检索结果-内蒙古大学图书馆

4th Asia-Pacific artificial intelligence and Big Data Forum, AIBDF 2024

作者： Wei, Wu The School of Computer Science and Artificial Intelligence Wuhan University of Technology Hubei Wuhan China

ISBN: (纸本)9798400710865

In the field of real-time object detection, the YOLO series has become a mainstream approach due to its exceptional performance. However, its performance on small object detection still has room for improvement. Small objects often struggle with limited feature representation in the P3, P4, and P5 detection layers. Traditional methods to address this issue typically add a P2 detection layer to enhance small object detection capabilities, but this often leads to a significant increase in computation and extended post-processing time. Therefore, developing an efficient and effective feature pyramid tailored for small objects has become an urgent problem to solve. This paper proposes a network specifically optimized for small object detection-YOLO-CSPOKM, which significantly enhances the performance of small object detection while also improving the detection of general objects. Based on the original PAFPN structure, we designed a Small Object Enhance Pyramid: the P2 feature layer is processed using SPD-Conv to extract features rich in small object information and then fused with the P3 layer. Subsequently, the CSP (Cross Stage Partial) strategy is employed to split input features along the channel dimension. One portion of the features is passed through the Omni-Kernel module to effectively capture multi-scale features ranging from global to local levels, while the other portion is concatenated with the Omni-Kernel output via skip connections. Furthermore, the P3, P4, and P5 features are passed through the SSFF module, and their output is added to the results from the CSPOKM module. Finally, the combined features are sent to the detection head, achieving a comprehensive enhancement in small object detection. Experiments on the MS COCO dataset demonstrate that compared to the baseline YOLOv8n model, YOLO-CSPOKM improves mAP@0.5:0.95 to 39.2%, a 2.8% increase, while maintaining a compact model size. When extended to the YOLOv8s model, the enhanced version achieves an mA

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

TCRNet: An Efficient Vehicle Re-Identification Network Using TinyCLIP-Assisted Feature Representation 24

TCRNet: An Efficient Vehicle Re-Identification Network Using...

引用

4th Asia-Pacific artificial intelligence and Big Data Forum, AIBDF 2024

作者： Fu, Zihao School of Computer Science and Artificial Intelligence Wuhan University of Technology Hubei Wuhan China

ISBN: (纸本)9798400710865

Vehicle re-identification (ReID) is an important component of intelligent transportation systems, yet existing methods often struggle with challenges such as inter-class similarity, viewpoint variations, and environmental noise. While CLIP-based approaches have shown promise in bridging visual and semantic domains, they often rely heavily on the pre-trained CLIP model, limiting flexibility and integration with standard baselines. To address this, we propose TCRNet, an efficient vehicle ReID network that integrates semantic features from TinyCLIP into the visual features extracted by a baseline ResNet50-IBN model. By fusing TinyCLIP-assisted semantic features with visual representations in an end-to-end training pipeline, TCRNet demonstrates strong capability in robust and discriminative feature learning. Extensive ablation experiments on the VeRi-776 dataset validate the discriminative ability of the proposed model, achieving 89.7% mAP and 97.5% Rank-1. © 2024 Copyright held by the owner/author(s).

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Characterizing the app recommendation relationships in the iOS app store: a complex network's perspective

引用

science China(Information sciences) 2025年第4期68卷 284-299页

作者： Gang HUANG Fuqi LIN Yun MA Haoyu WANG Qingxiang WANG Gareth TYSON Xuanzhe LIU Key Lab of High Confidence Software Technologies (Peking University) Ministry of Education School of Computer Science Peking University Institute for Artificial Intelligence Peking University School of Cyber Science and Engineering Huazhong University of Science and Technology Alibaba Group Hong Kong University of Science and Technology (Guangzhou)

Mobile apps have become widely adopted in our daily lives. To facilitate app discovery, most app markets provide recommendations for users, which may significantly impact how apps are accessed. However, little has been known about the underlying relationships and how they reflect(or affect) user behaviors. To fill this gap, we characterize the app recommendation relationships in the i OS app store from the perspective of the complex network. We collect a dataset containing over 1.3 million apps and 50 million app recommendations. This dataset enables us to construct a complex network that captures app recommendation relationships. Through this, we explore the recommendation relationships between mobile apps and how these relationships reflect or affect user behavior patterns. The insights gained from our research can be valuable for understanding typical user behaviors and identifying potential policy-violating apps.

关键词： mobile app recommendation complex network user behavior policy-violating app

来源：评论

学校读者我要写书评

暂无评论

FS2D: Fully Sparse Few-Shot 3D Object Detection

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5847-5854页

作者： Li, Chunzheng Wang, Gaihua Liang, Zeng Long, Qian Zhou, Zhengshu Pan, Xuran Hubei University of Technology School of Electrical and Electronic Engineering Wuhan430068 China Tianjin University of Science and Technology College of Artificial Intelligence Tianjin300457 China

Corner cases are a focal issue in current autonomous driving systems, with a significant portion attributed to few-shot detection. Due to the sparse distribution of point cloud data and the real-time requirements of autonomous driving, traditional few-shot detection methods face challenges in direct application to the 3D domain, making it more difficult for outdoor scene 3D detectors to handle corner cases. In this study, we employ fully sparse feature matching and aggregation operations, utilizing meta-learning methods to enhance performance on few-shot categories without increasing network inference parameters. Furthermore, our few-shot research is based on the inherent characteristics of publicly available data without introducing additional categories, allowing for fair comparisons with existing methods. Extensive experiments were conducted on the widely used nuScenes dataset to validate the effectiveness of our method. We demonstrate superior performance compared to the baseline method, especially in handling few-shot categories. © 2016 IEEE.

关键词： Three-dimensional displays Feature extraction Point cloud compression Training Metalearning Object detection Laser radar Accuracy Detectors Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Scale Object Detection Algorithm for Foggy Traffic Scenarios

引用

computers, Materials & Continua 2025年第2期82卷 2451-2474页

作者： Honglin Wang Zitong Shi Cheng Zhu School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China School of Electrical&Computer Engineering University of Illinois at Urbana ChampaignUrbanaIL 61801USA

In foggy traffic scenarios, existing object detection algorithms face challenges such as low detection accuracy, poor robustness, occlusion, missed detections, and false detections. To address this issue, a multi-scale object detection algorithm based on an improved YOLOv8 has been proposed. Firstly, a lightweight attention mechanism, Triplet Attention, is introduced to enhance the algorithm’s ability to extract multi-dimensional and multi-scale features, thereby improving the receptive capability of the feature maps. Secondly, the Diverse Branch Block (DBB) is integrated into the CSP Bottleneck with two Convolutions (C2F) module to strengthen the fusion of semantic information across different layers. Thirdly, a new decoupled detection head is proposed by redesigning the original network head based on the Diverse Branch Block module to improve detection accuracy and reduce missed and false detections. Finally, the Minimum Point Distance based Intersection-over-Union (MPDIoU) is used to replace the original YOLOv8 Complete Intersection-over-Union (CIoU) to accelerate the network’s training convergence. Comparative experiments and dehazing pre-processing tests were conducted on the RTTS and VOC-Fog datasets. Compared to the baseline YOLOv8 model, the improved algorithm achieved mean Average Precision (mAP) improvements of 4.6% and 3.8%, respectively. After defogging pre-processing, the mAP increased by 5.3% and 4.4%, respectively. The experimental results demonstrate that the improved algorithm exhibits high practicality and effectiveness in foggy traffic scenarios.

关键词： Deep learning object detection foggy scenes traffic detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Cooperative UAV Clustering for Fair Coverage of Communication Regions

引用

Intelligent and Converged Networks 2025年第1期6卷 1-19页

作者： Wu, Jiehong Gu, Linpeng Jia, Zhongli Wu, Jinsong School of Computer Science Shenyang Aerospace University Shenyang110136 China School of Artificial Intelligence Guilin University of Electronic Technology Guilin541004 China

Cooperative unmanned aerial vehicles (UAVs) cluster technology is considered a prospective solution for area coverage problems, enabling network access and emergency communications in remote areas. In this paper, we investigate how to control UAV cluster to achieve long-term and stable regional coverage while maintaining link connectivity and minimizing energy consumption, given the limited communication range and energy consumption of the UAVs themselves. To this end, we propose a cooperative UAV cluster strategy based on multi-agent deep reinforcement learning (MADRL) to achieve fair coverage of communication regions, which we call MADRL-based cooperative UAV cluster strategy (MADRL-CUCS). Our solution is a centralized training distributed execution architecture and defines a cluster structure for leader UAVs and follower UAVs. Under the premise of comprehensively considering the maximum coverage, we use a new energy efficiency function to minimize energy consumption, so as to extend the network lifetime of the UAVs cluster networks. The new fairness index and collision avoidance factor are used to ensure that the UAV cluster achieve effective and secure regional coverage. We adopt depth first search algorithm to check the link connectivity of the UAVs during the coverage process. Experiments show that the MADRL-CUCS algorithm outperforms the benchmark algorithm. © 2020 Tsinghua University Press.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Cropping-Classification based Semi-supervised Learning for Object Detection 8

Cropping-Classification based Semi-supervised Learning for O...

引用

8th International Conference on computer Graphics and Virtuality, ICCGV 2025

作者： Chai, Haonan Duan, Pengfei School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430070 China

ISBN: (纸本)9781510689213

In current semi-supervised object detection techniques, one-stage detectors typically realize only limited improvements when compared to two-stage detectors. The limitation is largely due to the assignment of incorrect labels to samples during the label allocation phase, as the process is influenced by inaccurate pseudo-labels. To tackle the problem, we propose a Cropping-Classification Semi-supervised Learning (CCSL) for one-stage detectors. After detection, we employ a Cropping-Classification module (CCM) designed to refine inaccurate pseudo-labels and to bolster the precision of localization. Extensive experiments on all SSOD settings of both COCO and Pascal VOC benchmark datasets show that our CCSL method outperforms all state-of-the-art one-stage methods. The experiments on the DIOR dataset show that CCSL has good generalization ability. © 2025 SPIE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Optimised EfficientNet for multi-class skin cancer diagnosis: integrating chaotic grey wolf algorithms

引用

Current science 2025年第7期128卷 728-736页

作者： Rama, P. Angayarkanni, V. Theresa, W. Gracy Pandiaraj, A. Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603 203 India Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai600 123 India

The detection of skin cancer holds paramount importance worldwide due to its impact on global health. While deep convolutional neural networks (DCNNs) have shown potential in this domain, current approaches often struggle with fine-grained variability in skin lesion features, imbalanced datasets and inadequate augmentation. The objectives of our study encompass building a model that not only enhances accuracy but also reduces training time and cost, improves dimensionality reduction during classification and segmentation, and is evaluated on larger datasets for robustness. We enhance the learning process using an improved nature-inspired optimisation algorithm tailored specifically for skin cancer classification tasks. This algorithm optimises model parameters to maximise classification accuracy while minimising computational overhead. Our proposed architecture leverages a gold standard dermatological image dataset meticulously curated and validated by experts. This dataset spans eight distinct classes, including actinic keratosis, basal cell carcinoma, melanoma, nevus, and others, ensuring a diverse representation of skin conditions. The balanced class distribution in the training and test sets enables fair evaluation and robustness assessment of our deep learning models. The developed algorithm showcases novelty in its approach, contributing to advancements in early skin cancer detection technologies. This study introduces an optimised deep learning model designed for the early detection of skin cancer, achieving a notable accuracy of 97.48%. Our study aims to contribute significantly to the medical field by providing a reliable and efficient tool for dermatologists and healthcare practitioners to assist in diagnosing skin conditions accurately and promptly, ultimately improving patient outcomes and healthcare efficiency. © (2025), (Indian Academy of sciences). All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

EduPlanner: LLM-Based Multiagent Systems for Customized and Intelligent Instructional Design

引用

IEEE Transactions on Learning Technologies 2025年 18卷 416-427页

作者： Zhang, Xueqiao Zhang, Chao Sun, Jianwen Xiao, Jun Yang, Yi Luo, Yawei Zhejiang University School of Software Technology Ningbo315048 China Central China Normal University Faculty of Artificial Intelligence in Education Wuhan430079 China Zhejiang University College of Computer Science and Technology Hangzhou310007 China

Large language models (LLMs) have significantly advanced smart education in the artificial general intelligence era. A promising application lies in the automatic generalization of instructional design for curriculum and learning activities, focusing on two key aspects: 1) customized generation: generating niche-targeted teaching content based on students' varying learning abilities and states and 2) intelligent optimization: iteratively optimizing content based on feedback from learning effectiveness or test scores. Currently, a single large LLM cannot effectively manage the entire process, posing a challenge for designing intelligent teaching plans. To address these issues, we developed EduPlanner, an LLM-based multiagent system comprising an evaluator agent, an optimizer agent, and a question analyst, working in adversarial collaboration to generate customized and intelligent instructional design for curriculum and learning activities. Taking mathematics lessons as our example, EduPlanner employs a novel Skill-Tree structure to accurately model the background mathematics knowledge of student groups, personalizing instructional design for curriculum and learning activities according to students' knowledge levels and learning abilities. In addition, we introduce the CIDDP, an LLM-based 5-D evaluation module encompassing Clarity, Integrity, Depth, Practicality, and Pertinence, to comprehensively assess mathematics lesson plan quality and bootstrap intelligent optimization. Experiments conducted on the GSM8K and Algebra datasets demonstrate that EduPlanner excels in evaluating and optimizing instructional design for curriculum and learning activities. Ablation studies further validate the significance and effectiveness of each component within the framework. © 2008-2011 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

NOMA Attack Prediction in Large-Scale Networks using Non-Linear Chaotic Belief Mechanism 3

NOMA Attack Prediction in Large-Scale Networks using Non-Lin...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Sangeetha, K. Suguna, M. Jebakumar Immanuel, D. Suje, S.A. Department of Computer Science and Engineering SNS College of Technology Tamil Nadu Coimbatore India Department of Artificial Intelligence and Data Science Karpagam Institute of Technology Tamil Nadu Coimbatore India Department of Artificial Intelligence and Data Science Nandha Engineering College Tamil Nadu Erode India

ISBN: (纸本)9798331527549

Non-Orthogonal Multiple Access (NOMA) systems are becoming relevant in the fast-expanding terrain of large-scale networks because of their efficiency in concurrently managing many users. This is true since NOMA systems let numerous users concurrently be managed. On the other hand, the intricacy of these networks leaves them vulnerable to a wide spectrum of attacks, including the more advanced and erratic NOMA attacks on the network. These strikes could produce major disturbances that would compromise the quality of service and cast questions regarding the general network security. It has been demonstrated that the effective projection of these hazards is limited by standard linear and probabilistic techniques. This is true as contemporary methods fail to adequately capture the basic non-linear dynamics of these large-scale networks. This article offers a novel method for NOMA attack prediction by means of a non-linear chaotic belief process. The results are shown here. To recreate the uncertainty and intricate interactions inside the network, the proposed method which is the logistic map which in turn generates the sequences for ensuring the accurate iterative updates which in turn provides better scalability and precision. This integrates belief networks with chaos theory. More exactly, we capture the random and nonlinear aspect of network dynamics by building belief values indicating the likelihood of an attack by use of a chaotic map. After that, the belief values proliferate across the network in search of defects and project the probability of NOMA attacks. Effectiveness of the proposed method is demonstrated by test results on a simulated large-scale network simulation. With a prediction accuracy of 92.7%, the chaotic belief mechanism obtained much above the average accuracy of 78.4% of traditional linear prediction systems. Moreover, the proposed approach lowered the false positive rate to 5.3%, substantially below the rate of 12.8% applied in the standard ap

关键词： Large scale 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：