检索结果-内蒙古大学图书馆

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Customization of the text-to-image diffusion model by fine-tuning for the generation of synthetic images of cyanobacterial blooms in lentic water bodies

引用

Expert Systems with Applications 2025年 287卷

作者： Barrientos-Espillco, Fredy Pajares, Gonzalo López-Orozco, José A. Besada-Portas, Eva Department of Computer Architecture and Automation University Complutense of Madrid Madrid28040 Spain Institute for Knowledge Technology University Complutense of Madrid Madrid28040 Spain

Cyanobacterial blooms emerge unpredictably on the surface of lentic water bodies, posing both ecological threats and public health risks. To effectively monitor these events, this study introduces the use of Machine Vision Systems (MVS) integrated into Autonomous Surface Vehicles (ASVs). These ASVs are capable of autonomous and safe navigation, enabling them to detect cyanobacterial blooms while avoiding obstacles. Convolutional Neural Networks (CNNs) are employed for early detection and continuous monitoring, but their effectiveness hinges on access to large, high-quality training datasets. Due to the sporadic and uncontrollable nature of bloom occurrences, acquiring sufficient real-world images for training and validating CNN models is a significant challenge. To overcome this, the Stable Diffusion XL (SDXL) text-to-image generative model is utilized to produce realistic synthetic images, ensuring a sufficient dataset for training. However, SDXL alone struggles to accurately depict cyanobacterial blooms. To address this limitation, DreamBooth is used to fine-tune SDXL with a small set of real bloom-specific image patches. To ensure the diversity of the synthetic dataset, detailed prompts for SDXL are generated using a Large Language Model (LLM). The combination of SDXL fine-tuning with LLM-driven prompts design applied to environmental monitoring and autonomous navigation in lentic environments represents the core innovation of this work. A dual-task CNN model is then trained on the synthetic dataset to simultaneously detect blooms and obstacles. Experimental results demonstrate the effectiveness and novelty of the proposed approach, showing improvements of up to 15.74% in object detection and 6.48% in semantic segmentation compared to the baseline dataset. © 2025 The Author(s)

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DESIGNING AN ONLINE TRAINING MODULE TO DEVELOP VIRTUAL AND BLENDED INTERNATIONAL MODALITIES IN HIGHER EDUCATION 21

DESIGNING AN ONLINE TRAINING MODULE TO DEVELOP VIRTUAL AND B...

引用

21st International Conferences on Mobile Learning, ML 2025 and 10th International Conference on Educational Technologies, ICEduTech 2025

作者： Barana, Alice Chatzea, Vasiliki Eirini Henao, Kelly Hildebrandt, Ania Maria Conte, Marina Marchisio Samoilovich, Daniel Triantafyllidis, Georgios Vidakis, Nikolas Department of Molecular Biotechnology and Health Sciences University of Turin Piazza Nizza 44 Torino10153 Italy Department of Electrical & Computer Engineering Hellenic Mediterranean University Estavromenos Heraklion71410 Greece Columbus Association 1 rue Moillis Paris75015 France Department of Architecture Design and Media Technology Aalborg University A. C. Meyers Vænge Copenhagen152450 Denmark

ISBN: (纸本)9789898704665

Virtual and blended international collaboration activities, including Collaborative Online International Learning and Blended Intensive Programmes, offer inclusive and sustainable alternatives to traditional mobility programmes. Effective training programmes for teachers and administrative staff are indispensable to enhance the higher education institutions’ capability to implement similar activities. This paper introduces an online training module aimed at providing higher education teachers and staff with competencies to implement virtual and blended modalities of international collaboration. The module is designed according to the principles of the Self-Determination Theory and the Analysis, Design, Development, Implementation and Evaluation (ADDIE) model. The paper explores whether the design of the module is effective in creating a valuable learning experience and what its strengths and areas for improvement are. Results were derived from 150 responses to the final survey questions completed by participants who completed the online training module, analysed qualitatively and quantitatively. Findings show that the autonomy, structure, and involvement support were perceived as effective in achieving the desired learning outcomes. The results offer valuable insights into the design of training modules for higher education staff to develop international collaboration modalities. © 2025 Proceedings of the International Conferences on Mobile Learning 2025 and Educational Technologies 2025. All rights reserved.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

An Efficient Intrusion Detection System using Advanced Machine Learning Techniques in SDN for Healthcare System

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Asif, Muhammad Waseem Aqdus, Aqsa Amin, Rashid Chaudhry, Shehzad Ashraf Alsubaei, Faisal S. Iqbal, Sajid Department of Computer Science and IT The University of Lahore Lahore54000 Pakistan Department of Computer Science University of Chakwal Chakwal48800 Pakistan Department of Computer Science and Information Technology College of Engineering Abu Dhabi University Abu Dhabi United Arab Emirates Department of Software Engineering Faculty of Engineering and Architecture Nisantasi University Istanbul Turkey The Department of Cybersecurity College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia

The quick advancement of healthcare systems necessitates robust and efficient network security keys to defend sensitive patient records and guarantee uninterrupted service delivery. The current IDS has many challenges, such as a high false positive rate, poor accuracy of detection, slow response to threats, and inability to scale well. This paper proposes an efficient and real-time intrusion detection system (IDS) using advanced machine learning techniques within a software-defined networking (SDN) framework specifically tailored for healthcare systems. The proposed architecture implements a Machine Learning (ML) model that combines the SVM and KNN to better identify malicious activities. Full sets of detection and mitigation capabilities are implemented to address different types of traffic in the network with the least interference. Through the different evaluation measures, the efficiency of the proposed model is assured. Network performance is determined by success rate queries, packet losses in each domain path, and the CPU being used by the system. Responsiveness is measured through delay metrics grounded on end-to-end delay, hop-to-hop packet delay, latency rate, and propagation delay. Moreover, model accuracy fidelity is reviewed via precision assessment, alpha (α) affecting the accuracy of the model, and confusion matrix with different techniques with the proposed hybrid SVM-KNN model. Last of all, a comparison of the security of the models in question strengthens the argument in favor of the proposed model. More specifically, flow and network topology diagrams are included to show how integration may be accomplished in linkage or merger with existing healthcare networks. The results also present a 30% overall advancement in detection and mitigation by presenting the hybrid SVM-KNN model to overcome other traditional models. This proposed model shows significant improvements not less than 20-30% improvement in CPU use, 30-50% reduction in end-to-end delay,

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

SiamCircle: Trajectory Representation Learning in Free Settings 23rd

SiamCircle: Trajectory Representation Learning in Free Sett...

引用

23rd International Symposium on Intelligent Data Analysis, IDA 2025

作者： Nasri, Maedeh Baratchi, Mitra Koutamanis, Alexander Rieffe, Carolien Department of Developmental Psychology Leiden University Leiden Netherlands Leiden Institute of Advanced Computer Science Leiden University Leiden Netherlands Faculty of Architecture and the Built Environment Delft University of Technology Delft Netherlands Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands Department of Psychology and Human Development Institute of Education UCL London United Kingdom

ISBN: (纸本)9783031913976

Trajectory representation learning (TRL) is an intermediate step in handling trajectory data to realize various downstream machine-learning tasks. While most previous TRL research focuses on modeling structured movements in large-scale urban spaces (e.g., cars or pedestrians on streets), this paper focuses on a more challenging scenario of modeling free movement in small-scale social spaces (e.g., children playing in a schoolyard). We present a TRL model, SiamCircle, to process raw trajectories without additional feature extraction to prevent information loss. SiamCircle adopts a Siamese network with Circle Loss to learn trajectory embeddings. Furthermore, SiamCircle employs a data augmentation process to enable self-supervised learning and enrich the input data to address the limited access to high-quality data and ground truth. We evaluate the performance of SiamCircle in downstream tasks using trajectory ranking and clustering performance via seven evaluation metrics collectively. Using an ablation study, we explored the impact of different loss functions on the model’s performance. Accordingly, we selected a 2-D convolutional design with Circle Loss as the best-performing model. In a comparative study, we compared our model against three other baselines. We observed up to 19% improvements in trajectory ranking tasks and achieved the highest average rank in supervised clustering tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Sorting

来源：评论

学校读者我要写书评

暂无评论

Optimal Synthesis of Memristive Mixed-Mode Circuits

Optimal Synthesis of Memristive Mixed-Mode Circuits

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Ilia Polian Xianyue Zhao Li-Wei Chen Felix Bayhurst Ziang Chen Heidemarie Schmidt Nan Du University of Stuttgart Institute of Computer Architecture and Computer Engineering Stuttgart Germany Department of Quantum Detection Friedrich Schiller University Jena Institute for Solid State Physics Leibniz Institute of Photonic Technology Jena Germany

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Memristive crossbars are attractive for in-memory computing due to their integration density combined with compute and storage capabilities of their basic devices. However, yield and fidelity of emerging memristive technologies can make their reliable operation unattainable, thus raising interest in simpler topologies. In this paper, we consider synthesis of Boolean functions on 1D memristive line arrays. We propose an optimal procedure that can fully utilize the rich electrical behavior of memristive devices, mixing stateful (resistance-input) and non-stateful (voltage-input) operations as desired by the designer, leveraging their respective strengths. The synthesis method is based on Boolean satisfiability (SAT) solving and supports flexible constraints to enforce, e.g., restrictions of the available peripher-als. We experimentally validate memristive logic circuits beyond individual logic gates by demonstrating the operation of a Galois field multiplier using a 1D line array of 10 memristors in parallel, highlighting the robust performance of our proposed mixed-mode circuit and its synthesis procedure.

关键词： Boolean functions Memristors Europe Logic gates In-memory computing Topology Logic Reliability Galois fields Logic arrays

来源：评论

学校读者我要写书评

暂无评论

Inspiring Creativity: A Comparative Study of Hands-On Artifact Interaction and 3D Art Viewing

Inspiring Creativity: A Comparative Study of Hands-On Artifa...

引用

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering (ECTI-NCON)

作者： Jirawat Sookkaew Pipatpong Saephoo Pheeraphon Changjaikla Department of Computer Graphic and Multimedia School of Information and Communication Technology University of Phayao Thailand Department of Digital Business School of Information and Communication Technology University of Phayao Thailand Department of Visual Communication Design School of of Architecture Kasem Bundit University Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

The use of 3D technology in creative processes not only facilitates the creation of complex and intricate works but also provides opportunities for creators to experiment and develop unique and engaging concepts. Additionally, multimedia and 3D technology enhance the diversity and interest of the audience's experience. This study focuses on comparing the impact of using 3D models versus viewing ancient artifacts in traditional formats on enhancing creativity among students in different groups. Descriptive data analysis revealed that both groups had equal mean outputs (7.14 pieces per person), but the group using 3D models (Group 2) showed greater consistency in their work, with lower variance (5.14) and standard deviation (2.27) compared to the group using traditional visuals (Group 1), which had higher variance (27.24) and standard deviation (5.22).The findings suggest that implementing 3D technology in education goes beyond preserving historical information - it serves as a crucial tool for stimulating creativity and fostering innovation. This technology enables the development of immersive learning environments that can adapt to individual learning styles while promoting collaborative and cross-disciplinary approaches to education.

关键词： Training Solid modeling Technological innovation Visualization Three-dimensional displays Art Education Problem-solving Creativity Standards

来源：评论

学校读者我要写书评

暂无评论

Investigating Context-Aware Collaborative Text Entry on Smartphones using Large Language Models 25

Investigating Context-Aware Collaborative Text Entry on Smar...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Weihao Chen Yuanchun Shi Yukun Wang Weinan Shi Meizhu Chen Cheng Gao Yu Mei Yeshuang Zhu Jinchao Zhang Chun Yu Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China and Qinghai University Xining Qinghai China School of Architecture Tsinghua University Beijing China Pattern Recognition Center WeChat AI Tencent Inc. Beijing China

来源：评论

学校读者我要写书评

暂无评论

Integrating Structural Information: Comparing Classification-Based and Segmentation-Based Predictors in Bioinformatics (Case Study: Protein-Peptide Region Residue-Level Interaction) Using Structural Information

Integrating Structural Information: Comparing Classification...

引用

International CSI computer Conference, CSICC

作者： Shima Shafiee Abdolhossein Fathi Faezeh Safari Department of Computer Engineering and Information Technology Razi University Kermanshah Iran Faculty of Eng. Architecture and Info. Tech. School of Electrical Eng. and Computer Science University of Queensland Brisbane QLD Australia

ISBN: (数字)9798331523114

ISBN: (纸本)9798331523121

Understanding the regions where proteins bind to peptides is vital for studying diseases like cancer, as it sheds light on various cellular processes and aids in drug discovery. Although researchers can experimentally investigate protein-peptide interactions at the region level by analyzing the structures of their complexes, only a limited number of these structures are known. Additionally, experiments to determine these interactions can be both costly and time-consuming. Computational methods provide an alternative and complementary approach to experimental techniques. As a result, using computational methods to predict peptide-binding regions can significantly enhance the efficiency and cost-effectiveness of experimental research. To leverage these advantages, this study introduces a new method named Structure-based Prediction of Residue-level Interaction of Peptides (SPRINT-Pep), designed to pinpoint the binding regions between proteins and peptides. This approach leverages two distinct predictive models: a classification-based model combining DeepResNet with a Support Vector Machine (SVM) and a segmentation-based model called DeepU-Net. Our predictions outperform other state-of-the-art methods in terms of F-measures (by at least 23%), precision (by at least 3.7%), and the balance between sensitivity and specificity (by about 7.7%). These findings demonstrate the proficiency of the proposed method.

关键词： Proteins Support vector machines Deep learning Peptides Predictive models Sensitivity and specificity Prediction algorithms Robustness Drug discovery Testing

来源：评论

学校读者我要写书评

暂无评论

Critical assessment of opal mining techniques, tools, market system, environmental impact challenges, and prospects — A systematic review

引用

Arabian Journal of Geosciences 2025年第6期18卷 1-14页

作者： Adamu, Anteneh Yayeh Eneyew, Demessie Mulu Ejigu, Assamen Ayalew Dubiniewicz, Andrzej Kajetan Endalew, Sisay Awoke Nigussie, Asmare Belay Amognehegn, Asnake Enawgaw School of Civil and Water Resource Engineering & Architecture Kombolcha Institute of Technology Kombolcha Ethiopia Department of Electrical and Computer Engineering Kombolcha Institute of Technology Kombolcha Ethiopia Faculty of Earth Sciences and Spatial Management Nicolaus Copernicus University Torun Poland Department of Chemistry College of Natural Science Wollo University Dessie Ethiopia

The study presents the existing challenges in opal mining in the Delanta area (mining methods, tools, market system, and environmental impact) and provides possible recommendations to overcome these challenges. Literature review, data collection, field survey, and data analysis were used as methods for this study. Environmental impact assessment also applied in the study area. Based on the study, the opal mining system in the Delanta area is performed in traditional ways and this method is not benefiting the local miners as well as the country. In the area, due to roof collapse of mining sites, three to eight artesian small-scale miners are dying each year. Opal quality deterioration (wastes locally called Ajara) because of cracking is the other main challenge in the study area. Moreover, environmental problems such as deforestation, concealed underground channels, landslides, the loss of numerous species’ habitats, annihilation of flora, land degradation, soil erosion and pollution, water pollution, air pollution, downstream sedimentation, and the covering of topsoil on agricultural land, which affects the farming system are the main findings of this study. In the study area, only 3% of the opal is processed, while 97% is rough, and this results in loss of income for the country. Finally, the study indicated the possible solutions in opal exploration and mining methods, as well as market system for the safe and sustainable extraction of Delanta opal resources. The study recommended for future work to design a safe mining method, a ventilation shaft, develop a smartphone app for quality grading and branding for selling, developing a low-cost opal cutting and polishing machine for value addition, and establishing training centers. In addition, the sector in the area also needs solar systems planting for lighting of mining sites, design and development of waste soil removal technology/conveyors and hammers for safe mining, sustainable development and management.

关键词：

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：