检索结果-内蒙古大学图书馆

TECMH:Transformer-Based Cross-Modal Hashing For Fine-Grained Image-Text Retrieval

computers, Materials & Continua 2023年第5期75卷 3713-3728页

作者： Qiqi Li Longfei Ma Zheng Jiang Mingyong Li Bo Jin College of Computer and Information Science Chongqing Normal UniversityChongqing401331China Institute of Systems and Robotics(ISR) Department of Electrical and Computer Engineering(DEEC)University of CoimbraCoimbraPortugal

In recent years,cross-modal hash retrieval has become a popular research field because of its advantages of high efficiency and low ***-modal retrieval technology can be applied to search engines,crossmodalmedical processing,*** existing main method is to use amulti-label matching paradigm to finish the retrieval ***,such methods do not use fine-grained information in the multi-modal data,which may lead to suboptimal *** avoid cross-modal matching turning into label matching,this paper proposes an end-to-end fine-grained cross-modal hash retrieval method,which can focus more on the fine-grained semantic information of multi-modal ***,the method refines the image features and no longer uses multiple labels to represent text features but uses BERT for ***,this method uses the inference capabilities of the transformer encoder to generate global fine-grained ***,in order to better judge the effect of the fine-grained model,this paper uses the datasets in the image text matching field instead of the traditional label-matching *** article experiment on Microsoft COCO(MS-COCO)and Flickr30K datasets and compare it with the previous *** experimental results show that this method can obtain more advanced results in the cross-modal hash retrieval field.

关键词： Deep learning cross-modal retrieval hash learning transformer

来源：评论

学校读者我要写书评

暂无评论

Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5575-5588页

作者： Jiang, Zihan Ma, Yiqun Shi, Bingyu Lu, Xin Xing, Jian Goncalves, Nuno Jin, Bo Suzhou215000 China Northeast Forestry University College of Computer and Control Engineering Harbin150000 China University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Coimbra3030-290 Portugal

This article introduces a novel model for low-quality pedestrian trajectory prediction, the social nonstationary transformers (NSTransformers), that merges the strengths of NSTransformers and spatiotemporal graph transformer (STAR). The model can capture social interaction cues among pedestrians and integrate features across spatial and temporal dimensions to enhance the precision and resilience of trajectory predictions. We also propose an enhanced loss function that combines diversity loss with logarithmic root mean squared error (log-RMSE) to guarantee the reasonableness and diversity of the generated trajectories. This design adapts well to complex pedestrian interaction scenarios, thereby improving the reliability and accuracy of trajectory prediction. Furthermore, we integrate a generative adversarial network (GAN) to model the randomness inherent in pedestrian trajectories. Compared to the conventional standard Gaussian distribution, our GAN approach better simulates the intricate distribution found in pedestrian trajectories, enhancing the trajectory prediction's diversity and robustness. Experimental results reveal that our model outperforms several state-of-the-art methods. This research opens the avenue for future exploration in low-quality pedestrian trajectory prediction. © 2024 IEEE.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Exploring Player's Body as a Game Controller for Fitness Activity Promotion 6

Exploring Player's Body as a Game Controller for Fitness Act...

引用

6th Experiment at International Conference, exp.at 2023

作者： Simoes, Diogo Menezes, Paulo University of Coimbra Institute of Systems and Robotics Electrical and Computer Engineering Department Coimbra Portugal

ISBN: (纸本)9798350314403

In recent years, there has been a tendency for people to resort to a more sedentary lifestyle, which has only been aggravated by the COVID-19 pandemic and the evermore common remote work policies. This lack of physical activity brings negative health outcomes and can generally be difficult to overcome due to how challenging it can be for a person to find the motivation to adopt a more physically active routine. To address this issue, we propose the use of serious games as an engaging, fun, and highly motivational tool that can aid people in their quest for a healthier lifestyle. We focus on three problem areas: motor control improvement and rehabilitation, post-stroke rehabilitation, and physical activity for general health. There exist multiple solutions for these problems which often require specific equipment that may not be available to the common user. Therefore, we propose a different approach requiring solely a laptop equipped with a camera, thus making it more practical and accessible to the wider public. © 2023 IEEE.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

MuSe4ASD - An Interactive Music Station for Children with ASD 6

MuSe4ASD - An Interactive Music Station for Children with AS...

引用

6th Experiment at International Conference, exp.at 2023

作者： Lagos, Beatriz Menezes, Paulo University of Coimbra Institute of Systems and Robotics Electrical and Computer Engineering Department Coimbra Portugal

ISBN: (纸本)9798350314403

This article explores the topic involving children with autism, referencing what this condition is about, as well as the hypotheses for approaching the problem based on the literature reviewed. The proposed approach involves the creation of an adequate space with an immersive interactive system based on musical stimuli, and physical exercise to improve their communication, memory, visual and motor capabilities, and eventually potentiate the development of artistic skills. The development of this interactive system includes the development of an avatar that will be animated using Motion Capture technology, so it can interact with the child and accompany him/her while doing the exercises with fluid movements. © 2023 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Human Detection Combining RGB and Thermal Modalities

Human Detection Combining RGB and Thermal Modalities

引用

Intelligent Reality (ICIR), IEEE International Conference on

作者： Chaymaa Fakrane Kennedy O. S. Mota Cristiano Premebida Rui P. Rocha Dept. of Electrical and Computer Engineering (DEEC) Institute of Systems and Robotics (ISR) University of Coimbra Portugal

ISBN: (数字)9798331534424

ISBN: (纸本)9798331534431

This paper addresses a late-fusion approach that combines RGB and thermal (long-wave IR) modalities to enhance human detection in indoor environments for robotic perception domains. The study explores multimodal human detection using YOLO series (v5s-6s and v8s-11s models), demonstrating significant improvements in detection accuracy under challenging lighting conditions on a dataset collected by a mobile robot. The use of a Weighted-Mean (WM) as a late-fusion approach demonstrates favorable results over more complex methods such as neural networks or SVM. The WM approach is simple to implement and has a low computational cost. Additionally, it is more interpretable and modular and allows straightforward adjustments to the weights of the YOLO models and thresholds, facilitating adaptation to the target system's specific needs. The experimental results indicate that the implemented late-fusion approach improves the baseline performance in terms of mean average precision.

关键词： YOLO Support vector machines Adaptation models Accuracy Computational modeling Neural networks Lighting Indoor environment Computational efficiency Mobile robots

来源：评论

学校读者我要写书评

暂无评论

FAIR-FATE: Fair Federated Learning with Momentum 23rd

FAIR-FATE: Fair Federated Learning with Momentum

引用

23rd International Conference on Computational Science, ICCS 2023

作者： Salazar, Teresa Fernandes, Miguel Araújo, Helder Abreu, Pedro Henriques Centre for Informatics and Systems Department of Informatics Engineering of the University of Coimbra University of Coimbra Coimbra Portugal Institute of Systems and Robotics Department of Electrical and Computer Engineering of the University of Coimbra University of Coimbra Coimbra Portugal

ISBN: (纸本)9783031359941

While fairness-aware machine learning algorithms have been receiving increasing attention, the focus has been on centralized machine learning, leaving decentralized methods underexplored. Federated Learning is a decentralized form of machine learning where clients train local models with a server aggregating them to obtain a shared global model. Data heterogeneity amongst clients is a common characteristic of Federated Learning, which may induce or exacerbate discrimination of unprivileged groups defined by sensitive attributes such as race or gender. In this work we propose FAIR-FATE: a novel FAIR FederATEd Learning algorithm that aims to achieve group fairness while maintaining high utility via a fairness-aware aggregation method that computes the global model by taking into account the fairness of the clients. To achieve that, the global model update is computed by estimating a fair model update using a Momentum term that helps to overcome the oscillations of non-fair gradients. To the best of our knowledge, this is the first approach in machine learning that aims to achieve fairness using a fair Momentum estimate. Experimental results on real-world datasets demonstrate that FAIR-FATE outperforms state-of-the-art fair Federated Learning algorithms under different levels of data heterogeneity. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Multimodal Human Detection using RGB, Thermal and LiDAR modalities for Robotic Perception

Multimodal Human Detection using RGB, Thermal and LiDAR moda...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Kennedy O. S. Mota Luís Garrote Cristiano Premebida Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Portugal

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

People detection is a relevant research topic in artificial perception with wide range of applications from security, surveillance, robotics to autonomous driving. Overcoming challenges in this field involves advanced algorithms, combination of machine learning approaches, as well as the use of sensory data e.g., from cameras and LiDARs. This work addresses the problem of people detection using YOLO, a state-of-the-art object detection method, trained on three distinct data sources LiDAR, RGB (color) and ‘thermal’ (long-wave infra-red) images. The rationale for combining multiple-sensory representation relies on the assumption that each sensor has its own advantages and disadvantages, but together they normally complement each other - specially in real-world conditions. LiDAR contributes to a physically-interpretable mapping of the environment, providing precise information regarding size/dimension and location of the objects, while RGB and thermal provide relevant textural features. The sensors have been calibrated w.r.t. each other thus, allowing the LiDAR’s point-clouds to be projected into the image plane, followed by an up-sampling step, to create dense-depth maps (DM) that enable direct use of the YOLO framework. To support the experiments, a new multi-sensory dataset has been collected using a mobile robot. Besides single-modality models, this paper also explores early and late-fusion strategies. Finally, the new dataset has been made available in a Github repository 1 .

关键词： YOLO Laser radar Machine learning algorithms Surveillance Soft sensors Thermal engineering Robot vision systems Security Mobile robots Software development management

来源：评论

学校读者我要写书评

暂无评论

A Compliant Robot-Assisted Mold Polishing Application Using the Franka Emika Robot 49

A Compliant Robot-Assisted Mold Polishing Application Using ...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Xenya, Michael Christopher Cortesao, Rui Institute of Systems and Robotics University of Coimbra Electrical and Computer Engineering Department Coimbra3030-290 Portugal FOE GCTU PMB100 Accra Ghana

ISBN: (纸本)9798350331820

Metal mold casting for many application areas remains imperfect since this involves the control of numerous factors that affect workpiece quality. Surface roughness which remains one of the many issues related to metal mold cast is often mitigated by means of grinding and polishing. As many attempts are being made to address this challenge through robot-assisted techniques, we focus on rapid mold polishing using the Franka Emika (FE) robot and its programming resources, including a built-in impedance control architecture. To accomplish the objective, mold surface segmentation is necessary. For each segment, the polishing approach is based on surface normals, relative motion, and torque sensor data. Results were obtained with open platform communication-unified architecture (opc-ua) client and server that record torque and force data. Results show that tuning internal impedance control parameters for polishing tasks is feasible. © 2023 IEEE.

关键词： Polishing

来源：评论

学校读者我要写书评

暂无评论

Advances in Wireless,Batteryless,Implantable Electronics for Real‑Time,Continuous Physiological Monitoring

引用

Nano-Micro Letters 2024年第3期16卷 254-302页

作者： Hyeonseok Kim Bruno Rigo Gabriella Wong Yoon Jae Lee Woon‑Hong Yeo IEN Center for Wearable Intelligent Systems and Healthcare Georgia Institute of TechnologyAtlantaGA 30332USA George W.Woodruff School of Mechanical Engineering Georgia Institute of TechnologyAtlantaGA 30332USA School of Electrical and Computer Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Wallace H.Coulter Department of Biomedical Engineering Georgia Tech and Emory University School of MedicineAtlantaGA 30332USA Parker H.Petit Institute for Bioengineering and Biosciences Institute for MaterialsInstitute for Robotics and Intelligent MachinesGeorgia Institute of TechnologyAtlantaGA 30332USA

This review summarizes recent progress in developing wireless,batteryless,fully implantable biomedical devices for real-time continuous physiological signal monitoring,focusing on advancing human health *** considerations,such as biological constraints,energy sourcing,and wireless communication,are discussed in achieving the desired performance of the devices and enhanced interface with human *** addition,we review the recent achievements in materials used for developing implantable systems,emphasizing their importance in achieving multi-functionalities,biocompatibility,and *** wireless,batteryless devices offer minimally invasive device insertion to the body,enabling portable health monitoring and advanced disease ***,we summarize the most recent practical applications of advanced implantable devices for human health care,highlighting their potential for immediate commercialization and clinical uses.

关键词： Implantable electronics Biomedical systems Batteryless devices Wireless electronics Physiological signal monitoring

来源：评论

学校读者我要写书评

暂无评论

Multimodal Human Detection Using YOLO and Representation Learning for Robot Perception

Multimodal Human Detection Using YOLO and Representation Lea...

引用

Iberian robotics Conference (ROBOT)

作者： Kennedy O. S. Mota Diogo S. De Oliveira Luís Garrote Cristiano Premebida Department of Electrical and Computer Engineering University of Coimbra Institute of Systems and Robotics Coimbra Portugal

ISBN: (数字)9798350376364

ISBN: (纸本)9798350376371

This work concentrates on the problem of multisensor people detection using YOLO trained on four distinct modalities: depth and intensity LiDAR-maps, RGB, and ‘thermal’ images. RGB cameras, ubiquitous in this application domain, offer great resolution but struggle with adverse lighting conditions resulting in overexposed or underexposed images which then impact negatively on the performance of the algorithms. Thermal (long-wave infrared) cameras are more resilient against varying light conditions and provide complementary textural features, although with lower resolution when compared to RGB cameras. LiDAR sensors, while having a significantly low resolution, contribute to a physically interpretable mapping of the environment providing precise information regarding size/dimension and location of the objects. The main goal of this work is to tackle people detection using deep-models trained on single and multi-modality representations. To support the experimental part this work introduces a new multimodal dataset (called MID-3K). MID-3K allows the development of data fusion strategies by leveraging four modalities (obtained from three distinct exteroceptive sensors mounted on a mobile robot). Leveraging on a single-modality YOLO framework, we propose a multimodal representation learning approach to improve the baseline performance and to capture more relevant features across all input modalities. The evaluation of the proposed detection pipeline is conducted on the MID-3K dataset, where the reported results are grounded on state-of-the-art performance measures. The new dataset is available in a GitHub repository 1 1 MID-3K dataset: https://***/MID-3K/.

关键词： YOLO Representation learning Training Image resolution Laser radar Robot vision systems Thermal sensors Sensor fusion Cameras Software development management

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：