检索结果-内蒙古大学图书馆

Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年第4期133卷 1711-1726页

作者： Shao, Zhiwen Zhu, Hancheng Zhou, Yong Xiang, Xiang Liu, Bing Yao, Rui Ma, Lizhuang China Univ Min & Technol Sch Comp Sci & Technol Xuzhou 221116 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat MoE Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Minist Educ Mine Digitizat Engn Res Ctr Xuzhou 221116 Peoples R China Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China

Facial action unit (AU) detection remains a challenging task, due to the subtlety, dynamics, and diversity of AUs. Recently, the prevailing techniques of self-attention and causal inference have been introduced to AU detection. However, most existing methods directly learn self-attention guided by AU detection, or employ common patterns for all AUs during causal intervention. The former often captures irrelevant information in a global range, and the latter ignores the specific causal characteristic of each AU. In this paper, we propose a novel AU detection framework called AC2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\textrm{AC}<^>{2}$$\end{document}D by adaptively constraining self-attention weight distribution and causally deconfounding the sample confounder. Specifically, we explore the mechanism of self-attention weight distribution, in which the self-attention weight distribution of each AU is regarded as spatial distribution and is adaptively learned under the constraint of location-predefined attention and the guidance of AU detection. Moreover, we propose a causal intervention module for each AU, in which the bias caused by training samples and the interference from irrelevant AUs are both suppressed. Extensive experiments show that our method achieves competitive performance compared to state-of-the-art AU detection approaches on challenging benchmarks, including BP4D, DISFA, GFT, and BP4D+ in constrained scenarios and Aff-Wild2 in unconstrained scenarios.

关键词： Adaptively constraining self-attention Causal intervention Sample confounder Facial AU detection

来源：评论

学校读者我要写书评

暂无评论

Proxy-Based control of intelligent Assistive Walker for Intentional Sit-to-Stand Transfer

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2022年第2期27卷 904-915页

作者： Huang, Jian Yan, Shihao Yang, Daqian Wu, Dongrui Wang, Lei Yang, Zhaohui Mohammed, Samer Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Tongji Med Coll Dept Rehabil Union Hosp Wuhan 430022 Peoples R China

Sit-to-stand (STS) transfer is an easy everyday activity for healthy people, but it is a challenging task for the elderly, and patients with lower-limb weaknesses. This article presents an intelligent assistive walker, which assists the user to accomplish safe STS transfers. An STS intention recognition method is proposed based on an optimized adaptive network-based fuzzy inference system (ANFIS), where the walker is able to accurately detect a voluntary STS and to apply an appropriate control accordingly. The walker is controlled by using a proxy-based controller with respect to the detected human intention, that is measured using thin-film force sensing resistors. During the STS transfer, the assistance force is generated on-line using a virtual spring-damper between the proxy and the linear actuator of the assistive walker. The stability of the proposed controller is theoretically analyzed, and verified by simulations. Experiments with five young healthy subjects and one elderly subject demonstrated that the proposed assistive walker is able to efficiently follow the user's intention to complete stable and compliant STS transfers.

关键词： Legged locomotion Force Senior citizens Actuators Sensors Mechatronics Force measurement Assistive walker optimized adaptive network-based fuzzy inference system (ANFIS) proxy-based controller sit-to-stand (STS) transfer

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Feature Embedding for Visual Tracking 17th

Hierarchical Feature Embedding for Visual Tracking

引用

17th European Conference on Computer Vision (ECCV)

作者： Pi, Zhixiong Wan, Weitao Sun, Chong Gao, Changxin Sang, Nong Li, Chen Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Wuhan Peoples R China Tencent WeChat Shenzhen Peoples R China

ISBN: (纸本)9783031200465;9783031200472

Features extracted by existing tracking methods may contain instance- and category-level information. However, it usually occurs that either instance- or category-level information uncontrollably dominates the feature embeddings depending on the training data distribution, since the two types of information are not explicitly modeled. A more favorable way is to produce features that emphasize both types of information in visual tracking. To achieve this, we propose a hierarchical feature embedding model which separately learns the instance and category information, and progressively embeds them. We develop the instance-aware and category-aware modules that collaborate from different semantic levels to produce discriminative and robust feature embeddings. The instance-aware module concentrates on the instance level in which the inter-video contrastive learning mechanism is adopted to facilitate inter-instance separability and intra-instance compactness. However, it is challenging to force the intra-instance compactness by using instance-level information alone because of the prevailing appearance changes of the instance in visual tracking. To tackle this problem, the category-aware module is employed to summarize high-level category information which remains robust despite instance-level appearance changes. As such, intra-instance compactness can be effectively improved by jointly leveraging the instance- and category-aware modules. Experimental results on various benchmarks demonstrate the proposed method performs favorably against the state-of-the-arts. The code is available on https://***/zxgravity/CIA.

关键词： Instance-level Category-level Visual tracking

来源：评论

学校读者我要写书评

暂无评论

Stabilization of switched systems with unstable modes via mode-partition-dependent ADT

引用

Journal of the Franklin Institute 2023年第2期360卷 1308-1326页

作者： Jin, Cui-Li Wang, Qing-Guo Wang, Rui Wu, Di Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education and School of Control Science and Engineering Dalian University of Technology Dalian116024 China Institute of Artificial Intelligence and Future Networks Beijing Normal University at ZhuhaiGuangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai519087 China Key Laboratory of Advanced Technology for Aerospace Vehicles Liaoning Province and School of Aeronautics and Astronautics Dalian University of Technology Dalian116024 China

This paper concerns the stability of switched systems orchestrating between unstable modes. First, a mode partition is applied to select stabilizing switching from the switching between modes from different subsets. Second, a piecewise Lyapunov-like function is applied to decline at stabilizing switching times. Then, the stability criteria build on mode-partition-dependent average dwell time by collecting enough stabilizing switching behavior to stabilize the destabilizing switching behavior and unstable modes. Finally, the simulation verification shows the feasibility and effectiveness of the method. © 2022 The Franklin Institute

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

Sampled-data robust visual servoing control for moving target tracking of an inertially stabilized platform with a measurement delay

引用

AUTOMATICA 2022年 137卷 110105-110105页

作者： Yang, Jun Liu, Xiangyang Sun, Jiankun Li, Shihua Loughborough Univ Dept Aeronaut & Automot Engn Loughborough LE11 3TU Leics England Southeast Univ Sch Automat Key Lab Measurement & Control CSE Minist Educ Nanjing 210096 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

The vision based moving target tracking is a key technology for unmanned systems in complex environments, which is mainly limited by the visual measurement delay and kinematic uncertainties. In this paper, a time-delay disturbance observer based sampled-data control approach is developed for the visual servoing of an inertially stabilized platform. As a camera is employed to capture the position of the target, the measurement delay is generated by the acquisition and the processing of the image information. Besides, kinematic uncertainties arising from the variable feature depth and inner-loop tracking errors of given reference signals are also unavoidable. To this end, the model of the perturbed and delayed system is established firstly. Due to the measurement delay, it is quite difficult to get the current system state. As such, a new time-delay disturbance observer is developed to estimate the previous disturbance and its differences, which facilitates predictions of the current state and the current disturbance. Based on above predictions, a sampled-data robust controller is designed with the rigorous stability analysis of the closed-loop system. Experiments on tracking a target are performed to validate promising qualities of the proposed method. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Inertially stabilized platform Moving target tracking image-based visual servoing Measurement delay Disturbance observer Sampled-data control

来源：评论

学校读者我要写书评

暂无评论

Modified Nested Saturated control for Uncertain Multiple Integrators With High-Order Nonlinear Perturbation

引用

IEEE TRANSACTIONS ON CYBERNETICS 2024年第4期54卷 2086-2098页

作者： Li, Meng Zeng, Zhigang Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Educ Minist China Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

This article studies the global asymptotic stability problem of multiple integrators subject to uncertain parameters and high-order nonlinear perturbation. By introducing a modified saturation function with positive tunable parameters, three types of modified nested saturated controllers with different parameter assignments are proposed to handle the uncertain integrators with high-order nonlinear perturbation. The specific mechanism of the modified nested saturated controllers with different parameter assignments, in which control parameters appear before states, saturation functions, or saturation levels, is comprehensively analyzed. With the help of a modified saturation function, the global convergence domain of each state can be kept invariable in the saturation reduction analysis. Meanwhile, a large saturation level is obtained by adjusting positive tunable parameters. Combining with derivatives calculation and $M$ -matrix-based comparison theory, proposed saturated control schemes are utilized to handle the considered system. Finally, an active magnetic bearing (AMB) system is revisited as an uncertain mechanical system and used to verify the feasibility of the proposed control designs.

关键词： Global asymptotic stability high-order nonlinear perturbation nested saturated control saturation functions uncertain integrators

来源：评论

学校读者我要写书评

暂无评论

Model-Based and Data-Driven Contingency Filtering for Real-Time Corrective Security-Constrained Economic Dispatch 5

Model-Based and Data-Driven Contingency Filtering for Real-T...

引用

5th IEEE Conference on Energy Internet and Energy System Integration, EI2 2021

作者： Han, Donghai Yu, Yaowen He, Dingxin Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665434256

Security-constrained economic dispatch (SCED) is one of the most important problems in power system operations. Corrective SCED (CSCED) is a type of SCED that considers corrective capabilities of the power system and adjusts base case decisions according to post-contingency states. Because of the large scale of the CSCED problem, it is difficult for purely model-based approaches to meet the time limits in real-time practical operations. To leverage historical operation data, this paper develops a novel hybrid model-based and data-driven framework to accelerate the solution process of CSCED. In the offline stage, our previous model-based contingency filtering approach is utilized to label active statuses of contingencies against historical net load samples. In the online stage, a multi-label classifier based on the K-Nearest Neighbor (KNN) algorithm quickly generates an active contingency set corresponding to the real-time net load. This active contingency set can be used to calculate the economic dispatch decisions in one shot. In addition, the accuracy of our framework can be further improved by adding an optional contingency filtering procedure at the end. Numerical testing results on the IEEE RTS-96 system demonstrate the accuracy and computational efficiency of the hybrid framework as compared to a purely model-based approach. © 2021 IEEE

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Lightweight LiDAR-Camera Alignment With Homogeneous Local-Global Aware Representation

引用

IEEE TRANSACTIONS ON intelligent TRANSPORTATION SYSTEMS 2024年第11期25卷 15922-15933页

作者： Zhu, Angfan Xiao, Yang Liu, Chengxin Tan, Mingkui Cao, Zhiguo China Acad Engn Phys Inst Comp Applicat Beijing 100873 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China South China Univ Technol Sch Software Engn Guangzhou 510006 Peoples R China

In this paper, a novel LiDAR-Camera Alignment (LCA) method using homogeneous local-global spatial aware representation is proposed. Compared with the state-of-the-art methods (e.g., LCCNet), our proposition holds 2 main superiorities. First, homogeneous multi-modality representation learned with a uniform CNN model is applied along the iterative prediction stages, instead of the state-of-the-art heterogeneous counterparts extracted from the separated modality-wise CNN models within each stage. In this way, the model size can be significantly decreased (e.g., 12.39M (ours) vs. 333.75M (LCCNet)). Meanwhile, within our proposition the interaction between LiDAR and camera data is built during feature learning to better exploit the descriptive clues, which has not been well concerned by the existing approaches. Secondly, we propose to equip the learned LCA representation with local-global spatial aware capacity via encoding CNN's local convolutional features with Transformer's non-local self-attention manner. Accordingly, the local fine details and global spatial context can be jointly captured by the encoded local features. And, they will be jointly used for LCA. On the other hand, the existing methods generally choose to reveal the global spatial property via intuitively concatenating the local features. Additionally at the initial LCA stage, LiDAR is roughly aligned with camera by our pre-alignment method, according to the point distribution characteristics of its 2D projection version with the initial extrinsic parameters. Although its structure is simple, it can essentially alleviate LCA's difficulty for the consequent stages. To better optimize LCA, a novel loss function that builds the correlation between translation and rotation loss items is also proposed. The experiments on KITTI data verifies the superiority of our proposition both on effectiveness and efficiency. The source code will be released at https://***/Zaf233/Light-weight-LCA upon acceptance.

关键词： LiDAR-camera alignment deep learning homogeneous multi-modality representation local-global spatial awareness transformer

来源：评论

学校读者我要写书评

暂无评论

Power Network Smart Meter Data Driven Cross-Task Transfer Learning for Resident Characteristics Estimation

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN INDUSTRIAL E...

引用

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN INDUSTRIAL ELECTRONICS 2024年第2期5卷 652-661页

作者： Zhang, Hai-Tao Wang, Zhiyue Liu, Xingjian Zhou, Wei Ding, Yizhou Li, Yuanzheng Hu, Jiabing Huazhong Univ Sci & Technol Engn Res Ctr Autonomous Intelligent Unmanned Syst Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Intelligent Mfg Equipment & Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol China EU Inst Clean & Renewable Energy Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc & Intelligent Control Minist Educ China Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Elect & Elect Engn Wuhan 430074 Peoples R China

To extract the household attribute information from the large volume of smart meter data, this study proposes a resident characteristics estimator. Such an estimator enables energy suppliers to provide personalized services whereas to assist customers to reduce energy consumption. By leveraging the potential connections among different characteristics, a deep convolutional neural network-based cross-task transfer learning scheme is designed, which makes full use of the knowledge learned from one characteristic (such as retirement status)-based classification to estimate another relevant characteristics (such as age). Extensive experiments are conducted on the Irish dataset with 4232 households to substantiate the superiority of the proposed scheme compared with conventional deep convolutional neural networks-based learning methods.

关键词： Feature extraction Smart meters Task analysis Estimation Transfer learning Data models Convolutional neural networks control engineering learning smart grids system identification

来源：评论

学校读者我要写书评

暂无评论

Bridging Feature Gaps to Improve Multi-Organ Segmentation on Abdominal Magnetic Resonance image

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2023年第3期27卷 1477-1487页

作者： Kang, Susu Yang, Muyuan Sharon Qi, X. Jiang, Jun Tan, Shan Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Minist Educ China Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Innovat Inst Wuhan 430074 Peoples R China Univ Calif Los Angeles Sch Med Dept Radiat Oncol Los Angeles CA 90001 USA

Accurate segmentation of abdominal organs on MRI is crucial for computer-aided surgery and computer-aided diagnosis. Most state-of-the-art methods for MRI segmentation employ an encoder-decoder structure, with skip connections concatenating shallow features from the encoder and deep features from the decoder. In this work, we noticed that simply concatenating shallow and deep features was insufficient for segmentation due to the feature gap between shallow features and deep features. To mitigate this problem, we quantified the feature gap from spatial and semantic aspects and proposed a spatial loss and a semantic loss to bridge the feature gap. The spatial loss enhanced spatial details in deep features, and the semantic loss introduced semantic information into shallow features. The proposed method successfully aggregated the complementary information between shallow and deep features by formulating and bridging the feature gap. Experiments on two abdominal MRI datasets demonstrated the effectiveness of the proposed method, which improved the segmentation performance over a baseline with nearly zero additional parameters. Particularly, the proposed method has advantages for segmenting organs with blurred boundaries or in a small scale, achieving superior performance than state-of-the-art methods.

关键词： Semantics image segmentation Decoding Bioinformatics Logic gates Fuses Feature extraction MRI segmentation feature aggregation convolutional neural networks deep learning

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：