检索结果-内蒙古大学图书馆

ZSTAD: Zero-Shot Temporal Activity Detection

学校读者我要写书评

暂无评论

ZSTAD: Zero-Shot Temporal Activity Detection

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Lingling Zhang Xiaojun Chang Jun Liu Minnan Luo Sen Wang Zongyuan Ge Alexander Hauptmann School of Computer Science and Technology Xi'an Jiaotong University Xian China Ministry of Education Key Lab For Intelligent Networks and Network Security Xian China Faculty of Information Technology Monash University Australia National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xian China School of Information Technology and Electrical Engineering The University of Queensland Australia School of Computer Science Carnegie Mellon University USA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS'14 and the Charades datasets show promising performance in terms of detecting unseen activities.

关键词： Semantics Proposals Training Task analysis Feature extraction Microsoft Windows Three-dimensional displays

Twin-field quantum digital signatures

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Chun-Hui Fan, Yu-Teng Zhang, Chun-Mei Guo, Guang-Can Wang, Qin Institute of quantum information and technology Nanjing University of Posts and Telecommunications Nanjing210003 China Broadband Wireless Communication and Sensor Network Technology Key Lab of Ministry of Education NUPT Nanjing210003 China Telecommunication and Networks National Engineering Research Center NUPT Nanjing210003 China Key Laboratory of Quantum Information CAS University of Science and Technology of China Hefei Anhui230026 China

Digital signature is a key technique in information security, especially for identity authentications. Compared with classical correspondence, quantum digital signatures (QDSs) provide a considerably higher level of security, i.e., information-theoretic security. At present, its performance is limited by key generation protocols (e.g., BB84 or measurement-device-independent protocols), which are fundamentally limited in terms of channel capacity. Fortunately, the recently proposed twin-field quantum key distribution can overcome this limit. This paper presents a twin-field QDS protocol and details a corresponding security analysis. In its distribution stage, a specific key generation protocol, the sending-or-not-sending twin-field protocol, has been adopted and full parameter optimization method has been implemented. Numerical simulation results show that the new protocol exhibits outstanding security and practicality compared with all other existing protocols. Therefore, the new protocol paves the way toward real-world applications of QDSs. Copyright © 2020, The Authors. All rights reserved.

关键词： Quantum cryptography

Graph wavelet neural network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Bingbing Shen, Huawei Cao, Qi Qiu, Yunqi Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China

We present graph wavelet neural network (GWNN), a novel graph convolutional neural network (CNN), leveraging graph wavelet transform to address the shortcomings of previous spectral graph CNN methods that depend on graph Fourier transform. Different from graph Fourier transform, graph wavelet transform can be obtained via a fast algorithm without requiring matrix eigendecomposition with high computational cost. Moreover, graph wavelets are sparse and localized in vertex domain, offering high efficiency and good interpretability for graph convolution. The proposed GWNN significantly outperforms previous spectral graph CNNs in the task of graph-based semi-supervised classification on three benchmark datasets: Cora, Citeseer and Pubmed. Copyright © 2019, The Authors. All rights reserved.

关键词： Wavelet transforms

Parameter estimation with the ordered 2 regularization via an alternating direction method of multipliers

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Humayoo, Mahammad Cheng, Xueqi CAS Key Laboratory of Network Data Science & Technology Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

Regularization is a popular technique in machine learning for model estimation and for avoiding overfitting. Prior studies have found that modern ordered regularization can be more effective in handling highly correlated, high-dimensional data than traditional regularization. The reason stems from the fact that the ordered regularization can reject irrelevant variables and yield an accurate estimation of the parameters. How to scale up the ordered regularization problems when facing large-scale training data remains an unanswered question. This paper explores the problem of parameter estimation with the ordered 2-regularization via Alternating Direction Method of Multipliers (ADMM), called ADMM-O2. The advantages of ADMM-O2 include (i) scaling up the ordered 2 to a large-scale dataset, (ii) predicting parameters correctly by excluding irrelevant variables automatically, and (iii) having a fast convergence rate. Experimental results on both synthetic data and real data indicate that ADMM-O2 can perform better than or comparable to several state-of-the-art baselines. Copyright © 2019, The Authors. All rights reserved.

关键词： Parameter estimation

Meta mask correction for nuclei segmentation in histopathological image

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shi, Jiangbo Jia, Chang Gao, Zeyu Gong, Tieliang Wang, Chunbao Li, Chen National Engineering Lab for Big Data Analytics Xi'an Jiao Tong University Shaanxi Xi'an710049 China School of Computer Science and Technology Xi'an Jiao tong University Shaanxi Xi'an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech.R&D Xi'an Jiao tong University Shaanxi Xi'an710049 China Department of Pathology The First Affiliated Hospital of Xi'an Jiaotong University Shaanxi Xi'an710061 China

Nuclei segmentation is a fundamental task in digital pathology analysis and can be automated by deep learning-based methods. However, the development of such an automated method requires a large amount of data with precisely annotated masks which is hard to obtain. Training with weakly labeled data is a popular solution for reducing the workload of annotation. In this paper, we propose a novel meta-learning-based nuclei segmentation method which follows the label correction paradigm to leverage data with noisy masks. Specifically, we design a fully conventional meta-model that can correct noisy masks using a small amount of clean meta-data. Then the corrected masks can be used to supervise the training of the segmentation model. Meanwhile, a bi-level optimization method is adopted to alternately update the parameters of the main segmentation model and the meta-model in an end-to-end way. Extensive experimental results on two nuclear segmentation datasets show that our method achieves the state-of-the-art result. It even achieves comparable performance with the model training on supervised data in some noisy settings. © 2021, CC BY.

关键词： Deep learning

Coupled graph neural networks for predicting the popularity of online content

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Cao, Qi Shen, Huawei Gao, Jinhua Wei, Bingzheng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China WeChat Tencent Inc

Predicting the popularity of online content in social network is an important problem for the practice of information dissemination, advertising, and recommendation. Previous methods mainly leverage demographics, temporal and structural patterns of early adopters for popularity prediction. These methods ignore the interaction between early adopters and potential adopters or the interactions among potential adopters over social networks. Consequently, they fail to capture the cascading effect triggered by early adopters in social networks, and thus have limited predictive power. In this paper, we consider the problem of network-aware popularity prediction, leveraging both early adopters and social networks among users for popularity *** propose a novel method, namely Coupled-GNNs, which use two coupled graph neural networks to capture the cascading effect in information diffusion. One graph neural network models the interpersonal influence, gated by the adoption state of users. The other graph neural network models the adoption state of users via interpersonal influence from their neighbors. Through such an iterative aggregation of the neighborhood, the proposed method naturally captures the cascading effect of information diffusion in social networks. Experiments conducted on both synthetic data and real-world SinaWeibo data demonstrate that our method significantly outperforms the state-of-the-art methods for popularity prediction. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

A Hypothesis on the Function of High-Valent Fe in NiFe (Hydr)oxide in the Oxygen-Evolution Reaction

学校读者我要写书评

暂无评论

Angewandte Chemie 2024年第6期137卷

作者： Nader Akbari Jafar Hussain Shah Cejun Hu Subhajit Nandy Pavlo Aleshkevych Rile Ge Sumbal Farid Changchang Dong Liang Zhang Keun Hwa Chae Wei Xie Taifeng Liu Junhu Wang Mohammad Mahdi Najafpour Department of Chemistry Institute for Advanced Studies in Basic Sciences (IASBS) Zanjan 45137-66731 Iran CAS Key Laboratory of Science and Technology on Applied Catalysis Mössbauer Effect Data Center Dalian Institute of Chemical Physics Chinese Academy of Sciences Dalian 116023 China Key Lab of Advanced Energy Materials Chemistry (Ministry of Education) Renewable Energy Conversion and Storage Center College of Chemistry Nankai University Tianjin 300071 China Advanced Analysis Center Korea Institute of Science and Technology Seoul 02792 Republic of Korea Institute of Physics Polish Academy of Sciences Warsaw 02-668 Poland School of Environmental and Chemical Engineering Jiangsu University of Science and Technology Zhenjiang 212100 China National and Local Joint Engineering Research Center for Applied Technology of Hybrid Nanomaterials Henan University Kaifeng 475004 China Department of Chemistry Sharif University of Technology Tehran 11155-9516 Iran

This study investigated the dynamic changes in NiFe (hydr)oxide and identified the role of high-valent Fe in the oxygen-evolution reaction (OER) within alkaline media via in situ techniques. Several high-valent Fe ions were found to remain considerably stable in the absence of potential in NiFe (hydr)oxide, even 96 hours after the OER. For Ni 2+ hydroxide treated with 57 Fe ions, where Fe sites are introduced onto the surface of Ni 2+ hydroxide, no Fe 4+ species were detected at the rate-determining step (RDS). The findings of this study suggested that the oxidation of bulk Fe ions, similar to Ni ions, to high valent forms, is charge accumulation without a direct role in OER; these results offered a novel perspective on manipulating Fe states to optimize OER efficacy. The prevailing hypothesis suggested that trace amounts of high-valent Fe ions, notably those on the surface, directly participate in OER.

关键词： NiFe (hydr)oxide oxygen evolution reaction high-valent Fe4+ in situ techniques electrocatalysts alkaline conditions mechanism active sites

ZSTAD: Zero-shot temporal activity detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Lingling Chang, Xiaojun Liu, Jun Luo, Minnan Wang, Sen Ge, Zongyuan Hauptmann, Alexander School of Computer Science and Technology Xian Jiaotong University Xian China Ministry of Education Key Lab For Intelligent Networks and Network Security Xian China Faculty of Information Technology Monash University Australia National Engineering Lab for Big Data Analytics Xian Jiaotong University Xian China School of Information Technology and Electrical Engineering University of Queensland Australia School of Computer Science Carnegie Mellon University United States

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

SenseMag: Enabling low-cost traffic monitoring using non-invasive magnetic sensing

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Kafeng Xiong, Haoyi Zhang, Jie Chen, Hongyang Dou, Dejing Xu, Cheng-Zhong Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Guangdong Shenzhen China Big Data Lab Baidu Inc. Haidian Beijing China Key Laboratory of High Confidence Software Technologies Peking University Haidian Beijing China Research Center for Intelligent Network Zhejiang Lab Zhejiang Hangzhou China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau Tapia Macau China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

The operation and management of intelligent transportation systems (ITS), such as traffic monitoring, relies on real-time data aggregation of vehicular traffic information, including vehicular types (e.g., cars, trucks, and buses), in the critical roads and highways. While traditional approaches based on vehicular-embedded GPS sensors or camera networks would either invade drivers’ privacy or require high deployment cost, this paper introduces a low-cost method, namely SenseMag, to recognize the vehicular type using a pair of non-invasive magnetic sensors deployed on the straight road section. SenseMag filters out noises and segments received magnetic signals by the exact time points that the vehicle arrives or departs from every sensor node. Further, SenseMag adopts a hierarchical recognition model to first estimate the speed/velocity, then identify the length of vehicle using the predicted speed, sampling cycles, and the distance between the sensor nodes. With the vehicle length identified and the temporal/spectral features extracted from the magnetic signals, SenseMag classify the types of vehicles accordingly. Some semi-automated learning techniques have been adopted for the design of filters, features, and the choice of hyper-parameters. Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i.e., 7 types by SenseMag versus 4 types by the existing work in comparisons). To be specific, our field experiment results validate that SenseMag is with at least 90% vehicle type classification accuracy and less than 5% vehicle length classification error. Copyright © 2021, The Authors. All rights reserved.

关键词： Sensor nodes