检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zeng, Wenzheng Xiao, Yang Wei, Sicheng Gan, Jinfang Zhang, Xintao Cao, Zhiguo Fang, Zhiwen Zhou, Joey Tianyi Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Biomedical Engineering Southern Medical University Guangzhou510515 China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou510280 China Singapore 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 unconstrained films to reveal "in the wild" characteristics. Meanwhile, a real-time multi-person eyeblink detection method is also proposed. Being different from the existing counterparts, 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. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

What Matters for 3D Scene Flow Network

arXiv

引用

arXiv 2022年

作者： Wang, Guangming Hu, Yunzhe Liu, Zhe Zhou, Yiyang Tomizuka, Masayoshi Zhan, Wei Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Mechanical Systems Control Laboratory University of California Berkeley United States

3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames. Thus, it is critical for the flow embeddings to capture the correct overall direction of the motion. However, previous works only search locally to determine a soft correspondence, ignoring the distant points that turn out to be the actual matching ones. In addition, the estimated correspondence is usually from the forward direction of the adjacent point clouds, and may not be consistent with the estimated correspondence acquired from the backward direction. To tackle these problems, we propose a novel all-to-all flow embedding layer with backward reliability validation during the initial scene flow estimation. Besides, we investigate and compare several design choices in key components of the 3D scene flow network, including the point similarity calculation, input elements of predictor, and predictor & refinement level design. After carefully choosing the most effective designs, we are able to present a model that achieves the state-of-the-art performance on FlyingThings3D and KITTI Scene Flow datasets. Our proposed model surpasses all existing methods by at least 38.2% on FlyingThings3D dataset and 24.7% on KITTI Scene Flow dataset for EPE3D metric. We release our codes at https://***/IRMVLab/3DFlow. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Inferring Topology of Networked Dynamical Systems by Active Excitations

arXiv

引用

arXiv 2022年

作者： Li, Yushan He, Jianping Chen, Cailian Guan, Xinping Dept. of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

Topology inference for networked dynamical systems (NDSs) has received considerable attention in recent years. The majority of pioneering works have dealt with inferring the topology from abundant observations of NDSs, so as to approximate the real one asymptotically. Leveraging the characteristic that NDSs will react to various disturbances and the disturbance’s influence will consistently spread, this paper focuses on inferring the topology by a few active excitations. The key challenge is to distinguish different influences of system noises and excitations from the exhibited state deviations, where the influences will decay with time and the exciatation cannot be arbitrarily large. To practice, we propose a one-shot excitation based inference method to infer h-hop neighbors of a node. The excitation conditions for accurate one-hop neighbor inference are first derived with probability guarantees. Then, we extend the results to h-hop neighbor inference and multiple excitations cases, providing the explicit relationships between the inference accuracy and excitation magnitude. Specifically, the excitation based inference method is not only suitable for scenarios where abundant observations are unavailable, but also can be leveraged as auxiliary means to improve the accuracy of existing methods. Simulations are conducted to verify the analytical results. Copyright © 2022, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection Based on Deep Learning and Collaborative Cloud-edge Computation 7

Surface Defect Detection Based on Deep Learning and Collabor...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： He, Shunjie Yang, Bo Zhu, Dafeng Li, Cheng Shanghai Jiao Tong University Department of Automation Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9781665409506

Surface defect detection is a fundamental step of quality management. Nowadays, surface defect detection system based on machine vision technology has made great progress which can gradually replace the human inspector. With the help of convolutional neural networks, the accuracy and stability of the surface defect detection algorithm are improving rapidly. However, it is difficult to process the images which have small defect areas and complex backgrounds. Furthermore, lacking defective samples and limited computation resources are also tough problems. To deal with these problems, a two-stage algorithm combined with object detection and classification networks is proposed. Transform learning and data augmentation are used to deal with the problem of lacking defect samples. Besides, a detection system based on collaborative cloud-edge computation is designed to improve the performance of the algorithm. The result shows that the proposed method has high performance and low requirements of computation resources. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB image

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Changlong Jiang Yang Xiao Cunlin Wu Mingyang Zhang Jinghong Zheng Zhiguo Cao 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 Alibaba Group 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

3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition. Our key idea is to equip A2J with strong local-global aware ability to well capture interacting hands' local fine details and global articulated clues among joints jointly. To this end, A2J is evolved under Transformer's non-local encoding-decoding framework to build A2J- Transformer. It holds 3 main advantages over A2J. First, self-attention across local anchor points is built to make them global spatial context aware to better capture joints' articulation clues for resisting occlusion. Secondly, each anchor point is regarded as learnable query with adaptive feature learning for facilitating pattern fitting capacity, instead of having the same local representation with the others. Last but not least, anchor point locates in 3D space instead of 2D as in A2J, to leverage 3D pose prediction. Experiments on challenging InterHand 2.6M demonstrate that, A2J-Transformer can achieve state-of-the-art model-free performance (3.38mm MPJPE advancement in 2-hand case) and can also be applied to depth domain with strong generalization. The code is avaliable at https://***/ChanglongJiangGit/A2J-Transformer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement

Watch the Speakers: A Hybrid Continuous Attribution Network ...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Shanglin Lei Xiaoping Wang Guanting Dong Jiang Li Yingjian Liu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Institute of Artificial Intelligence Huazhong University of Science and Technology (HUST) Wuhan China

Emotion Recognition in Conversation (ERC) has attracted widespread attention in the natural language processing field due to its enormous potential for practical applications. Existing ERC methods face challenges in achieving generalization to diverse scenarios due to insufficient modeling of context, ambiguous capture of dialogue relationships and overfitting in speaker modeling. In this work, we present a Hybrid Continuous Attributive Network (HCAN) to address these issues in the perspective of emotional continuation and emotional attribution. Specifically, HCAN adopts a hybrid recurrent and attention-based module to model global emotion continuity. Then a novel Emotional Attribution Encoding (EAE) is proposed to model intra- and inter-emotional attribution for each utterance. Moreover, aiming to enhance the robustness of the model in speaker modeling and improve its performance in different scenarios, A comprehensive loss function emotional cognitive loss $\mathcal{L}_{EC}$ is proposed to alleviate emotional drift and overcome the overfitting of the model to speaker modeling. Our model achieves state-of-the-art performance on three datasets, demonstrating the superiority of our work. Another extensive comparative experiments and ablation studies on three benchmarks are conducted to provided evidence to support the efficacy of each module. Further exploration of generalization ability experiments shows the plug-and-play nature of the EAE module in our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust H Sliding Mode controller Design of a Class of Time-Delayed Discrete Conic-Type Nonlinear Systems

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2021年第2期51卷 885-892页

作者： He, Shuping Lyu, Weizhi Liu, Fei Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi China

This paper studies the {H}_{ {\infty }} sliding mode control (SMC) problem for a class of discrete-time conic-type nonlinear systems with time-delays and uncertainties. The nonlinear terms satisfy the conic-type constraint condition that lies in a know hyper-sphere with an uncertain center. By choosing a proper Lyapunov candidate, sufficient conditions are derived to ensure the asymptotic stability of the sliding mode dynamics while achieving a prescribed {H}_{ {\infty }} disturbance attenuation level and finally converted into a minimization problem. The controller is constructed to guarantee the discrete-time reach condition and maintain the states on the prespecified sliding surface. A simulation result and a practical example related to the Chua's circuit are given at last to show the validity of our SMC strategy. © 2013 IEEE.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Predictability of Stochastic Dynamical System: A Probabilistic Perspective

Predictability of Stochastic Dynamical System: A Probabilist...

引用

IEEE Conference on Decision and control

作者： Tao Xu Jianping He Dept. of Automation Shanghai Jiao Tong University the Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

In this paper, to characterize the predictability of discrete-time continuous-state stochastic dynamical system (SDS) and use predictability to explain the probability of making accurate predictions, we have proposed a new performance metric, i.e., predictability exponent. This metric quantifies the asymptotic exponential decaying rate of the probability that prediction errors never exceed a fixed ϵ. The novelties of this predictability metric lie in that it is proposed from an asymptotic probabilistic perspective, which i) minimizes the exponential decaying rate of prediction probability, ii) holds an approximated expression deeply related with differential entropy within an error of O(ϵ), and iii) possesses a fast converging speed from finite decaying rate of O(e −K ) in the sense of probability. Numerical examples are given to illustrate the efficiency of the obtained results.

关键词： Measurement Stochastic processes Predictive models Probabilistic logic Entropy Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

A Generalized Subspace Distribution Adaptation Framework for Cross-Corpus Speech Emotion Recognition

A Generalized Subspace Distribution Adaptation Framework for...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Shaokai Li Peng Song Liang Ji Yun Jin Wenming Zheng School of Computer and Control Engineering Yantai University China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province School of Physics and Electronic Engineering Jiangsu Normal University China Key Laboratory of Child Development and Learning Science (Southeast University) Ministry of Education Research Center for Learning Science Southeast University China

In this paper, we propose a novel transfer learning framework, named generalized subspace distribution adaptation (GSDA), to tackle the challenging cross-corpus speech emotion recognition problem. First, we learn a common low-dimensional feature subspace by utilizing a generalized subspace learning method. Second, we develop a novel distance metric to reduce the divergence between the source and target corpora, which can efficiently explore the similarity and dissimilarity information in the process of knowledge transfer. Third, to demonstrate the effectiveness of our framework, we apply GSDA to the traditional subspace learning algorithms. Finally, we conduct extensive experiments by using the low-level features and deep features on three popular emotional databases, i.e., Berlin, IEMOCAP, and CVE. The results demonstrate that the proposed framework can achieve better performance than several state-of-the-art transfer learning approaches.

关键词： Measurement Learning systems Emotion recognition Databases Transfer learning Signal processing algorithms Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Fragility-Aware Stealthy Attack Strategy for Multi-Robot Systems against Multi-Hop Wireless Networks

Fragility-Aware Stealthy Attack Strategy for Multi-Robot Sys...

引用

IEEE Conference on Decision and control

作者： Yun Gao Kai Luo Chongrong Fang Jianping He Dept. of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

This paper proposes a fragility-aware stealthy attack for multiple mobile robots to secretly learn the accurate model of a multi-hop wireless network (MHWN). The stealthy attack scenario consists of three steps: active detection, node hijacking, and network eavesdropping. Our goal is to design distributed motion control strategies for naive attackers, for obtaining the connectivity information to evaluate the fragility degree of each node in MHWN. We designed a switching control strategy, which includes (i) move-to-fragile-neighbors-barycenter (MFNB) law and (ii) move-to-undetected-region-centroid (MURC) law. This strategy can drive mobile attackers to detect, hijack and eavesdrop on the MHWN’s nodes as quickly as possible. As a result, the fragility degree map of MHWN can be secretly learned to paralyze the whole network. Finally, the simulation results show that the proposed strategy is effective.

关键词： Wireless networks Simulation Spread spectrum communication Switches control systems Stability analysis Multi-robot systems

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：