检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Jinglun Zhou, Xinyu Jiang, Kaixun Hong, Lingyi Guo, Pinxue Chen, Zhaoyu Ge, Weifeng Zhang, Wenqiang Shanghai Engineering Research Center of Ai & Robotics Academy for Engineering & Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Engineering Research Center of Ai & Robotics Ministry of Education Academy for Engineering & Technology Fudan University China

ISBN: (纸本)9798400706868

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI models encounter unseen data in real-world scenarios, rely heavily on whole-image features. These image-level features can include irrelevant information that hinders the detection of OOD samples, ultimately limiting overall performance. In this paper, we propose TagOOD, a novel approach for OOD detection that leverages vision language representations to achieve label-free object feature decoupling from whole images. This decomposition enables a more focused analysis of object semantics, enhancing OOD detection performance. Subsequently, TagOOD trains a lightweight network on the extracted object features to learn representative class centers. These centers capture the central tendencies of IND object classes, minimizing the influence of irrelevant image features during OOD detection. Finally, our approach efficiently detects OOD samples by calculating distance-based metrics as OOD scores between learned centers and test samples. We conduct extensive experiments to evaluate TagOOD on several benchmark datasets and demonstrate its superior performance compared to existing OOD detection methods. This work presents a novel perspective for further exploration of multimodal information utilization in OOD detection, with potential applications across various tasks. Code is available at: https://***/Jarvisgivemeasuit/tagood. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D 38

LCGen: Mining in Low-Certainty Generation for View-consisten...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tao, Zeng Yang, Tong Lin, Junxiong Mai, Xinji Wang, Haoran Wang, Beining Zhou, Enyu Wang, Yan Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Computer Science Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

The Janus Problem is a common issue in SDS-based text-to-3D methods. Due to view encoding approach and 2D diffusion prior guidance, the 3D representation model tends to learn content with higher certainty from each perspective, leading to view inconsistency. In this work, we first model and analyze the problem, visualizing the specific causes of the Janus Problem, which are associated with discrete view encoding and shared priors in 2D lifting. Based on this, we further propose the LCGen method, which guides text-to-3D to obtain different priors with different certainty from various viewpoints, aiding in view-consistent generation. Experiments have proven that our LCGen method can be directly applied to different SDS-based text-to-3D methods, alleviating the Janus Problem without introducing additional information, increasing excessive training burden, or compromising the generation effect. Project page is [here]. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid EEG-EMG Framework for Humanoid Control using Deep Learning Transformers

A Hybrid EEG-EMG Framework for Humanoid Control using Deep L...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Olikkal, Parthan Pillai, Branesh M. Suthakorn, Jackrit Ali, Habib Vinjamuri, Ramana University of Maryland Baltimore County Vinjamuri lab Department of Computer Science and Electrical Engineering BaltimoreMD21220 United States Mahidol University Center for Biomedical and Robotics Technology Nakorm Pathom Salaya Thailand

ISBN: (纸本)9781665481090

Brain-computer interfaces (BCIs) offer promising solutions for upper limb rehabilitation. Despite advancements in deep learning, traditional models for motor rehabilitation using electroencephalography (EEG) or electromyography (EMG) to control assistive devices require enhancement. This study aims to enhance motor control capabilities by integrating EEG and EMG signals using a Transformer-based deep learning model. Ten able-bodies subjects performed center-out tasks on a low-cost upper limb rehabilitation table, capturing 2D kinematic data, EEG, and EMG signals simultaneously. The tasks varied in complexity across four levels. Preprocessed EEG and EMG signals were fused and given as input to the proposed model, which was evaluated using three performance metrics. Results showed that the EEG-EMG combined model achieved 87.27% accuracy across all the four levels. Furthermore, the model's output successfully controlled a humanoid robot to replicate similar movements. These findings highlight the efficacy of combined EEG-EMG data in improving accuracy and performance in BCI applications, advancing assistive technologies and neurorehabilitation interventions. © 2024 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Transformers Unveiled: A Comprehensive Evaluation of Emotion Detection in Text Transcription 7

Transformers Unveiled: A Comprehensive Evaluation of Emotion...

引用

7th Edition Global Conference on Wireless and Optical Technologies, GCWOT 2024

作者： Ali, Sara Naz, Bushra Narejo, Sanam Ali, Sahil Pabani, Jitander Kumar Mehran University of Engineering and Technology National Center of Robotics and Automation Cms Lab Jamshoro Pakistan Mehran University of Engineering and Technology Department of Computer Systems Engineering Jamshoro Pakistan Mehran University of Engineering and Technology National Center of Rorotics and Automation Cms Lab Jamshoro Pakistan Dawood University of Engineering and Technology Department of Telecommunication Engineering Karachi Pakistan

ISBN: (纸本)9798331534271

The fast growth of digital communication via smartphones and social media has made textual data as one of the most essential forms of people's expressions. Accurate emotion discovery from text is thus important for applications in customer sentiment analysis and interactive technologies, be it a web, desktop, or mobile application, an intelligent robot, or minor connected devices. This paper is intended to evaluate the performance of five state-of-the-art transformer models, including BERT, ALBERT, DistilBERT, Transformer XL, and RoBERTa, for multiclass emotion detection using the IEMOCAP dataset. From the results, it is observed that DistilBERT has the highest accuracy of 79.2%, implying an effective approach in balancing model size and performance. These research show that smaller models like DistilBERT often outperform larger models by reducing their overfitting and computational demands. The findings also highlights the need for task-specific fine-tuning and optimization in emotion detection. © 2024 IEEE.

关键词： DistilBERT IEMOCAP NLP Text Emotion Detection Transformers

来源：评论

学校读者我要写书评

暂无评论

DeTrack: In-model Latent Denoising Learning for Visual Object Tracking 38

DeTrack: In-model Latent Denoising Learning for Visual Objec...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhou, Xinyu Li, Jinglun Hong, Lingyi Jiang, Kaixun Guo, Pinxue Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Interpretable CNN for the Segmentation of the Left Ventricle in Cardiac MRI by Real-Time Visualization

引用

computer Modeling in Engineering & Sciences 2023年第5期135卷 1571-1587页

作者： Jun Liu Geng Yuan Changdi Yang Houbing Song Liang Luo Robotics Institute School of Computer ScienceCarnegie Mellon UniversityPittsburghPA15217USA Department of Electrical&Computer Engineering College of EngineeringNortheastern UniversityBostonMA02115USA Security and Optimization for Networked Globe Laboratory(SONG Lab) Embry-Riddle Aeronautical UniversityDaytona BeachFL32114USA School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu610054China

The interpretability of deep learning models has emerged as a compelling area in artificial intelligence *** safety criteria for medical imaging are highly stringent,and models are required for an ***,existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and ***,the interpretability of CNNs has come into the *** medical imaging data are limited,many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public Image Net datasets by the transfer learning ***,this generates many unreliable parameters and makes it difficult to generate plausible explanations from these *** this study,we trained from scratch rather than relying on transfer learning,creating a novel interpretable approach for autonomously segmenting the left ventricle with a cardiac *** enhanced GPU training system implemented interpretable global average pooling for graphics using deep *** deep learning tasks were *** included data management,neural network architecture,and *** system monitored and analyzed the gradient changes of different layers with dynamic visualizations in real-time and selected the optimal deployment *** results demonstrated that the proposed method was feasible and efficient:the Dice coefficient reached 94.48%,and the accuracy reached 99.7%.It was found that no current transfer learning models could perform comparably to the ImageNet transfer learning *** model is lightweight and more convenient to deploy on mobile devices than transfer learning models.

关键词： Interpretable graphics training visualization image segmentation left ventricle CNNs global average pooling

来源：评论

学校读者我要写书评

暂无评论

Trash Detection in Water Bodies Using Yolo With Explainable AI Insight

Trash Detection in Water Bodies Using Yolo With Explainable ...

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Shafaq Rasheed Amal Mirza Muhammad Saad Saeed Muhammad Haroon Yousaf Department of Computer Engineering University of Engineering and Technology Taxila Pakistan Swarm Robotics Lab National Center of Robotics and Automation Taxila Pakistan

ISBN: (数字)9798350355703

ISBN: (纸本)9798350355710

Waste disposal into water bodies is a serious concern for environmental engineers, often resulting in urban flooding, soil degradation in agricultural areas, and freshwater pollution. Additionally, trash accumulation in water bodies threatens ma-rine life by introducing contaminants through storm drains, rivers, and other channels. Furthermore, the unique character-istics of underwater environments, including high noise levels, low visibility, and color variation, pose challenges for trash detection. Thus, addressing this issue is crucial for environmental sustainability. The work focuses on both floating and submerged trash in water bodies. Typically, the detection of trash on water bodies is impacted by environmental variability, diverse appearance, and background clutter. These conditions also make usual object detection techniques less effective. Deep learning methods have shown promise in handling challenging visual tasks, therefore researchers have turned to them to get over these challenges. In this work, we focus on applying different versions of YOLO to the problem of water trash detection. To assess these models' performance, we use four different datasets: Trash Flow rate Dataset, DeepTrash, FloW, and TrashICRA. Each dataset represents various trash types under different conditions such as underwater trash and floating trash. Our study attempts to identify the best method suitable for the detection of aquatic waste. Our results highlight the effectiveness of YOLO variants in identifying the presence of trash in water ecosystems. By leveraging Grad-CAM we gain insights into the interpretability and transparency of deep learning models thus enabling Explainable AI. This approach will also contribute to the understanding and trustworthiness of artificial systems deployed for trash detection applications by providing a transparent view of decision making process of deep learning models.

关键词： Deep learning YOLO Visualization Explainable AI Storms Biological system modeling Soil Water pollution Waste disposal robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity in local governments: A systematic review and framework of key challenges

Urban Governance

引用

Urban Governance 2025年第1期5卷 1-19页

作者： Hossain, Sk Tahsin Yigitcanlar, Tan Nguyen, Kien Xu, Yue City 4.0 Lab School of Architecture and Built Environment Queensland University of Technology 2 George Street Brisbane 4000 QLD Australia School of Electrical Engineering and Robotics Queensland University of Technology 2 George Street Brisbane 4000 QLD Australia School of Computer Science Queensland University of Technology 2 George Street Brisbane 4000 QLD Australia

Cybersecurity has emerged as a critical concern in modern urban governance, as local governments now extend their responsibilities beyond traditional infrastructure management to safeguard digital systems and citizen data in increasingly digitised smart city environments. Despite the importance of robust cybersecurity measures, there is a concerning gap—i.e., local governments often exhibit a cybersecurity posture that is inadequately prepared to counter the rising cyber threats. This discrepancy underscores the urgency for a comprehensive understanding of the challenges restricting effective cybersecurity in local governmental settings. This paper aims to elucidate these challenges of local governments in a structured framework utilising a systematic literature review method named the PRISMA protocol. The findings reveal that the stakes are high when it comes to cybersecurity for local governments, with the key challenges being financial resource constraints, technological vulnerabilities, human factors, and the regulatory framework. This study recommends improving interdepartmental coordination, adopting relevant policies, and executing targeted cybersecurity training to address these challenges. The study also highlights unconventional approaches to mitigate financial and skill resource limitations, including the utilisation of open-source security tools, outsourcing specific cybersecurity functions, and establishing collaborations with local cybersecurity agencies, academic institutions, and the private sector to obtain expertise and advanced resources. Overall, this study offers valuable insights into the critical cybersecurity challenges faced by local governments and provides specific recommendations, equipping urban policymakers, administrators, and researchers with valuable guidance to enhance cybersecurity resilience within this critical yet understudied research domain. © 2024 The Author(s)

关键词： Cyber threat Cybersecurity Local government Municipality Smart city Urban governance

来源：评论

学校读者我要写书评

暂无评论

Preference detection of the humanoid robot face based on EEG and eye movement

引用

Neural Computing and Applications 2024年第19期36卷 11603-11621页

作者： Wang, Pengchao Mu, Wei Zhan, Gege Wang, Aiping Song, Zuoting Fang, Tao Zhang, Xueze Wang, Junkongshuai Niu, Lan Bin, Jianxiong Zhang, Lihua Jia, Jie Kang, Xiaoyang Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI and Robotics Ministry of Education Shanghai Engineering Research Center of AI and Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai200040 China Yiwu Research Institute of Fudan University Zhejiang Yiwu322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

The face of a humanoid robot can affect the user experience, and the detection of face preference is particularly important. Preference detection belongs to a branch of emotion recognition that has received much attention from researchers. Most of the previous preference detection studies have been conducted based on a single modality. In this paper, we detect face preferences of humanoid robots based on electroencephalogram (EEG) signals and eye movement signals for single modality, canonical correlation analysis fusion modality, and bimodal deep autoencoder (BDAE) fusion modality, respectively. We validated the theory of frontal asymmetry by analyzing the preference patterns of EEG and found that participants had higher alpha wave energy for preference faces. In addition, hidden preferences extracted by EEG signals were better classified than preferences from participants' subjective feedback, and also, the classification performance of eye movement data was improved. Finally, experimental results showed that BDAE multimodal fusion using frontal alpha and beta power spectral densities and eye movement information as features performed best, with the highest average accuracy of 83.13% for the SVM and 71.09% for the KNN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

IoT based Truck Wheel Temperature Monitoring System

IoT based Truck Wheel Temperature Monitoring System

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Zaid, Mohd Ahmad, Nadeem Aljamal, Mohammed Patel, Sarosh Khan, Asif Dept. of Computer Science and Engineering Integral University Lucknow India Dept. of Electronics and Communication Engg. Goel Institute of Technology and Managment Lucknow India School of Engineering University of Bridgeport United States Integral Robotics Lab Dept. of Computer Application Integral University Lucknow India

ISBN: (纸本)9798350374933

The main objective of this paper is to design an IoT based truck wheel temperature monitoring system using Arduino board with the aim to overcome endanger and raise the safety measures for truck and goods. By designing and implementing a temperature-detecting system, we can detect the temperature of the wheels trucks. By the use of such detecting device we can prevent the major problem associated with wheel’s temperature and may avoid the major accidents. This monitoring system senses the temperature data of the wheel and transmits through the Wi-Fi module. In addition, it upgrades Thingspeak channel that can collect the data and it can easily be accessed by the transport agency and the truck driver. This can further be analysed using any computer system or mobile with internet connectivity anywhere across the globe to take real-time decision. The core function of the proposed detecting system is to monitor the real- time value of truck wheel temperature and to inform the concerned people. © 2024 IEEE.

关键词： Wi-Fi

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：