检索结果-内蒙古大学图书馆

32nd ACM International conference on Multimedia, MM 2024

作者： Dai, Zhien Tang, Zhaohui Zhang, Hu Tian, Can Pan, Mingjun Xie, Yongfang School of Automation Central South University Changsha China College of Computer Science and Engineering Changsha University Changsha China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China School of Electronic and Computer Engineering Peking University Shenzhen China School of Mathematics and statistics Central South University China

ISBN: (纸本)9798400706868

Stereo matching is a pivotal technique for depth estimation and has been popularly applied in various computer vision tasks. Although many related methods have been reported recently, they still face some challenges such as significant disparity variations at object boundaries, difficult prediction at large disparity regions, and suboptimal generalization when label distribution varies between source and target domains. Therefore, we propose a stereo-matching model (i.e., Eglcr) that utilizes edge structure information and multi-scale matching similarity features for better disparity estimation. First, we use a lightweight network to predict the initial disparity. Then, we develop a multi-scale similarity feature extraction module, incorporating adaptive attention mechanisms, to capture the fusion similarity information of stereo images across various scales. Meanwhile, we introduce an edge structure-aware module that features an iteratively optimized disparity map and a scale attention factor, aimed at accurately delineating edge information in complex scenes. After that, we employ an iterative strategy for disparity estimation, guided by the fusion similarity features across multiple scales and the detailed edge structure information. We conduct abundant experiments on some popular stereo matching datasets including Middlebury, KITTI, ETH3D, and Scene Flow. The results show that our proposed Eglcr achieves state-of-the-art performance both in accuracy and generalization. Our code is available at https://***/kangarooCV/Eglcr. © 2024 ACM.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multiple Attention Network for Facial Expression Recognition 20th

Multiple Attention Network for Facial Expression Recognition

引用

20th Pacific Rim International conference on Artificial Intelligence, PRICAI 2023

作者： Feng, Wenyu Fei, Zixiang Zhou, Wenju Fei, Minrui School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China School of Computer Engineering and Science Shanghai University Shanghai200444 China

ISBN: (纸本)9789819970247

Facial expression recognition (FER) has become increasingly important in the field of human-computer interaction. This paper proposes an improved method with attention mechanism to improve FER performance. Our approach is grounded in two crucial observations. Firstly, as multiple categories share similar underlying facial characteristics, distinguishing between them may be subtle. Secondly, recognizing facial expressions demands a comprehensive approach by encoding high-order interactions among localized features from multiple facial regions simultaneously. To address these challenges, we introduce our MAN model consisting of three key components: Multi-branch stack Residual Network (MRN), Transitional Attention Network (TAN), and Appropriate Cascade Structure (ACS). The TAN learns objectives to maximize class separability, while the MRN deploys attention heads to focus on various facial regions and generate attention maps. Additionally, the ACS module provides a more reasonable construction method for the model. Comprehensive experiments on three publicly available datasets (AffectNet, RAF-DB, and CK+) consistently achieves better expression recognition performance. Compared to the ResNet network, our approach yielded an improved accuracy of 3.3%, 3.2%, 4.1% and 1.8% on the Affectnet7 dataset, Affectnet8 dataset, RAF-DB dataset, and CK+ dataset, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

CoMO-NAS: Core-Structures-Guided Multi-Objective Neural Architecture Search for Multi-Modal Classification 24

CoMO-NAS: Core-Structures-Guided Multi-Objective Neural Arch...

引用

32nd ACM International conference on Multimedia, MM 2024

作者： Fu, Pinhan Liang, Xinyan Qian, Yuhua Guo, Qian Wei, Zhifang Li, Wen Institute of Big Data Science and Industry Shanxi University Taiyuan China School of Computer Science and Technology Taiyuan University of Science and Technolog Taiyuan China

ISBN: (纸本)9798400706868

Most existing NAS-based multi-modal classification (MMC-NAS) methods are optimized using the classification *** can not simultaneously provide multiple models with diverse perferences such as model complex and classification performance for meeting different users' demands. Combining NAS-MMC with multi-objective optimization is a nature way for this issue. However, the challenge problem of this solution is the high computation cost. For multi-objective optimization, the computing bottleneck is pareto front search. Some higher-quality MMC models (namely core structures, CSs) consisting of high-quality features and fusion operators are easier to identify. We find that CSs have a close relation with the pareto front (PF), i.e., the individuals lying in PF contain the CSs. Based on the finding, we propose an efficient multi-objective neural architecture search for multi-modal classification by applying CSs to guide the PF search (CoMO-NAS). In conclusion, experimental results thoroughly demonstrate the effectiveness of our CoMO-NAS. Compared to state-of-the-art competitors on benchmark multi-modal tasks, we achieve comparable performance with lower model complexity in shorter search time. © 2024 ACM.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities

引用

IEEE ACCESS 2022年 10卷 112392-112415页

作者： Neupane, Subash Ables, Jesse Anderson, William Mittal, Sudip Rahimi, Shahram Banicescu, Ioana Seale, Maria Mississippi State Univ Dept Comp Sci & Engn Mississippi State MS 39762 USA US Army Engineer Res & Dev Ctr Vicksburg MS 39180 USA

The application of Artificial Intelligence (AI) and Machine Learning (ML) to cybersecurity challenges has gained traction in industry and academia, partially as a result of widespread malware attacks on critical systems such as cloud infrastructures and government institutions. Intrusion Detection Systems (IDS), using some forms of AI, have received widespread adoption due to their ability to handle vast amounts of data with a high prediction accuracy. These systems are hosted in the organizational Cyber Security Operation Center (CSoC) as a defense tool to monitor and detect malicious network flow that would otherwise impact the Confidentiality, Integrity, and Availability (CIA). CSoC analysts rely on these systems to make decisions about the detected threats. However, IDSs designed using Deep Learning (DL) techniques are often treated as black box models and do not provide a justification for their predictions. This creates a barrier for CSoC analysts, as they are unable to improve their decisions based on the model's predictions. One solution to this problem is to design explainable IDS (X-IDS). This survey reviews the state-of-the-art in explainable AI (XAI) for IDS, its current challenges, and discusses how these challenges span to the design of an X-IDS. In particular, we discuss black box and white box approaches comprehensively. We also present the tradeoff between these approaches in terms of their performance and ability to produce explanations. Furthermore, we propose a generic architecture that considers human-in-the-loop which can be used as a guideline when designing an X-IDS. Research recommendations are given from three critical viewpoints: the need to define explainability for IDS, the need to create explanations tailored to various stakeholders, and the need to design metrics to evaluate explanations.

关键词： Artificial intelligence Machine learning Intrusion detection computer security Deep learning Cognition Predictive models Glass box Closed box Explainable intrusion detection systems explainable artificial intelligence machine learning deep learning white box black box explainability cybersecurity

来源：评论

学校读者我要写书评

暂无评论

MSAOT: Enhancing Video Object Segmentation with Memory-Selective Updates and high-Quality Mask Regeneration 24

MSAOT: Enhancing Video Object Segmentation with Memory-Selec...

引用

13th International conference on Computing and Pattern Recognition, ICCPR 2024

作者： Du, Yinglong Luo, Yifei Zhao, Xu Yu, Tao Zhu, Guibo Wang, Jinqiao Foundation Model Research Center Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400717482

Video Object Segmentation (VOS) is an important computer vision task that involves tracking and segmenting objects across video frames. The mainstream VOS method typically employs long and short-term memory to aid the model in retaining the object's feature representation. However, current state-of-the-art methods do not adequately address the issue of information loss and contamination when updating long-term memory. To address these issues, we propose an innovative method MSAOT, including an object tracker with a memory-selective update strategy and high-quality mask regeneration for post-process. This thereby assists in subsequent sequence predictions and enhances model accuracy. MSAOT employs an object tracker with the mutual similarity evaluation for long-term memory management and leverages HQ-SAM for high-quality mask generation. Extensive experiments show that our method's long-term memory successfully preserves information from all stages of the video sequence, particularly during the mid to late phases of prediction. The richness of the stored memory information is instrumental in improving the model's performance. The experimental results on the VOT2020 benchmark highlight that MSAOT outperforms the current state-of-the-art by a notable margin of 1.1% in Expected Average Overlap (EAO). © 2024 Copyright held by the owner/author(s).

关键词： Memory management

来源：评论

学校读者我要写书评

暂无评论

PONO: Power Optimization with Near Optimal SMT-based Sub-circuit Generation 24

PONO: Power Optimization with Near Optimal SMT-based Sub-cir...

引用

61st ACM/IEEE Design Automation conference, DAC 2024

作者： Zou, Sunan Luo, Guojie School of Computer Science Peking University Beijing China Center for Energy-efficient Computing and Applications Peking University Beijing China

ISBN: (纸本)9798400706011

Generating high-quality sub-circuits for local substitution is an effective optimization technique in logic synthesis. There have been abundant works on generating area- and delay-optimal sub-circuits, greatly enhancing the logic optimization quality. However, power-oriented sub-circuit generation is rarely discussed, while optimizing power consumption in this sub-15 nm era is of paramount interest. We propose PONO, an SMT-based near optimal sub-circuit generation flow for power optimization. PONO enables power-oriented circuit library building and fills the gap in generating circuits near the Pareto frontier in PPA (Power, performance, and Area). It manifests superiority in power reduction over traditional one in rewrite, a key logic optimization algorithm. We test PONO on EFPL benchmarks, and it shows 8.7% less power consumption without degrading the post-place-and-route performance and area. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Logic Synthesis

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Deep Learning Framework for Enhanced Waste Detection and Classification 22

A Two-Stage Deep Learning Framework for Enhanced Waste Detec...

引用

22nd IEEE International conference on Machine Learning and Applications, ICMLA 2023

作者： Pang, Hongbo Huang, Changcheng Carleton University Department of Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350345346

With the rapid modernization progress over the past decades, waste classification has become increasingly important as cities worldwide seek to implement more sustainable waste management practices. Traditional manual sorting methods are labor-intensive, prone to inaccuracies, and hard to scale, driving the need for automated, efficient solutions. Although deep learning techniques, recognized for their ability to process complex hierarchical data, have emerged as potential aids, their successful implementation is often hampered by the challenging task of gathering diverse, large-scale, high-quality waste image datasets, leading to possible overfitting and model bias. This study proposes an innovative, two-stage waste detection framework that first identifies the bounding box of waste items, then classifies them into one of six primary categories, effectively addressing the inherent issues with previous methodologies by optimally utilizing available data and reducing overfitting and bias. Trained and evaluated on the comprehensive TACO and WaRP waste datasets, our model has demonstrated superior performance relative to existing methods, underscoring its promise as a scalable, accurate, and efficient solution for waste classification, thus offering exciting prospects for further research and practical applications in sustainable waste management. © 2023 IEEE.

关键词： Deep learning garbage classification waste management

来源：评论

学校读者我要写书评

暂无评论

Urban-scale Point Cloud Semantic Segmentation with Transformer

Urban-scale Point Cloud Semantic Segmentation with Transform...

引用

2022 International conference on Electronic Information Engineering and computer Science, EIECS 2022

作者： Song, Jinge Cao, Zhenyuan Li, Xueyan Li, Xiuying Guo, Shuxu College of Electronic Science and Engineering Jilin University Changchun China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9781510663312

Semantic segmentation of urban-scale point clouds is widely used in aviation, unmanned aerial vehicles, and autonomous driving. However, owing to the many points in the urban-scale point cloud dataset and massive computation in the learning process, traditional networks often have poor segmentation performance and high costs. In this study, we adopted the Point Transformer network as the baseline and integrated random point sampling and attentive pooling into a new transition-down block, embedded in the encoder structure of the baseline to improve the speed and accuracy of semantic segmentation. On the challenging SensatUrban dataset, the Point Transformer network and the proposed network obtained mIoU values of 71.1% and 76.8%, respectively. The results show that the proposed network effectively improves the shortcomings of the Point Transformer network and achieves better semantic segmentation performance of urban-scale point clouds. © 2023 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

OSKDet: Orientation-sensitive Keypoint Localization for Rotated Object Detection

OSKDet: Orientation-sensitive Keypoint Localization for Rota...

引用

IEEE/CVF conference on computer Vision and Pattern Recognition (CVPR)

作者： Lu, Dongchen Li, Dongmei Li, Yali Wang, Shengjin Tsinghua Univ Dept Elect Engn Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Rotated object detection is a challenging issue in computer vision field. Inadequate rotated representation and the confusion of parametric regression have been the bottleneck for high performance rotated detection. In this paper, we propose an orientation-sensitive keypoint based rotated detector OSKDet. First, we adopt a set of keypoints to represent the target and predict the keypoint heatmap on ROI to get the rotated box. By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for rotated representation, which improves the localization accuracy and acquires high quality detection results. Second, we explore a new unordered keypoint representation paradigm, which could avoid the confusion of keypoint regression caused by rule based ordering. Furthermore, we propose a localization quality uncertainty module to better predict the classification score by the distribution uncertainty of keypoints heatmap. Experimental results on several public benchmarks show the state-of-the-art performance of OSKDet. Specifically, we achieve an AP of 80.91% on DOTA, 89.98% on HRSC2016, 97.27% on UCAS-AOD, and a F-measure of 92.18% on ICDAR2015, 81.43% on ICDAR2017, respectively.

关键词： Location awareness Heating systems computer vision Uncertainty Shape Object detection Detectors

来源：评论

学校读者我要写书评

暂无评论

Green roof energy performance in different climate zones: a simulation study

Green roof energy performance in different climate zones: a ...

引用

2023 International conference on the Built Environment in Transition, CISBAT 2023

作者： Kulumkanov, Nursat Nadeem, Abid Tokbolat, Serik School of Engineering and Digital Sciences Nazarbayev University Astana Kazakhstan Faculty of Engineering University of Nottingham Nottingham United Kingdom

Green roofs are widely used as a passive building design technique to decrease the cooling demand in buildings. The vegetation uses the energy of the surroundings during the evapotranspiration process, leading to a temperature decrease in air. This paper investigates the effectiveness of green roofs in 45 cities in different climate zones. The simulation of the energy performance of buildings is performed using DesignBuilder software, which integrates the EnergyPlus engine. The results show that green roofs effectively reduce the cooling load but increase heating energy consumption. The highest performance in total energy savings was in the arid zone with savings ranging from 3.2% to 9.1%, despite having a high heating demand. Tropic and temperate zones show relatively lower results, which vary from 1.4% to 4.1% and -0.2% to 4.2%. The cold zone shows the worst result, ranging by around 1%. Thus, green roofs show better performance in cities with high-temperature ranges, direct radiation, and humidity level. © 2023 Institute of Physics Publishing. All rights reserved.

关键词： computer software

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：