检索结果-内蒙古大学图书馆

HyRSM++: Hybrid relation guided temporal set matching for few-shot action recognition

Pattern Recognition 2024年 147卷

作者： Wang, Xiang Zhang, Shiwei Qing, Zhiwu Zuo, Zhengrong Gao, Changxin Jin, Rong 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 Meta AI United States

Few-shot action recognition is a challenging but practical problem aiming to learn a model that can be easily adapted to identify new action categories with only a few labeled samples. However, existing attempts still suffer from two drawbacks: (i) learning individual features without considering the entire task may result in limited representation capability, and (ii) existing alignment strategies are sensitive to noises and misaligned instances. To handle the two limitations, we propose a novel Hybrid Relation guided temporal Set Matching (HyRSM++) approach for few-shot action recognition. The core idea of HyRSM++ is to integrate all videos within the task to learn discriminative representations and involve a robust matching technique. To be specific, HyRSM++ consists of two key components, a hybrid relation module and a temporal set matching metric. Given the basic representations from the feature extractor, the hybrid relation module is introduced to fully exploit associated relations within and cross videos in an episodic task and thus can learn task-specific embeddings. Subsequently, in the temporal set matching metric, we carry out the distance measure between query and support videos from a set matching perspective and design a bidirectional Mean Hausdorff Metric to improve the resilience to misaligned instances. Furthermore, we extend the proposed HyRSM++ to deal with the more challenging semi-supervised few-shot action recognition and unsupervised few-shot action recognition tasks. Experimental results on multiple benchmarks demonstrate that our method consistently outperforms existing methods and achieves state-of-the-art performance under various few-shot settings. The source code is available at https://***/alibaba-mmai-research/HyRSMPlusPlus. © 2023 Elsevier Ltd

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Robust Optimization for Energy Chemical Processes under Uncertainties: A Review and Tutorial 4

Data-Driven Robust Optimization for Energy Chemical Processe...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Ning, Chao Li, Longyan Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai200240 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

In recent years, data-driven robust optimization (DDRO) is becoming a popular and effective paradigm to address the challenging issue of uncertainty in energy chemical processes. This paper provides an overview of recent advances in the field of DDRO, with a primary focus on its methods and applications in process industries. Firstly, a brief introduction to various robust optimization model formulations and solution algorithms is presented. Secondly, research achievements of machine-learning enabled uncertainty sets, the corresponding DDRO, and variant techniques are summarized and analyzed in a systematic manner. Additionally, tutorial-like numerical examples are used to illustrate merits of DDRO compared with conventional robust optimization. Finally, fruitful applications of DDRO in energy chemical processes are encapsulated and categorized from domain perspectives. © 2022 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A Recipe for Scaling up Text-to-Video Generation with Text-free Videos

A Recipe for Scaling up Text-to-Video Generation with Text-f...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiang Wang Shiwei Zhang Hangjie Yuan Zhiwu Qing Biao Gong Yingya Zhang Yujun Shen Changxin Gao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Alibaba Group Zhejiang University Ant Group

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Diffusion-based text-to-video generation has witnessed impressive progress in the past year yet still falls behind text-to-image generation. One of the key reasons is the limited scale of publicly available data (e.g., 10M video-text pairs in WebVid10m vs. 5B image-text pairs in LAION), considering the high cost of video captioning. Instead, it could be far easier to collect unlabeled clips from video platforms like YouTube. Motivated by this, we come up with a novel text-to-video generation framework, termed TF-T2V, which can directly learn with text-free videos. The rationale behind is to separate the process of text decoding from that of temporal modeling. To this end, we employ a content branch and a motion branch, which are jointly optimized with weights shared. Following such a pipeline, we study the effect of doubling the scale of training set (i.e., video-only WebVid10M) with some randomly collected text-free videos and are encouraged to observe the performance improvement (FID from 9.67 to 8.19 and FVD from 484 to 441), demonstrating the scalability of our approach. We also find that our model could enjoy sustainable performance gain (FID from 8.19 to 7.64 and FVD from 441 to 366) after reintroducing some text labels for training. Finally, we validate the effectiveness and generalizability of our ideology on both native text-to-video generation and compositional video synthesis paradigms. Code and models will be publicly available at here.

关键词： Training Video on demand Scalability Pipelines Text to image Performance gain Market research

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Online Learning Distributionally Robust Energy Management of Ammonia-Based Multi-Energy Microgrid 4

Event-Triggered Online Learning Distributionally Robust Ener...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Li, Longyan Ning, Chao 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 Shanghai200240 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

This paper proposes a novel uncertainty-aware energy management framework for Multi-energy Microgrid (MEMG), which comprehensively comprises electricity, heat, natural gas, hydrogen, and ammonia. In particular, green ammonia is produced from hydrogen, which is derived from electrolysis powered by renewable energy. The proposed framework seamlessly integrates day-ahead optimal scheduling with data-driven model predictive control. To offer a just-in-time resilience to uncertainties of renewable energy and load, we further develop event-triggered online learning distributionally robust model predictive control (ET-OLDRMPC). Specifically, an event trigger mechanism is designed to enable the controller to intelligently switch between certainty-equivalence and distributionally robust schemes as per their respective advantageous regimes, thereby ensuring operation safety while mitigating unnecessary conservatism. For the distributionally robust scheme, we leverage a nonparametric Bayesian model to construct online ambiguity sets of uncertainty distributions, which encode statistical multimodality and local moment information. The effectiveness of the proposed framework is validated in a case study. © 2022 IEEE.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

来源：评论

学校读者我要写书评

暂无评论

Displacement detection method of QR code reference object based on feature points 4

Displacement detection method of QR code reference object ba...

引用

4th IEEE International Conference on Power, intelligent Computing and Systems, ICPICS 2022

作者： Yang, Qiuhui Zhang, Baoxiang Ji, Xiaoyu Guangxi Colleges and Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Wuzhou China Faculty of Computer and Electronic Information Guangxi University Nanning China Faculty of Information Technology Macau University of Science and Technology China

ISBN: (数字)9781665467735

ISBN: (纸本)9781665467735

With the continuous development of construction technology and computer technology, in order to meet the needs of concrete quality management, a real-time monitoring information system based on computer vision is established. The identification label is added to the concrete specimen to prevent the exchange of concrete specimens. According to the needs of the application scene, this paper proposes a new feature point extraction algorithm based on Harris. By improving the positioning accuracy of feature points, it can avoid the interference of background noise points or feature points in unclear focus area on feature matching and the calculation of projection matrix;and a few feature points are used to calibrate the camera, which overcomes the problem that the traditional camera calibration method needs to make a calibration board. Experiments show that the algorithm proposed in this paper has good stability to illumination, camera angle and distractors, and is flexible in application. © 2022 IEEE.

关键词： Quality management

来源：评论

学校读者我要写书评

暂无评论

Toward Understanding How the Saturation Effect Impacts the Spread of Computer Viruses 6

Toward Understanding How the Saturation Effect Impacts the S...

引用

6th International Conference on Electronic Engineering and Informatics, EEI 2024

作者： Zhang, Xianxiu Feng, Yuming Yang, Yi Zhang, Baojie School of Computer Science and Engineering Chongqing Three Gorges University Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Wanzhou404100 China School of Three Gorges Artificial Intelligence Chongqing Three Gorges University Chongqing Wanzhou404100 China

ISBN: (纸本)9798350353594

It is well known that people who know the presence of network viruses will defend against them, and the more computer viruses are detected and the more measures are taken. However, most previous computer virus propagation models have completely ignored the saturation effect. This paper investigates how the saturation effect impacts the transmission of electronic virus. For this purpose, a new transmission model of network virus is proposed, in which the virus is not very prevalent. Under certain conditions, there is a global asymptotical stable equilibrium point with no virus in this model. Finally, we give several numerical examples to exhibit that sufficient saturation effect is greatly conducive to containing network viruses. © 2024 IEEE.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Two-Stage OD Flow Prediction for Emergency in Urban Rail Transit

引用

IEEE Transactions on intelligent Transportation Systems 2024年第1期25卷 920-928页

作者： Zhu, Guangyu Ding, Jiacun Wei, Yun Yi, Yang Xu, Sendren Sheng-Dong Wu, Edmond Q. Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport The Beijing Research Center of Urban Traffic Information Sensing and Service Technologies Beijing100044 China Beijing Mass Transit Railway Operation Corporation Ltd. Beijing100014 China Yangzhou University College of Information Engineering Yangzhou225127 China National Taiwan University of Science and Technology Automation and Control Center The Graduate Institute of Automation and Control Taipei106335 Taiwan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

Urban rail transit (URT) is vulnerable to natural disasters and social emergencies including fire, storm and epidemic (such as COVID-19), and real-time origin-destination (OD) flow prediction provides URT operators with important information to ensure the safety of URT system. However, hindered by the high dimensionality of OD flow and the lack of supportive information reflecting the real-time passenger flow changes, study in this area is at the beginning stage. A novel model consisting of two stages is proposed for OD flow prediction. The first stage predicts the inflows of all stations by Long Short-Term Memory (LSTM) in real time, where the dimension is reduced compared with predicting OD flows directly. In the second stage, the notion of separation rate, namely, the proportion of inbound passengers bounding for another station, is estimated. Finally, The OD flow is predicted by multiplying the inflow and separation rate. Experiments based on Hangzhou Metro dataset show the proposed model outperforms the contrast model in weighted mean average error (WMAE) and weighted mean square error (WMSE). Results also suggest that the proposed prediction model performs better on weekdays than on weekends, and with greater accuracy on larger OD flows. © 2000-2011 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

image saliency detection method based on multi-feature maps fusion 4

Image saliency detection method based on multi-feature maps ...

引用

4th International Conference on Computer Graphics, image, and Virtualization, ICCGIV 2024

作者： Li, Xiaoli Liu, Yunpeng Zhao, Huaici Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Opto-Electronic Information Processing Shenyang China The Key Lab of Image Understanding and Computer Vision Shenyang China Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510683242

In this research, we introduce an innovative saliency detection algorithm, comprising three essential steps. Firstly, leveraging fully convolutional networks with aggregation interaction modules, we generate an initial saliency map. Secondly, we extract hand-craft and deep features to express the image, then use manifold ranking method to construct saliency maps. Ultimately, by integrating the outcomes from preceding stages, we generate the final saliency map. Experimental findings demonstrate that our method surpasses twelve cutting-edge saliency detection techniques in terms of precision, recall, F-measure, and MAE value metrics." © 2024 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Dual-Camera All-in-Focus Neural Radiance Fields

arXiv

引用

arXiv 2025年

作者： Luo, Xianrui Wu, Zijin Peng, Juewen Sun, Huiqiang Cao, Zhiguo Lin, Guosheng 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 Singapore639798 Singapore

We present the first framework capable of synthesizing the all-in-focus neural radiance field (NeRF) from inputs without manual refocusing. Without refocusing, the camera will automatically focus on the fixed object for all views, and current NeRF methods typically using one camera fail due to the consistent defocus blur and a lack of sharp reference. To restore the all-in-focus NeRF, we introduce the dual-camera from smartphones, where the ultra-wide camera has a wider depth-of-field (DoF) and the main camera possesses a higher resolution. The dual camera pair saves the high-fidelity details from the main camera and uses the ultra-wide camera’s deep DoF as reference for all-in-focus restoration. To this end, we first implement spatial warping and color matching to align the dual camera, followed by a defocus-aware fusion module with learnable defocus parameters to predict a defocus map and fuse the aligned camera pair. We also build a multi-view dataset that includes image pairs of the main and ultra-wide cameras in a smartphone. Extensive experiments on this dataset verify that our solution, termed DC-NeRF, can produce high-quality all-in-focus novel views and compares favorably against strong baselines quantitatively and qualitatively. We further show DoF applications of DC-NeRF with adjustable blur intensity and focal plane, including refocusing and split diopter. Copyright © 2025, The Authors. All rights reserved.

关键词：

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：