检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Depeng Wang, Tianqi Xu, Bingrong Kawaguchi, Kenji Zeng, Zhigang Suganthan, Ponnuthurai Nagaratnam The School of Artificial Intelligence and Automation The Institute of Artificial Intelligence Huazhong University of Science and Technology The Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China The School of Automation Wuhan University of Technology Wuhan430070 China The School of Computing National University of Singapore 117417 Singapore The School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore The KINDI Center for Computing Research College of Engineering Qatar University Doha Qatar

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated how to design an Innately Forgetting-Free Network (IF2Net) for continual learning context. This study proposed a straightforward yet effective learning paradigm by ingeniously keeping the weights relative to each seen task untouched before and after learning a new task. We first presented the novel representation-level learning on task sequences with random weights. This technique refers to tweaking the drifted representations caused by randomization back to their separate task-optimal working states, but the involved weights are frozen and reused (opposite to well-known layer-wise updates of weights). Then, sequential decision-making without forgetting can be achieved by projecting the output weight updates into the parsimonious orthogonal space, making the adaptations not disturb old knowledge while maintaining model plasticity. IF2Net allows a single network to inherently learn unlimited mapping rules without telling task identities at test time by integrating the respective strengths of randomization and orthogonalization. We validated the effectiveness of our approach in the extensive theoretical analysis and empirical study. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

MMTrans-MT: A Framework for Multimodal Emotion Recognition Using Multitask Learning

MMTrans-MT: A Framework for Multimodal Emotion Recognition U...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Jinrui Shen Jiahao Zheng Xiaoping Wang the School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China the School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

With the development of deep learning, emotion recognition tasks are more inclined to use multimodal data and adequate supervised information to improve accuracy. In this work, MMTrans-MT (Multimodal Transformer-Multitask), the framework for multimodal emotion recognition using multitask learning is proposed. It has three modules: modalities representation module, multimodal fusion module, and multitask output module. Three modalities, i.e, words, audio and video, are comprehensively utilized to carry out emotion recognition by a simple but efficient fusion model based on Transformer. As for multitask learning, the two tasks are defined as categorical emotion classification and dimensional emotion regression. Considering a potential mapping relationship between two kinds of emotion model, multitask learning is adopted to make the two tasks promote each other and improve recognition accuracy. We conduct experiments on CMU-MOSEI and IEMOCAP datasets. Comprehensive experiments show that the accuracy of recognition using multimodal information is higher than that using unimodal information. Adopting multitask learning promotes the performance of emotion recognition.

关键词： Learning systems Deep learning Emotion recognition Correlation Computational modeling Task analysis Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video

Real-time Multi-person Eyeblink Detection in the Wild for Un...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wenzheng Zeng Yang Xiao Sicheng Wei Jinfang Gan Xintao Zhang Zhiguo Cao Zhiwen Fang Joey Tianyi Zhou Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Biomedical Engineering Southern Medical University Guangzhou China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou China Centre for Frontier AI Research Agency for Science Technology and Research (A*STAR) Singapore Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

Real-time eyeblink detection in the wild can widely serve for fatigue detection, face anti-spoofing, emotion analysis, etc. The existing research efforts generally focus on single-person cases towards trimmed video. However, multi-person scenario within untrimmed videos is also important for practical applications, which has not been well concerned yet. To address this, we shed light on this research field for the first time with essential contributions on dataset, theory, and practices. In particular, a large-scale dataset termed MPEblink that involves 686 untrimmed videos with 8748 eyeblink events is proposed under multi-person conditions. The samples are captured from uncon-strainedfilms to reveal “in the wild“ characteristics. Meanwhile, a real-time multi-person eyeblink detection method is also proposed. Being different from the existing counter-parts, our proposition runs in a one-stage spatio-temporal way with end-to-end learning capacity. Specifically, it simultaneously addresses the sub-tasks of face detection, face tracking, and human instance-level eyeblink detection. This paradigm holds 2 main advantages: (1) eyeblink features can be facilitated via the face's global context (e.g., head pose and illumination condition) with joint optimization and interaction, and (2) addressing these sub-tasks in parallel instead of sequential manner can save time remarkably to meet the real-time running requirement. Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video. Our method also outperforms existing approaches by large margins and with a high inference speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Fault Detection Observer Design using Excluding Degree

Optimal Fault Detection Observer Design using Excluding Degr...

引用

IEEE Conference on Decision and control

作者： Feng Xu Yiming Wan Ye Wang Division of Information Science and Technology Shenzhen International Graduate School Tsinghua University Shenzhen P.R. China School of Artificial Intelligence and Automation Huazhong University of Science and Technology and Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan P.R. China Department of Electrical and Electronic Engineering The University of Melbourne Parkville VIC Australia

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

This paper proposes a novel optimal gain design method for robust fault detection using set-valued observers. First, a new fault detection performance specification is proposed for set-valued observers based on a new notion named the excluding degree of the origin from a zonotope. Second, a fractional programming problem is formulated to describe fault detection optimality of set-valued observers. Third, optimal fault detection gains are obtained by solving the fractional programming problem. Finally, numerical examples are used to illustrate the effectiveness of the proposed method.

关键词： Fault detection Design methodology Observers Programming Computational complexity Optimization Numerical stability

来源：评论

学校读者我要写书评

暂无评论

keypoint-Based Feature Matching For Partial Person Re-Identification

Keypoint-Based Feature Matching For Partial Person Re-Identi...

引用

IEEE International Conference on image processing

作者： Chuchu Han Changxin Gao Nong Sang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

As a derivative of person re-identification (re-ID), partial re- ID aims to retrieve a partial pedestrian across holistic person images captured by non-overlapping cameras. This task is more challenging and closer to real-world applications. Since we cannot locate the part of the partial image, the misaligned region compromises the performance greatly when directly (a) compare a partial pedestrian with a holistic one. To alleviate this issue, we propose a keypoint-Based Feature Matching (KBFM) network, which constructs a simple and effective framework for partial re-ID. Specifically, our architecture explicitly leverages the keypoints generated by pose estimation. Based on the visible keypoints, coordinates of the corresponding visible region can be computed. And the keypoint-based feature embeddings can be generated by bilinear sampling. When matching two images, we extract their features on the basis of shared visible keypoints, avoiding the misalignment and disturbance. Moreover, considering the triplet loss cannot be flexibly built in the partial re-ID pipeline, we improve the original sampling method and achieve significant performance. Extensive experimental results on two widely used benchmarks demonstrate significant performance improvements of our method over most state-of-the-art methods.

关键词： Feature extraction Cameras Task analysis Pose estimation Training Pipelines Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Fault detection of lithium-ion batteries subject to probabilistic parametric uncertainties 11

Fault detection of lithium-ion batteries subject to probabil...

引用

11th CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2019

作者： Liu, Yuhao Wan, Yiming Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

ISBN: (纸本)9781728106816

The fault detection task in lithium-ion battery management system (BMS) is critical to the safety and reliability of rechargeable and hybrid electric vehicles. To explicitly account for inevitable errors of battery model parameters, a robust fault detection method is proposed in this paper. The residual generator is established by exploiting an equivalent circuit model. The effect of uncertainties on the residual is parametrized as polynomial dependence on probabilistic uncertain parameters and noises. Then Gaussian mixtures are adopted to derive the residual distribution. To account for residual uncertainties in the detection decision, the weighted sum of distances from the generated residual to each Gaussian component of the residual distribution is proposed. Simulation results illustrate that our proposed method outperforms the conventional approach that does not consider parametric uncertainties. © 2019 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Bayesian deep-learning structured illumination microscopy enables reliable super-resolution imaging with uncertainty quantification

引用

Nature communications 2025年第1期16卷 5027页

作者： Tao Liu Jiahao Liu Dong Li Shan Tan Key Laboratory of Image Processing and Intelligent Control of Ministry of Education of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430074 China. State Key Laboratory of Membrane Biology Tsinghua-Peking Center for Life Sciences Beijing Frontier Research Center for Biological Structure IDG/McGovern Institute for Brain Research New Cornerstone Science Laboratory School of Life Sciences Tsinghua University Beijing 100084 China. li-dong@***. Key Laboratory of Image Processing and Intelligent Control of Ministry of Education of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430074 China. shantan@***.

The objective of optical super-resolution imaging is to acquire reliable sub-diffraction information on bioprocesses to facilitate scientific discovery. Structured illumination microscopy (SIM) is acknowledged as the optimal modality for live-cell super-resolution imaging. Although recent deep learning techniques have substantially advanced SIM, their transparency and reliability remain uncertain and under-explored, often resulting in unreliable results and biological misinterpretation. Here, we develop Bayesian deep learning (BayesDL) for SIM, which enhances the reconstruction of densely labeled structures while enabling the quantification of super-resolution uncertainty. With the uncertainty, BayesDL-SIM achieves high-fidelity distribution-informed SIM imaging, allowing for the communication of credibility estimates to users regarding the model outcomes. We also demonstrate that BayesDL-SIM boosts SIM reliability by identifying and preventing erroneous generalizations in various model misuse scenarios. Moreover, the BayesDL uncertainty shows versatile utilities for daily super-resolution imaging, such as error estimation, data acquisition evaluation, etc. Furthermore, we demonstrate the effectiveness and superiority of BayesDL-SIM in live-cell imaging, which reliably reveals F-actin dynamics and the reorganization of the cell cytoskeleton. This work lays the foundation for the reliable implementation of deep learning-based SIM methods in practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

城市耦合风险——以人为本的复杂系统视角（英文）

引用

Engineering 2025年第1期 44-50页

作者：欧阳敏程泽楷马佳欣王红卫 Stergios Aristoteles Mitoulis School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology School of Management Huazhong University of Science and Technology School of Engineering University of Birmingham

The complexity of coupled risks, which refer to the compounded effects of interacting uncertainties across multiple interdependent objectives, is inherent to cities functioning as dynamic, interdependent systems. A disruption in one domain ripples across various urban systems, often with unforeseen consequences. Central to this complexity are people, whose behaviors, needs, and vulnerabilities shape risk evolution and response effectiveness. Realizing cities as complex systems centered on human needs and behaviors is essential to understanding the complexities of coupled urban risks. This paper adopts a complex systems perspective to examine the intricacies of coupled urban risks, emphasizing the critical role of human decisions and behavior in shaping these dynamics. We focus on two key dimensions: cascading hazards in urban environments and cascading failures across interdependent exposed systems in cities. Existing risk assessment models often fail to capture the complexity of these processes, particularly when factoring in human decision-making. To tackle these challenges, we advocate for a standardized taxonomy of cascading hazards, urban components, and their interactions. At its core is a people-centric perspective, emphasizing the bidirectional interactions between people and the systems that serve them. Building on this foundation, we argue the need for an integrated, people-centric risk assessment framework that evaluates event impacts in relation to the hierarchical needs of people and incorporates their preparedness and response capacities. By leveraging real-time data, advanced simulations, and innovative validation methods, this framework aims to enhance the accuracy of coupled urban risk modeling. To effectively manage coupled urban risks, cities can draw from proven strategies in real complex systems. However, given the escalating uncertainties and complexities associated with climate change, prioritizing people-centric strategies is crucial. This ap

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visual SLAM Based on Dynamic Object Detection

Visual SLAM Based on Dynamic Object Detection

引用

第33届中国控制与决策会议

作者： Bocheng Chen Gang Peng Dingxin He Cheng Zhou Bin Hu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Shantui Construction Machinery Co. Ltd.

On the one hand,traditional visual SLAM does not consider dynamic objects in the scene,on the other hand,deep learning technology has been widely used in computer *** paper combines the two organically,and proposes an algorithm that uses dynamic object detection to improve the robustness of visual SLAM in a dynamic ***,we use the object detection network integrated into the attention mechanism to detect the dynamic target in the key ***,we follow the optical flow detection to further determine the dynamic feature points in the scene and eliminate ***,we use the static feature points for camera tracking to achieve highly robust monocular visual *** method described in this paper can not only eliminate dynamic feature points,but also retain as many static feature points as *** method described in this paper is compared with the original ORB-SLAM2 algorithm and DS-SLAM algorithm,and tested with public data *** results show that the method described in this paper can effectively eliminate the influence of dynamic objects on the visual SLAM algorithm.

关键词： Visual SLAM dynamic object detection deep learning optical flow detection attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A self-supervised learning-based 6-DOF grasp planning method for manipulator

arXiv

引用

arXiv 2021年

作者： Peng, Gang Ren, Zhenyu Wang, Hao Li, Xinde School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China IEEE senior member School of Automation South East University Nanjing China

To realize a robust robotic grasping system for unknown objects in an unstructured environment, large amounts of grasp data and 3D model data for the object are required, the sizes of which directly affect the rate of successful grasps. To reduce the time cost of data acquisition and labeling and increase the rate of successful grasps, we developed a self-supervised learning mechanism to control grasp tasks performed by manipulators. First, a manipulator automatically collects the point cloud for the objects from multiple perspectives to increase the efficiency of data acquisition. The complete point cloud for the objects is obtained by utilizing the hand-eye vision of the manipulator, and the TSDF algorithm. Then, the point cloud data for the objects is used to generate a series of six-degrees-of-freedom grasp poses, and the force-closure decision algorithm is used to add the grasp quality label to each grasp pose to realize the automatic labeling of grasp data. Finally, the point cloud in the gripper closing area corresponding to each grasp pose is obtained;it is then used to train the grasp-quality classification model for the manipulator. The results of data acquisition experiments demonstrate that the proposed method allows high-quality data to be obtained. The simulated results prove the effectiveness of the proposed grasp-data acquisition method. The results of performing actual grasping experiments demonstrate that the proposed self-supervised learning method can increase the rate of successful grasps for the manipulator. Copyright © 2021, The Authors. All rights reserved.

关键词： Manipulators

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：