检索结果-内蒙古大学图书馆

RADepthNet:Reflectance-aware monocular depth estimation

Virtual Reality & Intelligent Hardware 2022年第5期4卷 418-431页

作者： Chuxuan LI Ran YI Saba Ghazanfar ALI Lizhuang MA Enhua WU Jihong WANG Lijuan MAO Bin SHENG Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Department of State Key Laboratory of Computer Science University of MacaoMacao 999078China Shanghai University of Sports Shanghai 200438China

Background Monocular depth estimation aims to predict a dense depth map from a single RGB image,and has important applications in 3D reconstruction,automatic driving,and augmented ***,existing methods directly feed the original RGB image into the model to extract depth features without avoiding the interference of depth-irrelevant information on depth-estimation accuracy,which leads to inferior *** To remove the influence of depth-irrelevant information and improve the depth-prediction accuracy,we propose RADepthNet,a novel reflectance-guided network that fuses boundary ***,our method predicts depth maps using the following three steps:(1)Intrinsic Image *** propose a reflectance extraction module consisting of an encoder-decoder structure to extract the depth-related *** an ablation study,we demonstrate that the module can reduce the influence of illumination on depth estimation.(2)Boundary Detection.A boundary extraction module,consisting of an encoder,refinement block,and upsample block,was proposed to better predict the depth at object boundaries utilizing gradient constraints.(3)Depth Prediction *** use an encoder different from(2)to obtain depth features from the reflectance map and fuse boundary features to predict *** addition,we proposed FIFADataset,a depth-estimation dataset applied in soccer *** Extensive experiments on a public dataset and our proposed FIFADataset show that our method achieves state-of-the-art performance.

关键词： Monocular depth estimation Deep learning Intrinsic image decomposition

来源：评论

学校读者我要写书评

暂无评论

Performance and power modeling and prediction using MuMMI and 10 machine learning methods

Performance and power modeling and prediction using MuMMI an...

引用

作者： Wu, Xingfu Taylor, Valerie Lan, Zhiling Mathematics & Computer Science Division Argonne National Laboratory University of Chicago LemontIL United States Department of Computer Science Illinois Institute of Technology ChicagoIL United States

Energy-efficient scientific applications require insight into how high performance computing system features impact the applications' power and performance. This insight can result from the development of performance and power models. In this article, we use the modeling and prediction tool MuMMI (Multiple Metrics Modeling Infrastructure) and 10 machine learning methods to model and predict performance and power consumption and compare their prediction error rates. We use an algorithm-based fault-tolerant linear algebra code and a multilevel checkpointing fault-tolerant heat distribution code to conduct our modeling and prediction study on the Cray XC40 Theta and IBM BG/Q Mira at Argonne National laboratory and the Intel Haswell cluster Shepard at Sandia National Laboratories. Our experimental results show that the prediction error rates in performance and power using MuMMI are less than 10% for most cases. By utilizing the models for runtime, node power, CPU power, and memory power, we identify the most significant performance counters for potential application optimizations, and we predict theoretical outcomes of the optimizations. Based on two collected datasets, we analyze and compare the prediction accuracy in performance and power consumption using MuMMI and 10 machine learning methods. © 2022 John Wiley & Sons, Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Framework for Expensive Multitask Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Tan, Shenglian Wang, Yong Sun, Guangyong Pang, Tong Tang, Ke School of Automation Central South University Changsha China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

This paper proposes a surrogate-assisted evolutionary framework (called SELF) to solve expensive multitask optimization problems (ExMTOPs). SELF consists of two main phases: global knowledge transfer phase and local knowledge transfer phase. In the former, a multitask Gaussian process model (MTGP) is established by fusing previously evaluated solutions of multiple optimization tasks. MTGP can capture task-relevant information and the knowledge of landscapes. Then, differential evolution assisted with MTGP is proposed to preselect high-quality candidates. During the preselection, the knowledge of landscapes is transferred among multiple optimization tasks for locating promising regions quickly. In the latter, for each optimization task, Bayesian optimization is adopted to improve the quality of the best individual in the population. Moreover, the improved best individuals in the populations of multiple optimization tasks are adaptively transferred based on a transfer probability, which is computed through the task-relevant information provided by MTGP. By combining these two phases, SELF not only achieves the tradeoff between exploration and exploitation, but also utilizes the global and local knowledge transfer to improve the efficiency for solving ExMTOPs. We test SELF on seven benchmark test problems in the IEEE CEC2017 evolutionary multitask optimization competition. The results demonstrate that the performance of SELF is better than that of other seven advanced methods. In addition, we also apply SELF to deal with two real-world ExMTOPs. The designs provided by SELF exhibit the best performance among all the compared methods, verifying the potential of SELF in practical engineering applications. IEEE

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

Leveraging IR based sequence and graph features for source-binary code alignment 4

Leveraging IR based sequence and graph features for source-b...

引用

4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

作者： Yu, Zhouqian Zhang, Wei Xu, Tao Beijing Information Science and Technology University Computer School Beijing China Beijing Information Science and Technology University Beijing Laboratory of National Economic Security Early-Warning Engineering Beijing China Tsinghua University Department of Computer Science and Technology Beijing China

ISBN: (纸本)9798350394375

Code similarity analysis is a versatile technique that can be applied across various domains, including code clone detection, code search, malware detection, patch analysis, and vulnerability search. The core of source-binary code similarity analysis lies in effective modeling of the both of source code and binary code. Existing researches have overlooked the fact that code has both text and graph structure features, so they usually only use one of these features for modeling. In this paper, we propose a method that combines sequence features based on intermediate representation and program graph features derived from intermediate representation to enhance the capture of program semantics. Our approach involves the parallel embedding and learning of LLVM IR and the derived program graphs, leading to the extraction of the final code feature representation. Furthermore, we employ a triplet-loss network to identify code characteristic disparities and produce similarity rankings. The experimental results have demonstrated that our approach outperforms other models on the baseline, achieving a 6% improvement in accuracy for source-binary code similarity tasks. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Hardware Security in Evolving FinTech Landscape 5th

Hardware Security in Evolving FinTech Landscape

引用

5th International Conference on Computing and Network Communications, CoCoNet 2023

作者： Bhowmik, Biswajit Dongala, Joshitha Reddy Sudhama, Kruthika K. Antony, Reshma Tresa Girish, K.K. Maharshi Sushrut CAS Lab BRICS Laboratory Department of Computer Science and Engineering National Institute of Technology Karnataka Mangalore Surathkal575025 India

ISBN: (纸本)9789819745395

The assimilation of technology into the financial sector, often referred to as FinTech, has brought about a significant transformation. This shift has not only widened the scope of financial inclusivity but has also fundamentally reshaped the contours of financial solutions delivered. As FinTech solutions continue to empower individuals with greater control over their finances through mobile banking, digital wallets, and advanced data analytics, the security of these innovations becomes paramount. While software security has traditionally received more attention, this paper underscores the significance of hardware security, which serves as the foundational infrastructure for software security measures. It delves into the factors used to evaluate hardware security and outlines various categories of hardware attacks. A case study, focusing on point-of-sale (PoS) systems, exemplifies the importance of hardware security in FinTech. Ultimately, this research contributes to a comprehensive understanding of the evolving FinTech landscape and its implications for both financial inclusion and cybersecurity. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Rational 3D object placement based on deep learning based plane detection

引用

Multimedia Tools and Applications 2023年第28期82卷 44555-44576页

作者： Yang, Wei-Jong Lu, Li-Yu Chan, Din-Yuen Department of Artificial Intelligence and Computer Engineering National Chin-Yi University of Technology Taichung Taiwan Telecommunication Laboratories Chunghwa Telecom Co. Ltd. Internet of Things Laboratory Taoyuan Taiwan Department of Computer Science and Information Engineering National Chiayi University Chiayi Taiwan

Effective acquisition of 3D planar features from a 2D image for immersive AR applications is challenging without any 3D depth information. In this paper, we present a novel planar object placement (POP) system for rational insertion of 3D objects on plane surfaces and fitting their plane orientations in a given 2D image. The POP system is composed of an adaptive edge extractor (AEE), a vanishing point detector (VPD), a rational fitting transformer (RFT) and a plane normal detection network (PNDnet), which performs the estimation of planar features. With the inputs of the color image and the guided edge map retrieved by the AEE, the PNDnet based on a gating weighted U-Net, whose gating weights are controlled by global cross-level connection (GCC) blocks, can properly extract 3D information including planar pixel-wise normal map, semantic plane-segmented map and plane-wise normal vectors. Simultaneously, with plane-wise normal vectors and the VPD-estimated vanishing points, the RFT can easily induce the best placement position for projecting the AR object on a destination plane with better coherent 3D perspectives. Besides, the POP system allows the users to make the subtle tunes of 3D orientation to the inserted object for personal preferences. Experimental results show that the proposed POP system, which successfully guides the 3D-inserted objects to match up the surfaces and orientations of the planes in the target image, will become an effective AR tool for the insertion of 3D objects in target images and videos in the future. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Tomato Leaf Disease Detection: Insights into Model Interpretability 26

Explainable AI for Tomato Leaf Disease Detection: Insights i...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Mahmud, Tanjim Barua, Koushick Barua, Anik Basnin, Nanziba Das, Sudhakar Hossain, Mohammad Shahadat Andersson, Karl Rangamati Science and Technology University Department of Computer Science and Engineering Rangamati4500 Bangladesh Leeds Beckett University Department of Computer Science and Engineering United Kingdom University of Chittagong Department of Computer Science and Engineering Chittagong4331 Bangladesh Luleå University of Technology Pervasive and Mobile Computing Laboratory Luleå971 87 Sweden

ISBN: (纸本)9798350359015

Plant diseases pose a significant threat to global food security by limiting access to safe and abundant food sources while impacting agricultural productivity and food safety. To address this challenge, innovative disease detection techniques are crucial. This paper presents a novel approach to tomato leaf disease detection grounded in deep transfer learning. We employ convolutional neural networks (CNNs) to recognize and categorize diseases, leveraging pre-trained models such as EfficientNetB3, Xception, and MobileNetV2. Our experimental results highlight the efficacy of these models, with the CNN achieving an accuracy of 0.92, MobileNetV2 at 0.93, Xception at 0.94 and EfficientNetB3 at 0.993. By combining these machine learning techniques with image processing methods, we create a system capable of diagnosing tomato leaf diseases promptly. The system employs image processing techniques to facilitate disease recognition, enabling automated disease identification as soon as symptoms manifest on leaves or plants. This empowers farmers with timely information and appropriate treatment options, ultimately leading to precise disease management. Furthermore, our research delves into model interpretability by employing Saliency maps and Grad-CAM techniques, providing valuable insights into the decision-making process of our deep learning models. This transparency enhances the trustworthiness of the AI-driven disease detection system, fostering its practical application in agriculture. © 2023 IEEE.

关键词： Convolutional neural network Image diagnosis Image processing Machine learning techniques

来源：评论

学校读者我要写书评

暂无评论

Composing Like an Ancient Chinese Poet:Learn to Generate Rhythmic Chinese Poetry

引用

Journal of computer science & Technology 2023年第6期38卷 1272-1287页

作者：何明陈艳赵洪科刘淇吴乐崔羽曾贵华刘贵全 Department of Electronic Engineering Shanghai Jiao Tong UniversityShanghai 200240China AI Laboratory Lenovo ResearchBeijing 100193China Baidu Incorporated Beijing 100193China College of Management and Economics Tianjin UniversityTianjin 300072China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230027China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China Risk Control Department OPayBeijing 100010China

Automatic generation of Chinese classical poetry is still a challenging problem in artificial ***-cently,Encoder-Decoder models have provided a few viable methods for poetry ***,by reviewing the pri-or methods,two major issues still need to be settled:1)most of them are one-stage generation methods without further polishing;2)they rarely take into consideration the restrictions of poetry,such as tone and ***,some an-cient Chinese poets tended first to write a coarse poem underlying aesthetics and then deliberated its semantics;while oth-ers first create a semantic poem and then refine its *** this basis,in order to better imitate the human creation procedure of poems,we propose a two-stage method(i.e.,restricted polishing generation method)of which each stage fo-cuses on the different aspects of poems(i.e.,semantics and aesthetics),which can produce a higher quality of generated *** this way,the two-stage method develops into two symmetrical generation methods,the aesthetics-to-semantics method and the semantics-to-aesthetics *** particular,we design a sampling method and a gate to formulate the tone and rhyme restrictions,which can further improve the rhythm of the generated *** results demon-strate the superiority of our proposed two-stage method in both automatic evaluation metrics and human evaluation met-rics compared with baselines,especially in yielding consistent improvements in tone and rhyme.

关键词： aesthetics poetry generation polishing semantics two-stage method

来源：评论

学校读者我要写书评

暂无评论

Radiative cooling for passive thermal management towards sustainable carbon neutrality

引用

National science Review 2023年第1期10卷 87-97页

作者： Jun Liang Jiawei Wu Jun Guo Huagen Li Xianjun Zhou Sheng Liang Cheng-Wei Qiu Guangming Tao Wuhan National Laboratory for Optoelectronics and Optics Valley Laboratory Huazhong University of Science and Technology Department of Electrical and Computer Engineering National University of Singapore MOE Key Laboratory of Thermo-Fluid Science and Engineering School of Energy and Power Engineering Xi'an Jiaotong University Key Laboratory of Education Ministry on Luminescence and Optical Information Technology National Physical Experiment Teaching Demonstration CenterDepartment of PhysicsSchool of Physical Science and Engineering Beijing Jiaotong University State Key Laboratory of Material Processing and Die &Mould Technology School of Materials Science and Engineering Huazhong University of Science and Technology

Photonic structures at the wavelength scale offer innovative energy solutions for a wide range of applications,from high-efficiency photovoltaics to passive cooling,thus reshaping the global energy *** cooling based on structural and material design presents new opportunities for sustainable carbon neutrality as a zero-energy,ecologically friendly cooling *** this review,in addition to introducing the fundamentals of the basic theory of radiative cooling technology,typical radiative cooling materials alongside their cooling effects over recent years are summarized and the current research status of radiative cooling materials is outlined and ***,technical challenges and potential advancements for radiative cooling are forecast with an outline of future application scenarios and development *** the future,radiative cooling is expected to make a significant contribution to global energy saving and emission reduction.

关键词： photonic structures radiative cooling energy saving and emission reduction carbon neutrality

来源：评论

学校读者我要写书评

暂无评论

Automated Skin Cancer Detection using Deep Learning with Self-Attention Mechanism

Automated Skin Cancer Detection using Deep Learning with Sel...

引用

2023 International Conference on Computational Intelligence and Sustainable Engineering Solution, CISES 2023

作者： Singh, Himanshi Suganya Devi, K. Gaur, Shraddha Singh Bhattacharjee, Ramanuj National Institute of Technology Silchar Medical Imaging Laboratory Department of Computer Science and Engineering Silchar India

ISBN: (纸本)9798350323917

Skin cancer is a prevalent and potentially fatal disease that affects a large number of individuals worldwide. Detecting skin cancer early is vital for effective treatment and positive patient outcomes. In this research, a deep learning (DL) model is presented that utilizes the VGG19 architecture with self-attention modules to automate skin cancer detection. The proposed model achieved an impressive overall accuracy of 91.4% on HAM10000 dataset and outperformed several standard classification models, proving that incorporating self-attention modules into convolutional neural networks can significantly enhance skin cancer detection systems' efficiency. Nonetheless, the model has certain limitations, such as a limited dataset and lower accuracy for the melanoma class. Thus, further studies are required to improve the model's performance, which could potentially save lives by allowing for early detection and treatment of melanoma. This proposed approach has shown promising results for automating skin cancer detection, and the potential impact of this research is significant for developing more accurate and reliable skin cancer detection systems. © 2023 IEEE.

关键词： Diseases

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：