检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Xiang Zhang, Shiwei Cen, Jun Gao, Changxin Zhang, Yingya Zhao, Deli Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China The Hong Kong University of Science and Technology Hong Kong

Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action recognition (FSAR) task. In this work, we aim to transfer the powerful multimodal knowledge of CLIP to alleviate the inaccurate prototype estimation issue due to data scarcity, which is a critical problem in low-shot regimes. To this end, we present a CLIP-guided prototype modulating framework called CLIP-FSAR, which consists of two key components: a video-text contrastive objective and a prototype modulation. Specifically, the former bridges the task discrepancy between CLIP and the few-shot video task by contrasting videos and corresponding class text descriptions. The latter leverages the transferable textual concepts from CLIP to adaptively refine visual prototypes with a temporal Transformer. By this means, CLIP-FSAR can take full advantage of the rich semantic priors in CLIP to obtain reliable prototypes and achieve accurate few-shot classification. Extensive experiments on five commonly used benchmarks demonstrate the effectiveness of our proposed method, and CLIP-FSAR significantly outperforms existing state-of-the-art methods under various settings. The source code and Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair

arXiv

引用

arXiv 2023年

作者： Luo, Xianrui Peng, Juewen Zhao, Weiyue Xian, Ke Lu, Hao Cao, Zhiguo The Key Laboratory of Image Processing and Intelligent Control Ministry of Education The School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The S-Lab for Advanced Intelligence Nanyang Technological University Singapore

All-in-Focus (AIF) photography is expected to be a commercial selling point for modern smartphones. Standard AIF synthesis requires manual, time-consuming operations such as focal stack compositing, which is unfriendly to ordinary people. To achieve point-and-shoot AIF photography with a smartphone, we expect that an AIF photo can be generated from one shot of the scene, instead of from multiple photos captured by the same camera. Benefiting from the multi-camera module in modern smartphones, we introduce a new task of AIF synthesis from main (wide) and ultra-wide cameras. The goal is to recover sharp details from defocused regions in the main-camera photo with the help of the ultra-wide-camera one. The camera setting poses new challenges such as parallax-induced occlusions and inconsistent color between cameras. To overcome the challenges, we introduce a predict-and-refine network to mitigate occlusions and propose dynamic frequency-domain alignment for color correction. To enable effective training and evaluation, we also build an AIF dataset with 2686 unique scenes. Each scene includes two photos captured by the main camera, one photo captured by the ultra-wide camera, and a synthesized AIF photo. Results show that our solution, termed EasyAIF, can produce high-quality AIF photos and outperforms strong baselines quantitatively and qualitatively. For the first time, we demonstrate point-and-shoot AIF photo synthesis successfully from main and ultra-wide cameras. Copyright © 2023, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

General Sparse Normalization and Proportionate ASE Algorithms 5

General Sparse Normalization and Proportionate ASE Algorithm...

引用

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Hadi, Abdul Peng, Yan Qadir, Abdul Li, Yingsong Khan, Khushal College of Information and Communication Engineering Harbin Engineering University Harbin China Anhui Province Key Laboratory of Target Recognition and Feature Extraction LuAn230088 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China College of Intelligent System and Control Science Engineering Harbin Engineering University China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

Andrew's Sine Estimator (ASE) has recently been used to invent adaptive filtering, which can combat more kind of noises than conventional estimators. Inspired by the LMS and its sparse forms, normalization and proportionate ASE algorithms with Lawson constraints are constructed with the respective given names of Lawson normalization ASE (LNASE) and Lawson proportionate NASE (LPNASE). Simulations are performed to analyze the performance of these algorithms under impulsive noise. © 2022 IEEE.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

An OpenPLC-based Active Real-time Anomaly Detection Framework for Industrial control Systems

An OpenPLC-based Active Real-time Anomaly Detection Framewor...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Zheng, Chengxu Wang, Xiaopeng Luo, Xiaoyu Fang, Chongrong He, Jianping 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 The Dept. of Automation Shanghai China NSFOCUS Technologies Group Co. Ltd Beijing China

ISBN: (纸本)9781665465335

In recent years, the design of anomaly detectors has attracted a tremendous surge of interest due to security issues in industrial control systems (ICS). Restricted by hardware resources, most anomaly detectors can only be deployed at the remote monitoring ends, far away from the control sites, which brings potential threats to anomaly detection. In this paper, we propose an active real-time anomaly detection framework deployed in the controller of OpenPLC, which is a standardized open-source PLC and has high scalability. Specifically, we add adaptive active noises to control signals, and then identify a linear dynamic system model of the plant offline and implement it in the controller. Finally, we design two filters to process the estimated residuals based on the obtained model and use χ2 detector for anomaly detection. Extensive experiments are conducted on an industrial control virtual platform to show the effectiveness of the proposed detection framework. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Streaming-Data-Driven Distributionally Robust Joint Operation of Multi-Microgrids and Off-Site Hydrogen Refueling Stations under Uncertainties 11

Streaming-Data-Driven Distributionally Robust Joint Operatio...

引用

11th International Conference on Innovative Smart Grid Technologies - Asia, ISGT-Asia 2022

作者： Li, Longyan Ning, Chao Qiu, Haifeng 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 Department of Automation Shanghai China School of Electrical & Electronic Engineering Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798350399660

This paper proposes a novel online-learning-enabled hierarchical distributionally robust energy management framework for multi-microgrids (MMGs) with off-site hydrogen refueling stations (HRSs). The proposed framework integrates day-ahead scheduling, intra-day rescheduling and real-time control. The day-ahead scheduling is implemented via a central energy management system for optimal joint scheduling of the MMG systems and off-site HRSs, then the intra-day rescheduling is carried out to optimize the real-time operation and to generate the reference for local controllers. To adequately characterize the statistical properties of renewable and load uncertainties from data streams, we leverage a Dirichlet process mixture model to construct an online-update ambiguity set, which encodes multimodality and local moment information. Based upon this ambiguity set, an online-learning distributionally robust model predictive control (OL-DRMPC) is developed to enhance the tracking performance of energy storage references and to reduce conservatism while guaranteeing probabilistic operational constraints. Its effectiveness is verified in a case study. © 2022 IEEE.

关键词： Real time control

来源：评论

学校读者我要写书评

暂无评论

Effective and Efficient Intracortical Brain Signal Decoding with Spiking Neural Networks

arXiv

引用

arXiv 2024年

作者： Fu, Haotian Zhang, Peng Yang, Song Zhang, Herui Wang, Ziwei Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Department of Biomedical Engineering College of Life Science and Technology Huazhong University of Science and Technology Wuhan430074 China

A brain-computer interface (BCI) facilitates direct interaction between the brain and external devices. To concurrently achieve high decoding accuracy and low energy consumption in invasive BCIs, we propose a novel spiking neural network (SNN) framework incorporating local synaptic stabilization (LSS) and channel-wise attention (CA), termed LSS-CA-SNN. LSS optimizes neuronal membrane potential dynamics, boosting classification performance, while CA refines neuronal activation, effectively reducing energy consumption. Furthermore, we introduce SpikeDrop, a data augmentation strategy designed to expand the training dataset thus enhancing model generalizability. Experiments on invasive spiking datasets recorded from two rhesus macaques demonstrated that LSS-CA-SNN surpassed state-of-the-art artificial neural networks (ANNs) in both decoding accuracy and energy efficiency, achieving 0.80-3.87% performance gains and 14.78-43.86 times energy saving. This study highlights the potential of LSS-CA-SNN and SpikeDrop in advancing invasive BCI applications. © 2024, CC BY.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Dynamic Event-Triggered control for Multi-Agent Consensus with Relative Output Feedback

Dynamic Event-Triggered Control for Multi-Agent Consensus wi...

引用

American control Conference (ACC)

作者： Sikang Zhan Xianwei Li Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

This paper studies the consensus problem of linear multi-agent systems (MASs) with relative output measurement on undirected graphs. Output-feedback protocols are designed for both leaderless and leader-follower consensus. Different from [1], dynamic event-triggered sampling strategies are integrated to reduce the communication burdens between agents. Compared with most of the existing results which are based absolute output, the proposed protocols are based on sampled relative output. Finally, a simulation example is provided to illustrate the theoretical results.

关键词： Protocols Decentralized control Numerical simulation Topology Closed loop systems Output feedback Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation

arXiv

引用

arXiv 2024年

作者： Wu, Yizheng Pan, Zhiyu Wang, Kewei Li, Xingyi Cui, Jiahao Xiao, Liwen Lin, Guosheng Cao, Zhiguo The 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 S-Lab Nanyang Technological University Singapore639798 Singapore Nanyang Technological University Singapore639798 Singapore

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization. They intuitively utilize both instance and semantic pseudo labels in a joint learning manner. However, semantic pseudo labels contain numerous noise derived from the imbalanced category distribution and natural confusion of similar but distinct categories, which leads to severe collapses in self-training. Motivated by the observation that 3D instances are non-overlapping and spatially separable, we ask whether we can solely rely on instance consistency regularization for improved semi-supervised segmentation. To this end, we propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. We first build a parallel base 3D instance segmentation model DKNet, which distinguishes each instance from the others via discriminative instance kernels without reliance on semantic segmentation. Based on DKNet, we further design a novel instance consistency regularization framework to generate and leverage high-quality instance pseudo labels. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches. Code is available: https://***/W1zheng/InsTeacher3D. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Deployment of Microservice at Edge based on MQTT for Low Latency

The Deployment of Microservice at Edge based on MQTT for Low...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Mengqi Han Bo Yang Yuxiang Liu Sicheng Liu Qi Liu Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

With the rapid development of smart manufacturing, existing microservice deployment strategies based on the TCP protocol tend to encounter problems such as network latency, excessive header length, and port exhaustion in high concurrency scenarios. MQTT Broker can relay data between microservices, effectively alleviating these issues. However, the communication overhead of the Broker is significantly related to its deployment and the dependency of microservices. An appropriate deployment solution can significantly improve service quality. To address this issue, this paper models the deployment of MQTT Broker and microservices as a graph with cycles. By introducing auxiliary variables, the NP-hard problem is transformed into a mixed-integer quadratic programming problem, improving problem-solving efficiency and optimizing the microservices deployment strategy to reduce communication overhead. Meanwhile, a real-world heterogeneous cluster was constructed to experiment on fault detection applications, elaborating on the superiority of the microservice deployment strategy designed in this paper. Experimental results demonstrate that our approach reduces communication overhead by 20% in comparison to both the greedy strategy and the K8s strategy. This suggests that achieving an optimal balance between the number of Brokers and microservices is vital for ensuring efficient resource utilization and maintaining low communication latency, particularly as the scale of services expands.

关键词： Protocols Fault detection Microservice architectures Transforms Programming Quadratic programming Resource management Problem-solving Relays Smart manufacturing

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：