocklength at a 3 dB signal-to-noise ratio (SNR). Moreover, under 128 code blocklength for satellite IoT, our DTS-RBP decoder provides the best memory-performance tradeoff with approximately the same number of iterations as BP. © 2014 IEEE.

关键词： 5G mobile communication systems

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：