检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2024

作者： Chen, Shixin Software Engineering Institute of Guangzhou Department of Computer Science Guangzhou510980 China

ISBN: (纸本)9798350366174

Owing to the challenge of target occlusion leading to tracking failure during the target tracking process, achieving efficient and robust tracking of targets under occlusion scenarios has become a focal point of research. In this paper, we addresses the issue of tracking failure caused by the reduction or disappearance of target appearance information in occlusion scenarios. It proposes a study on target tracking under occlusion scenes based on deep learning methodologies. A foundation tracker is constructed that leverages location enhancement and multi-template fusion. Built upon this, graph attention mechanisms and target loss detection mechanisms are introduced. In cases where the target is lost due to occlusion, a re-detection strategy is employed to resume tracking once the target reappears. Experiments conducted on datasets demonstrate that the proposed algorithm can effectively determine whether a target is undergoing occlusion and significantly enhances tracking performance under such conditions. © 2024 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A Reduced State-Space Generation Method for Concurrent Systems Based on CPN-PR Model

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年第6期44卷 2328-2342页

作者： Zhong, Wenjie Sun, Tao Zhou, Jian-Tao Wang, Zhuowei Song, Xiaoyu Inner Mongolia University College of Computer Science the Engineering Research Center of Ecological Big Data Ministry of Education the Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software the Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot010000 China Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China Portland State University Department of Electrical and Computer Engineering PortlandOR97207 United States

Colored Petri nets (CPNs) provide descriptions of the concurrent behaviors for software and hardware. Model checking based on CPNs is an effective method to simulate and verify the concurrent behavior in system design. However, the model-checking method traverses the full state space, which suffers from the state-space explosion problem. A reduced state-space generation method related to the property of concurrent systems is proposed. Specifically, we extend CPNs to define a property-related model (CPN-PR) and give a property-related analysis method whose results can be used to generate the CPN-PR model. A reduced state-space generation method is developed based on enabled binding element filtering rules. The stutter trace equivalence between the state spaces of CPN and CPN-PR has been proven by showing that the reduced state space may not change the model-checking result. A comparison experiment is conducted to demonstrate the effectiveness of our method. © 1982-2012 IEEE.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

SDD: Strawberry Disease Detection Framework Based on Computer Vision Neural Networks 5

SDD: Strawberry Disease Detection Framework Based on Compute...

引用

5th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2024

作者： Zhu, Xiangyuan Fan, Jianneng Yan, Xiaobing Mao, Taotao Huang, Jiandong Zhang, Yu Nie, Hong Zhaoqing University School of Computer Science and Software Guangdong Zhaoqing526061 China

ISBN: (纸本)9798350373820

Identifying and treating strawberry diseases are crucial in farmers' cultivation practices. However, accurate disease identification remains challenging, including limited available datasets, diversity in disease appearance, and low accuracy in disease detection. To address these challenges, we propose a Strawberry Disease Detection (SDD) framework based on multiple computer vision neural networks. We first build a well-annotated dataset of 1,943 images with 7 categories of strawberry diseases. Four popular deep visual detection models, including YOLOv3-tiny, Faster R-CNN, YOLOv6-m, and YOLOv7-m, are incorporated into the SDD framework. We further enhance the YOLOv7 algorithm by integrating data augmentation techniques to diversify the training data. Our algorithm utilizes the SIoU loss function to locate diseases precisely. Extensive experiments are conducted on real-world datasets to evaluate the performance of all networks within the SDD framework. The experimental results indicate that YOLOv3-tiny exhibits the lowest performance in terms of F1score, Precision, and Recall. Conversely, Faster R-CNN, YOLOv6m, and YOLOv7-m demonstrate superior recognition accuracy, despite their relatively higher Giga Floating Point Operations Per Second (GFLOPs). The proposed Enhanced YOLOv7 achieves the best performance, with an mAP of 90.87% and an F1-score of 0.862, respectively. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

More and Larger Auxiliary Feature-Guided Spatial-Temporal Super-Resolution for Rendered Sequences 17th

More and Larger Auxiliary Feature-Guided Spatial-Temporal S...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Zheng, Lijie Liang, Xiao School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China

ISBN: (纸本)9789819609628

The post-processing rendered sequences improves the quality of the sequences and shortens the time of the rendering phase. However, most of the current post-processing methods for sequences are suitable for video. Directly transferring these methods to rendered sequences cannot obtain high-quality results. To address this problem, we propose an end-to-end spatial-temporal super-resolution network for rendered sequences, which improves rendering efficiency by simultaneously implementing frame interpolation (FI) and super-resolution. In the FI task, accurately inferring results that closer to the real motion state of the target frames is the key and difficult point to ensure the generation effect. For this issue, we design an auxiliary feature-guided interpolation (AFGI) module. By introducing the auxiliary features corresponding to the target frames, AFGI module provides the real motion state of the target frames to the network. In the part of aggregating contextual information, we propose a weighted aggregation upsampling (WAUpS) module. Aggregation is selectively performed based on the correlation between incoming information and the current frame. WAUpS module effectively prevents irrelevant information from affecting the super-resolution results, which is a problem with the direct aggregation methods used previously. At the same time, WAUpS module combines the upsampled features with the corresponding high-resolution auxiliary features. This addition provides the output with rich detail textures and other key information, further improving the overall processing quality. Experimental results show that compared with state-of-the-art (SOTA) methods, our method not only obtains high-quality rendered sequences processing results, but also effectively improves the rendering efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

DIVING SEGMENTATION MODEL INTO PIXELS 12

DIVING SEGMENTATION MODEL INTO PIXELS

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Gan, Chen Yin, Zihao He, Kelei Gao, Yang Zhang, Junfeng Medical School of Nanjing University China State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China

More distinguishable and consistent pixel features for each category will benefit the semantic segmentation under various settings. Existing efforts to mine better pixel-level features attempt to explicitly model the categorical distribution, which fails to achieve optimal due to the significant pixel feature variance. Moreover, prior research endeavors have scarcely delved into the thorough analysis and meticulous handling of pixel-level variance, leaving semantic segmentation at a coarse granularity. In this work, we analyze the causes of pixel-level variance and introduce the concept of pixel learning to concentrate on the tailored learning process of pixels to handle the pixel-level variance, enhancing the per-pixel recognition capability of segmentation models. Under the context of the pixel learning scheme, each image is viewed as a distribution of pixels, and pixel learning aims to pursue consistent pixel representation inside an image, continuously align pixels from different images (distributions), and eventually achieve consistent pixel representation for each category, even cross-domains. We proposed a pure pixel-level learning framework, namely PiXL, which consists of a pixel partition module to divide pixels into sub-domains, a prototype generation, a selection module to prepare targets for subsequent alignment, and a pixel alignment module to guarantee pixel feature consistency intra-/inter-images, and inter-domains. Extensive evaluations of multiple learning paradigms, including unsupervised domain adaptation and semi-/fully-supervised segmentation, show that PiXL outperforms state-of-the-art performances, especially when annotated images are scarce. Visualization of the embedding space further demonstrates that pixel learning attains a superior representation of pixel features. The code is available here. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

ST-PINN: A Self-Training Physics-Informed Neural Network for Partial Differential Equations

arXiv

引用

arXiv 2023年

作者： Yan, Junjun Chen, Xinhai Wang, Zhichao Zhoui, Enqiang Liu, Jie Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Changsha410073 China

Partial differential equations (PDEs) are an essential computational kernel in physics and engineering. With the advance of deep learning, physics-informed neural networks (PINNs), as a mesh-free method, have shown great potential for fast PDE solving in various applications. To address the issue of low accuracy and convergence problems of existing PINNs, we propose a self-training physics-informed neural network, ST-PINN. Specifically, ST-PINN introduces a pseudo label based self-learning algorithm during training. It employs governing equation as the pseudo-labeled evaluation index and selects the highest confidence examples from the sample points to attach the pseudo labels. To our best knowledge, we are the first to incorporate a self-training mechanism into physics-informed learning. We conduct experiments on five PDE problems in different fields and scenarios. The results demonstrate that the proposed method allows the network to learn more physical information and benefit convergence. The ST-PINN outperforms existing physics-informed neural network methods and improves the accuracy by a factor of 1.33x-2.54x. The code of ST-PINN is available at GitHub: https://***/junjun-yan/ST-PINN. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

EmoNet: A Convolutional Neural Network and Transfer Learning-Based Framework for Facial Micro-Expression Recognition and Emoticonification 5

EmoNet: A Convolutional Neural Network and Transfer Learning...

引用

5th International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2024

作者： Gong, Rui Wang, Zhongyi Zhao, Jie Southwest Petroleum University School of Computer Science and Software Engineering Chengdu China

ISBN: (纸本)9798350366174

With the rising popularity of online social interactions, emojis play a pivotal role in communication, effectively conveying people's emotions. Hence, accurately converting facial micro-expressions into corresponding emojis becomes crucial. However, current micro-expression recognition technology faces challenges of low accuracy and poor generalization. To address these issues, this paper innovatively proposes a method that combines transfer learning with convolutional neural networks. This approach significantly enhances the model's generalization capability and recognition accuracy. Experimental results demonstrate notable improvements in both accuracy and robustness in micro-expression recognition, effectively overcoming common problems found in traditional methods, such as overfitting and sample imbalance. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Electrical Characteristic and Power Fluctuations of GAA Si NS CFETs by Simultaneously Considering Six Process Variation Factors

IEEE Open Journal of Nanotechnology

引用

IEEE Open Journal of Nanotechnology 2023年 4卷 229-238页

作者： Kola, Sekhar Reddy Li, Yiming National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Parallel and Scientific Computing Laboratory National Yang Ming Chiao Tung University Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Biomedical Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

Characteristic variability induced by process variation effect (PVE) is one of technological challenges in semiconductor industry. In this work, we computationally study electrical characteristic and power fluctuations induced by six factors of PVE of the gate-all-around (GAA) silicon (Si) nanosheet (NS) complementary field-effect-transistors (CFETs) which are formed by vertically stacking n-FET on top of p-FET. Among the six factors, NS thickness (TNS), NS width (WNS), and gate length (LG) are identified as crucial factors contributing to large variations in device characteristics. The p-FET exhibits substantial off-state current fluctuation (about 151%) due to the bottom parasitic channel leakages. Compared with the magnitudes of dynamic and short circuit powers, the static power is marginal, but it possesses the largest fluctuation (up to 148%). If we assume that each factor of PVE has the same probability distribution as the others and all are mutually independent, the statistical sum of their power fluctuations will exhibit more than 50% overestimations, compared with the results when all factors are considered simultaneously. © 2020 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

QDMI Quantum Device Management Interface: Hardware -software Interface for the Munich Quantum software Stack 5

QDMI Quantum Device Management Interface: Hardware -Software...

引用

2024 International Conference on Quantum Computing and Engineering

作者： Wille, Robert Schmid, Ludwig Stade, Yannick Echavarria, Jorge Schulz, Martin Schulz, Laura Burgholzer, Lukas Tech Univ Munich Chair Design Automat Munich Germany Software Competence Ctr Hagenberg GmbH Hagenberg Austria Leibniz Supercomp Ctr Garching Germany Tech Univ Munich Chair Comp Architecture & Parallel Syst Munich Germany

ISBN: (纸本)9798331541378

Quantum computing is a promising technology that requires a sophisticated software stack to connect end users to the wide range of possible quantum backends. However, current software tools are usually hard -coded for single platforms and lack a dynamic interface that can automatically retrieve and adapt to changing physical characteristics and constraints of different platforms. With new hardware platforms frequently introduced and their performance changing on a daily basis, this constitutes a serious limitation. In this paper, we showcase a concept and a prototypical realization of an interface, called the Quantum Device Management Interface (QDMI), that addresses this problem by explicitly connecting the software and hardware developers, mediating between their competing interests. QDMI allows hardware platforms to provide their physical characteristics in a standardized way, and software tools to query that data to guide the compilation process accordingly. This enables software tools to automatically adapt to different platforms and to optimize the compilation process for the specific hardware constraints. QDMI is a central part of the Munich Quantum software Stack (MQSS) a sophisticated software stack to connect end users to the wide range of possible quantum backends. QDMI is publicly available as open source at https://***/Munich- Quantum- software- Stack/QDMI.

关键词： hardware-software interface mqss qdmi quantum software software stack

来源：评论

学校读者我要写书评

暂无评论

YOLOv5-LW: Lightweight UAV Object Detection Algorithm Based on YOLOv5 13th

YOLOv5-LW: Lightweight UAV Object Detection Algorithm Based ...

引用

13th EAI International Conference on Mobile Networks and Management, MONAMI 2023

作者： Xiao, He Zhao, Kai Xie, Xiaomei Song, Peilong Dong, Siwen Yang, Jiahui School of Software Engineering Jiangxi University of Science and Technology Jiangxi Nanchang330013 China Nanchang Key Laboratory of Virtual Digital Factory and Cultural Communications Nanchang330013 China

ISBN: (纸本)9783031554704

UAV object detection task is a highly popular computer vision task, where algorithms can be deployed on unmanned aerial vehicles (UAVs) for real-time object detection. However, YOLOv5’s performance for UAV object detection is not entirely satisfactory due to the small size of the detected objects and the problem of occlusion. To address these two issues in the YOLOv5 algorithm, we propose the YOLOv5-LW algorithm model. Building upon YOLOv5, we replace the FPN-PAN network structure with the FPN-PANS structure. This modification helps mitigate the issue of feature disappearance for small objects during the training process while reducing the model parameters and computational complexity. Additionally, within the FPN-PANS structure, we employ a multistage feature fusion approach instead of the original feature fusion module. This approach effectively corrects the erroneous information generated during the upsampling stage for certain objects. Finally, we replace the SPPF module with the SPPF-W module to further increase the receptive field while maintaining almost unchanged parameters. We conducted multiple experiments and demonstrate that YOLOv5-LW performs exceptionally well in lightweight small object detection tasks using the VisDrone dataset. Compared to YOLOv5, YOLOv5-LW achieves a 4.7% improvement in mean average precision (mAP), reduces the model size by 40%, and decreases the parameters by 40%. © ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Object detection

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：