检索结果-内蒙古大学图书馆

IEEE VLSI Test Symposium (VTS)

作者： Tao Lv Hua-wei Li Xiao-wei Li Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)9781424437696

As the design complexity increases dramatically, results of functional simulation are usually checked through only a part of signals during design verification. It is important, therefore, to consider the observability of internal signals for effective checking. This paper proposes a static observability analysis method to automatically select internal observation signals, which improves the quality of functional verification. A series of formulas are defined to evaluate observability of internal signals, and an algorithm is proposed to locate the sources of low-observability. Such sources, rather than general hard-to-observe signals, are desirable internal observation signals. Experimental results indicate that signals selected by this method can improve the observability of designs more than those randomly selected from hard-to-observe signals.

关键词： Internal observation signals Design verification Static analysis

来源：评论

学校读者我要写书评

暂无评论

StyleGene: Crossover and Mutation of Region-level Facial Genes for Kinship Face Synthesis

StyleGene: Crossover and Mutation of Region-level Facial Gen...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Hao Li Xianxu Hou Zepeng Huang Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

High-fidelity kinship face synthesis has many potential applications, such as kinship verification, missing child identification, and social media analysis. However, it is challenging to synthesize high-quality descendant faces with genetic relations due to the lack of large-scale, high-quality annotated kinship data. This paper proposes RFG (Region-level Facial Gene) extraction framework to address this issue. We propose to use IGE (Image-based Gene Encoder), LGE (Latent-based Gene Encoder) and Gene Decoder to learn the RFGs of a given face image, and the relationships between RFGs and the latent space of Style-GAN2. As cycle-like losses are designed to measure the $\mathcal{L}_{2}$ distances between the output of Gene Decoder and image encoder, and that between the output of LGE and IGE, only face images are required to train our framework, i.e. no paired kinship face data is required. Based upon the proposed RFGs, a crossover and mutation module is further designed to inherit the facial parts of parents. A Gene Pool has also been used to introduce the variations into the mutation of RFGs. The diversity of the faces of descendants can thus be significantly increased. Qualitative, quantitative, and subjective experiments on FIW, TSKinFace, and FF-Databases clearly show that the quality and diversity of kinship faces generated by our approach are much better than the existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GM-DF: Generalized Multi-Scenario Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be available on https://***/laiyingxin2/GM-DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a kind of EUPS for mobile service

引用

Journal of Information and Computational Science 2010年第11期7卷 2248-2257页

作者： Zhang, Xiaodan Zhang, Degan Qiao, Xiaodong Liang, Bing Peng, Hongtao Institute of Scientific and Technical Information of China Beijing 100038 China Tianjin Key Lab. of Intelligent Computing and Novel software Technology Tianjin University of Technology Tianjin 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China Beijing Petroleum Managers Training Institute Beijing 100096 China

In order to support mobile service of long-distance monitoring and controlling UPS based on Web, a kind of design and implementation solution of embedded UPS (EUPS) system is brought forward in this paper. The design and implementation of system is based on ATmega161 and RTL8019AS with TCP/IP protocol suite for communication. In the EUPS system, an embedded file system is designed and implemented which can store the data and index information on a serial EEPROM chip in structured way and communicate with MCU through I2C bus. By embedding the file system into UPS system or other information appliances, users can browse and manipulate local data on the web client side. Based on our experimental tests, the performance of EUPS can meet the requirements of Web-based mobile services. © 2010 Binary Information Press.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Design issues in ZigBee-based sensor network for healthcare applications

Design issues in ZigBee-based sensor network for healthcare ...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Jin Soo Choi Meng Chu Zhou Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA Key Laboratory of Embedded System and Service Computing Ministry of Education University of Tongji Shanghai China ECE Department New Jersey Institute of Technology Newark NJ USA

IEEE 802.15.4/ZigBee sensor networks support small power consumption and node expansion compared to other network standards for WSN. Body sensor networks (BSN) require a number of sensors for sensing medical information from human body, and low power consumption to monitor a patient's status for a long time. However, ZigBee has limited bandwidth and is thus hard to support real time data transmission because of the adoption of CSMA-CA as its medium access control (MAC) protocol. In this paper, we will analyze the reasonable number of nodes, size of payload and packet interval for best QoS for such network. It is found that an appropriate MAC parameters setting can improve the QoS compared to the default setting in IEEE 802.15.4 specification. The effective data rate, average end-to-end delay and packet delivery ratio are found via simulation for various network settings. The results are useful for the construction of ZigBee networks for patient monitoring and care.

关键词： Delay IEEE 802.15 Standards Zigbee Monitoring Payloads Medical services Data models

来源：评论

学校读者我要写书评

暂无评论

DCMTs: Supporting Dynamically Created Migratory Threads

DCMTs: Supporting Dynamically Created Migratory Threads

引用

IEEE International Conference on Computational Science and Engineering, CSE

作者： Yueting Zhu Wu Zhang Hai Jiang Yu Lei Junjie Peng Department of Computer Science and Engineering Shanghai University Shanghai China Department of Computer Science and Engineering University of Technology Arlington TX USA Department of Computer Science Arkansas State University Jonesboro AR USA Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy and Sciences China

Thread migration is an effective technique for fault resilience and load balancing in high performance computing. However, flexible thread migration is not easy to achieve. In this paper, we present an approach to creating migratory threads dynamically at application level. The targets must be executable source files. Compared to the static ones, the number of threads created during migration with the new scheme is independent from the context. Various thread cases are considered for migration. Thread state is handled at application level. Variables are saved in structures in C language for speedy state construction. In order to solve the inability of traditional methods in tracking the created threads, a tree of active function calls is used to record the callback. The preprocessor of the proposed one is written in YACC for accuracy and programmability. The migration enabling process is transparent to programmers with the help of the preprocess. The experimental results have demonstrated the effectiveness of this approach.

关键词： Instruction sets Switches computer science Electronic mail Data preprocessing Flexible printed circuits

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

arXiv

引用

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

来源：评论

学校读者我要写书评

暂无评论

Dynamics of Interacting Diseases

引用

Physical Review X 2014年第4期4卷 041005-041005页

作者： Joaquín Sanz Cheng-Yi Xia Sandro Meloni Yamir Moreno Institute for Biocomputation and Physics of Complex Systems (BIFI) University of Zaragoza Zaragoza 50018 Spain Department of Theoretical Physics University of Zaragoza Zaragoza 50009 Spain Key Laboratory of Computer Vision and System (Ministry of Education) and Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin 300191 People’s Republic of China Complex Networks and Systems Lagrange Lab Institute for Scientific Interchange Turin 10126 Italy

Current modeling of infectious diseases allows for the study of complex and realistic scenarios that go from the population to the individual level of description. However, most epidemic models assume that the spreading process takes place on a single level (be it a single population, a metapopulation system, or a network of contacts). In particular, interdependent contagion phenomena can be addressed only if we go beyond the scheme-one pathogen-one network. In this paper, we propose a framework that allows us to describe the spreading dynamics of two concurrent diseases. Specifically, we characterize analytically the epidemic thresholds of the two diseases for different scenarios and compute the temporal evolution characterizing the unfolding dynamics. Results show that there are regions of the parameter space in which the onset of a disease’s outbreak is conditioned to the prevalence levels of the other disease. Moreover, we show, for the susceptible-infected-susceptible scheme, that under certain circumstances, finite and not vanishing epidemic thresholds are found even at the limit for scale-free networks. For the susceptible-infected-removed scenario, the phenomenology is richer and additional interdependencies show up. We also find that the secondary thresholds for the susceptible-infected-susceptible and susceptible-infected-removed models are different, which results directly from the interaction between both diseases. Our work thus solves an important problem and paves the way toward a more comprehensive description of the dynamics of interacting diseases.

关键词： Complex systems Interdisciplinary physics Statistical physics

来源：评论

学校读者我要写书评

暂无评论

Instruction level test for parallel multipliers

Instruction level test for parallel multipliers

引用

IEEE International Conference on Electronics, Circuits and systems (ICECS)

作者： Ma Lin Gao Yan Chinese Academy of Sciences Beijing China Key Laboratory of Computer System and Architecturen+î Institute of Computing Technology Chinese Academy and Sciences Beijing China College of Electronics and Information Engineering University of Tongji Shanghai China

Multiplication operations are the normal operations in operating systems or scientific calculations. Multipliers embedded in processors, DSP or SoC are well optimized for best performance, and they are sensitive to test overhead. Instruction level test is a popular functional test approach for microprocessors test, and it can get satisfactory test results. But for the multipliers, one important part of microprocessors, there is no detail on how to testing them. This paper presents an instruction level test approach for the multiplier test. The proposed approach does not modify the multipliers and does not need any extra logic just using instructions of the processors to test processorspsila multipliers. Sequentially it does not have any test cost on area or timing. Moreover the instruction-level test is suited for at-speed test in nature. Experimental results on the real processorpsilas circuits show that the instruction level test approach has good effect on parallel multipliers.

关键词： Circuit testing Built-in self-test system testing Circuit faults Sequential analysis Microprocessors Automatic testing Costs Very large scale integration Integrated circuit testing

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：