检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Guo, Pinxue Hong, Lingyi Zhou, Xinyu Gao, Shuyong Li, Wanyun Li, Jinglun Chen, Zhaoyu Li, Xiaoqiang Zhang, Wei Zhang, Wenqiang the Shanghai Engineering Research Center of AI&Robotics Academy for Engineering&Technology Fudan University Shanghai China the Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China the School of Computer Engineering and Science Shanghai University Shanghai China Engineering Research Center of AI&Robotics Ministry of Education Academy for Engineering&Technology Fudan University Shanghai China

—Video Object Segmentation (VOS) task aims to segment objects in videos. However, previous settings either require time-consuming manual masks of target objects at the first frame during inference or lack the flexibility to specify arbitrary objects of interest. To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame. And we provide the extended datasets DAVIS-P and YouTubeVOS-P that with point annotations to support this task. ClickVOS is of significant practical applications and research implications due to its only 1-2 seconds interaction time for indicating an object, comparing annotating the mask of an object needs several minutes. However, ClickVOS also presents increased challenges. To address this task, we propose an end-to-end baseline approach named called Attention Before Segmentation (ABS), motivated by the attention process of humans. ABS utilizes the given point in the first frame to perceive the target object through a concise yet effective segmentation attention. Although the initial object mask is possibly inaccurate, in our ABS, as the video goes on, the initially imprecise object mask can self-heal instead of deteriorating due to error accumulation, which is attributed to our designed improvement memory that continuously records stable global object memory and updates detailed dense memory. In addition, we conduct various baseline explorations utilizing off-the-shelf algorithms from related fields, which could provide insights for the further exploration of ClickVOS. The experimental results demonstrate the superiority of the proposed ABS approach. Extended datasets and codes will be available at https://***/PinxueGuo/ClickVOS. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

A Transfer Entropy Based Approach for Fault Isolation in Industrial Robots

引用

ASME Letters in Dynamic Systems and Control 2022年第1期2卷 011009页

作者： Vallachira, Sathish Norrlof, Mikael Orkisz, Michal Butail, Sachit Robotics Service Intelligence Unit ABB Ability Innovation Center Karnataka Bangalore560048 India Department of Computer Science and Engineering Indraprastha Institute of Information Technology Delhi New Delhi110020 India ABB Robotics Division Vasteras721 68 Sweden ABB Corporate Technology Center Krakow31-038 Poland Department of Mechanical Engineering Northern Illinois University DeKalbIL60115 United States

In this paper, we cast the problem of fault isolation in industrial robots as that of causal analysis within coupled dynamical processes and evaluate the related efficacy of the information-theoretic approach of transfer entropy. To create a realistic and exhaustive dataset, we simulate wear-induced failure by increasing friction coefficient on select axes within an in-house robotic simulation tool that incorporates an elastic gearbox model. The source axis of failure is identified as one which has the highest net transfer entropy across all pairs of axes. In an exhaustive simulation study, we vary the friction successively in each axis across three common industrial tasks: pick and place, spot welding, and arc welding. Our results show that transfer entropy-based approach is able to detect the axis of failure more than 80% of the time when the friction coefficient is 5% above the nominal value and always when friction coefficient is 10% above the nominal value. The transfer entropy approach is more than twice as accurate as cross-correlation, a classical time series analysis used to identify directional dependence among processes. Copyright © 2021 by ASME.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Position: Social Choice Should Guide ai Alignment in Dealing with Diverse Human Feedback 41

Position: Social Choice Should Guide AI Alignment in Dealing...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Conitzer, Vincent Freedman, Rachel Heitzig, Jobst Holliday, Wesley H. Jacobs, Bob M. Lambert, Nathan Mossé, Milan Pacuit, Eric Russell, Stuart Schoelkopf, Hailey Tewolde, Emanuel Zwicker, William S. Foundations of Cooperative AI Lab Computer Science Department Carnegie Mellon University Pittsburgh United States Institute for Ethics in AI University of Oxford Oxford United Kingdom Center for Human-Compatible AI Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Potsdam Institute for Climate Impact Research Brandenburg Potsdam Germany Department of Philosophy University of California Berkeley United States Department of Philosophy and Moral Sciences Ghent University Ghent Belgium Allen Institute for AI BerkeleyCA United States Department of Philosophy University of Maryland College Park United States EleutherAI United States Department of Mathematics Union College Schenectady United States Murat Sertel Center for Advanced Economic Studies Istanbul Bilgi University Istanbul Turkey

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans' expressed preferences over multiple outputs. Another approach is constitutional ai, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about "collective" preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for ai Ethics and Safety held in Berkeley, CA, USA in December 2023. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Wearable ai Reveals the Impact of Intermittent Fasting on Stress Levels in School Children During Ramadan

Wearable AI Reveals the Impact of Intermittent Fasting on St...

引用

21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023

作者： Ahmed, Arfan Aziz, Sarah Abd-Alrazaq, Alaa Qidwai, Uvais Farooq, Faisal Sheikh, Javaid AI Center for Precision Health Weill Cornell Medicine-Qatar Doha Qatar Department of Computer Science and Engineering Qatar University Qatar Center for Digital Health and Precision Medicine Qatar Computing Research Institute Doha Qatar

ISBN: (纸本)9781643684000

Intermittent fasting has been practiced for centuries across many cultures globally. Recently many studies have reported intermittent fasting for its lifestyle benefits, the major shift in eating habits and patterns is associated with several changes in hormones and circadian rhythms. Whether there are accompanying changes in stress levels is not widely reported especially in school children. The objective of this study is to examine the impact of intermittent fasting during Ramadan on stress levels in school children as measured using wearable artificial intelligence (ai). Twenty-nine school children (aged 13-17 years and 12M / 17F ratio) were given Fitbit devices and their stress, activity and sleep patterns analyzed 2 weeks before, 4 weeks during Ramadan fasting and 2 weeks after. This study revealed no statistically significant difference on stress scores during fasting, despite changes in stress levels being observed for 12 of the participants. Our study may imply intermittent fasting during Ramadan poses no direct risks in terms of stress, suggesting rather it may be linked to dietary habits, furthermore as stress score calculations are based on heart rate variability, this study implies fasting does not interfere the cardiac autonomic nervous system. © 2023 The authors and IOS Press.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Self-supervised object-centric learning for videos 23

Self-supervised object-centric learning for videos

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Görkay Aydemir Weidi Xie Fatma Güney Department of Computer Engineering Koç University CMIC Shanghai Jiao Tong University and Shanghai AI Laboratory Department of Computer Engineering Koç University and KUIS AI Center

Unsupervised multi-object segmentation has shown impressive results on images by utilizing powerful semantics learned from self-supervised pretraining. An additional modality such as depth or motion is often used to facilitate the segmentation in video sequences. However, the performance improvements observed in synthetic sequences, which rely on the robustness of an additional cue, do not translate to more challenging real-world scenarios. In this paper, we propose the first fully unsupervised method for segmenting multiple objects in real-world sequences. Our object-centric learning framework spatially binds objects to slots on each frame and then relates these slots across frames. From these temporally-aware slots, the training objective is to reconstruct the middle frame in a high-level semantic feature space. We propose a masking strategy by dropping a significant portion of tokens in the feature space for efficiency and regularization. Additionally, we address over-clustering by merging slots based on similarity. Our method can successfully segment multiple instances of complex and high-variety classes in YouTube videos.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Irregular Change Detection in Sparse Bi-Temporal Point Clouds using Learned Place Recognition Descriptors and Point-to-Voxel Comparison

arXiv

引用

arXiv 2023年

作者： Stathoulopoulos, Nikolaos Koval, Anton Nikolakopoulos, George The Robotics and AI Group Department of Computer Electrical and Space Engineering Luleå University of Technology Luleå971 87 Sweden

Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments. This article proposes an innovative approach for change detection in 3D point clouds using deep learned place recognition descriptors and irregular object extraction based on voxel-to-point comparison. The proposed method first aligns the bi-temporal point clouds using a map-merging algorithm in order to establish a common coordinate frame. Then, it utilizes deep learning techniques to extract robust and discriminative features from the 3D point cloud scans, which are used to detect changes between consecutive point cloud frames and therefore find the changed areas. Finally, the altered areas are sampled and compared between the two time instances to extract any obstructions that caused the area to change. The proposed method was successfully evaluated in real-world field experiments, where it was able to detect different types of changes in 3D point clouds, such as object or muck-pile addition and displacement, showcasing the effectiveness of the approach. The results of this study demonstrate important implications for various applications, including safety and security monitoring in construction sites, mapping and exploration and suggests potential future research directions in this field. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Environmental Awareness Dynamic 5G QoS for Retaining Real Time Constraints in Robotic Applications

arXiv

引用

arXiv 2024年

作者： Damigos, Gerasimos Saradagi, Akshit Sandberg, Sara Nikolakopoulos, George Ericsson Research Ericsson AB Luleå Sweden The Robotics and AI Group Department of Computer Electrical and Space Engineering Luleå University of Technology Luleå Sweden

The fifth generation (5G) cellular network technology is mature and increasingly utilized in many industrial and robotics applications, while an important functionality is the advanced Quality of Service (QoS) features. Despite the prevalence of 5G QoS discussions in the related literature, there is a notable absence of real-life implementations and studies concerning their application in time-critical robotics scenarios. This article considers the operation of time-critical applications for 5G-enabled unmanned aerial vehicles (UAVs) and how their operation can be improved by the possibility to dynamically switch between QoS data flows with different priorities. As such, we introduce a robotics oriented analysis on the impact of the 5G QoS functionality on the performance of 5G-enabled UAVs. Furthermore, we introduce a novel framework for the dynamic selection of distinct 5G QoS data flows that is autonomously managed by the 5G-enabled UAV. This problem is addressed in a novel feedback loop fashion utilizing a probabilistic finite state machine (PFSM). Finally, the efficacy of the proposed scheme is experimentally validated with a 5G-enabled UAV in a real-world 5G stand-alone (SA) network. Copyright © 2024, The Authors. All rights reserved.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

EEG-based self-paced decoding of upper limb movement intention in healthy subjects 2

EEG-based self-paced decoding of upper limb movement intenti...

引用

2nd Edition IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRaiNE 2023

作者： Ceradini, Matteo Tortora, Stefano Tonin, Luca Micera, Silvestro Scuola Superiore Sant 'Anna The BioRobotics Institute Department of Excellence in Robotics and Ai Pisa Italy University of Padova Department of Information Engineering Padova Italy Padua Neuroscience Center University of Padova Padova Italy Bertarelli Foundation in Translational Neuroengineering Epfl Geneva Switzerland

ISBN: (纸本)9798350300802

EEG-based brain-machine interfaces (BMIs) offer an intuitive approach for individuals with motor impairments to control prosthetic or rehabilitation devices. Decoding movement intentions plays a vital role in accurately translating the motor execution plans of subjects, such as identifying the desired grasp type or target position. In this study, EEG signals were recorded from seven healthy subjects during self-paced reaching and grasping tasks. Power Spectral Density (PSD) and Entropy were extracted as features to assess their efficacy in discrimination between different brain states related to movement planning. Classification between anticipation of movement and resting-state periods were evaluated using machine-learning methods (Linear Discriminant Analysis, Quadratic Discriminant Analysis, and Support Vector Machines). The achieved results provide strong evidence for the feasibility of decoding movement intention, laying the foundation for future applications and advancements in the field. Attaining high accuracy in decoding movement intention holds significant potential for the translational applications of BMIs in the fields of biomedical engineering and rehabilitation. © 2023 IEEE.

关键词： brain signal processing brain-machine interface (BMI) electroencephalography movement intention decoding

来源：评论

学校读者我要写书评

暂无评论

A Fully Test-Time Adaptation Method for Motor Imagery

SSRN

引用

SSRN 2024年

作者： Peng, Yiheng Luo, Jingjing Wang, Hongbo Chen, Li Guo, Shijie Guo, Yuzhu Li, Yang The Institute of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai200433 China Engineering Research Center of AI and Robotics Ministry of Education Shanghai200043 China Department of Automation Sciences and Electrical Engineering Beihang University Beijing100191 China School of Automation Science and Electrical Engineering China

Transfer learning offers a promising solution to the annotation and calibration challenges associated with motor imagery (MI) electroencephalogram (EEG) decoding during neural-feedback rehabilitation. In this study, we address the challenge of online unsupervised cross-subject adaptation in MI-EEG classification, where target samples arrive sequentially, and we should adapt the model online with limited target data. We focus on the testing stage and propose a MI Fully Test-Time Adaptation (MI-FTTA) method that essentially enables online training using limited and unlabeled target data. MI-FTTA effectively alleviates the influence of noisy pseudo labels with teacher-student mutual learning and time-constrained sample selection. Through recalculating normalization statistics with limited accessible source and target information and prototype-based cross-domain contrastive learning, MI-FTTA adaptively enhances the representational capability of models. It thoroughly harnesses the limited online target samples to enhance adaptation performance. Experimental evaluations are conducted using three classification datasets , including two-class (BCI-IV2b), three-class (High-Gamma), and four-class (BCI-IV2a) scenarios. MI-FTTA demonstrates its superiority by surpassing direct source model deployment with an average performance gain of 4.11\% across different scenarios. Notably, our proposed approach also achieves a significant improvement over 12 different online test-time adaptation algorithms at three different backbones, thus affirming its *** work represents early endeavor in source-free fully test-time adaptation for cross-subject MI-EEG decoding. © 2024, The Authors. All rights reserved.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation

arXiv

引用

arXiv 2023年

作者： Aydemir, Görkay Akan, Adil Kaan Güney, Fatma KUIS AI Center Turkey Department of Computer Engineering Koç University Turkey

Forecasting future trajectories of agents in complex traffic scenes requires reliable and efficient predictions for all agents in the scene. However, existing methods for trajectory prediction are either inefficient or sacrifice accuracy. To address this challenge, we propose ADAPT, a novel approach for jointly predicting the trajectories of all agents in the scene with dynamic weight learning. Our approach outperforms state-of-the-art methods in both single-agent and multi-agent settings on the Argoverse and Interaction datasets, with a fraction of their computational overhead. We attribute the improvement in our performance: first, to the adaptive head augmenting the model capacity without increasing the model size;second, to our design choices in the endpoint-conditioned prediction, reinforced by gradient stopping. Our analyses show that ADAPT can focus on each agent with adaptive prediction, allowing for accurate predictions efficiently. https://***/adapt © 2023, CC BY.

关键词： Trajectories

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：