检索结果-内蒙古大学图书馆

Semantics-Guided Contrastive network for Zero-Shot Object Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yan, Caixia Chang, Xiaojun Luo, Minnan Liu, Huan Zhang, Xiaoqin Zheng, Qinghua The Ministry of Education Key Lab of Intelligent Networks and Network Security National Engineering Lab for Big Data Analytics School of Electronic and Information Engineering Xi'an Jiaotong University Shaanxi710049 China The ReLER Lab AAAI Faculty of Engineering and Information Technology University of Technology Sydney Australia The College of Computer Science and Artificial Intelligence Wenzhou University China

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories;2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks. © 2021, CC BY.

关键词： Object detection

Long-distance entanglement purification for quantum communication

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Xiao-Min Huang, Cen-Xiao Sheng, Yu-Bo Zhou, Lan Liu, Bi-Heng Guo, Yu Zhang, Chao Xing, Wen-Bo Huang, Yun-Feng Li, Chuan-Feng Guo, Guang-Can CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei230026 China Institute of Quantum Information and Technology Nanjing University of Posts and Telecommunications Nanjing210003 China College of Mathematics & Physics Nanjing University of Posts and Telecommunications Nanjing210003 China CAS Center For Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei230026 China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Nanjing210003 China

High quality long-distance entanglement is essential for both quantum communication and scalable quantum networks. Entanglement purification is to distill high-quality entanglement from low-quality entanglement in a noisy environment and it plays a key role in quantum repeaters. The previous significant entanglement purification experiments require two pairs of low-quality entangled states and were demonstrated in table-top. Here we propose and report a high-efficiency and long-distance entanglement purification using only one pair of hyperentangled state. We also demonstrate its practical application in entanglement-based quantum key distribution (QKD). One pair of polarization spatial-mode hyperentanglement was distributed over 11 km multicore fiber (noisy channel). After purification, the fidelity of polarization entanglement arises from 0.771 to 0.887 and the effective key rate in entanglement-based QKD increases from 0 to 0.332. The values of Clauser-Horne-Shimony-Holt (CHSH) inequality of polarization entanglement arises from 1.829 to 2.128. Moreover, by using one pair of hyperentanglement and deterministic controlled-NOT gate, the total purification efficiency can be estimated as 6.6 × 103 times than the experiment using two pairs of entangled states with spontaneous parametric down conversion (SPDC) sources. Our results offer the potential to be implemented as part of a full quantum repeater and large scale quantum network. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum communication

Optimal algorithm for profiling dynamic arrays with finite values 22

学校读者我要写书评

暂无评论

Optimal algorithm for profiling dynamic arrays with finite v...

22nd International Conference on Extending database technology, EDBT 2019

作者： Yang, Dingcheng Yu, Wenjian Deng, Junhui Liu, Shenghua BNRist Dept. Computer Science and Tech. Tsinghua Univ. Beijing China CAS Key Lab. Network Data Science and Tech. Inst. Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783893180813

How can one quickly answer the most and top popular objects at any time, given a large log stream in a system of billions of users? It is equivalent to find the mode and top-frequent elements in a dynamic array corresponding to the log stream. However, most existing work either restrain the dynamic array within a sliding window, or do not take advantages of only one element can be added or removed in a log stream. Therefore, we propose a profiling algorithm, named S-Profile, which is of O(1) time complexity for every updating of the dynamic array, and optimal in terms of computational complexity. With the profiling results, answering the queries on the statistics of dynamic array becomes trivial and fast. With the experiments of various settings of dynamic arrays, our accurate S-Profile algorithm outperforms the existing methods, showing at least 2X speedup to the heap based approach and 13X speedup to the balanced tree based approach. © 2019 Copyright held by the owner/author(s).

关键词： Trees (mathematics)

How medical crowdfunding helps people? A large-scale case study on waterdrop fundraising

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Huang, Junjie Shen, Huawei Cao, Qi Cai, Li 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 Beijing Zongqing Xiangqian Science and Technology Co Ltd Beijing China

While online medical crowdfunding achieved tremendous success, quantitative study about whether and how medical crowdfunding helps people remains little explored. In this paper, we empirically study how online medical crowdfunding helps people using more than 27, 000 fundraising cases in Waterdrop Fundraising, one of the most popular online medical crowdfunding platforms in China. We find that the amount of money obtained by fundraisers is broadly distributed, i.e., a majority of lowly donated cases coexist with a handful of very successful cases. We further investigate the factors that potentially correlate with the success of medical fundraising cases. Profile information of fundraising cases, e.g., geographic information of fundraisers, affects the donated amounts, since detailed description may increase the credibility of a fundraising case. One prominent finding lies in the effect of social network on the success of fundraising cases: the spread of fundraising information along social network is a key factor of fundraising success, and the social capital of fundraisers play an important role in fundraising. Finally, we conduct prediction of donations using machine learning models, verifying the effect of potential factors to the success of medical crowdfunding. Altogether, this work presents a data-driven view of medical fundraising on the web and opens a door to understanding medical crowdfunding. Copyright © 2020, The Authors. All rights reserved.

关键词： Crowdsourcing

Modelling universal order book dynamics in bitcoin market

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shi, Fabin Aden, Nathan Huang, Shengda Johnson, Neil Sun, Xiaoqian Gao, Jinhua Xu, Li Shen, Huawei Cheng, Xueqi Song, Chaoming 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 Beijing100049 China Department of Physics University of Miami Coral GablesFL33142 United States Physics Department George Washington University WashingtonD.C.20052 United States

Understanding the emergence of universal features such as the stylized facts in markets is a longstanding challenge that has drawn much attention from economists and physicists. Most existing models, such as stochastic volatility models, focus mainly on price changes, neglecting the complex trading dynamics. Recently, there are increasing studies on order books, thanks to the availability of large-scale trading datasets, aiming to understand the underlying mechanisms governing the market dynamics. In this paper, we collect order-book datasets of Bitcoin platforms across three countries over millions of users and billions of daily turnovers. We find a 1+1D field theory, govern by a set of KPZ-like stochastic equations, predicts precisely the order book dynamics observed in empirical data. Despite the microscopic difference of markets, we argue the proposed effective field theory captures the correct universality class of market dynamics. We also show that the model agrees with the existing stochastic volatility models at the long-wavelength limit. © 2021, CC BY.

关键词： Bitcoin

Integrated Sensing and Communication Signals Toward 5G-A and 6G: A Survey

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wei, Zhiqing Qu, Hanyang Wang, Yuan Yuan, Xin Wu, Huici Du, Ying Han, Kaifeng Zhang, Ning Feng, Zhiyong The Key Laboratory of Universal Wireless Communications Ministry of Education School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The National Engineering Lab for Mobile Network Technologies Beijing University of Posts and Telecommunications Beijing100876 China Peng Cheng Laboratory Shenzhen518066 China Data61 CSIRO Sydney Australia The Department of Electrical and Computer Engineering University of Windsor WindsorONN9B 3P4 Canada The University of Science and Technology of China China Academy of Information and Communications Technology Beijing100191 China China Academy of Information and Communications Technology Beijing100191 China

Integrated sensing and communication (ISAC) has the advantages of efficient spectrum utilization and low hardware cost. It is promising to be implemented in the fifth-generation-advanced (5G-A) and sixth-generation (6G) mobile communication systems, having the potential to be applied in intelligent applications requiring both communication and high-accurate sensing capabilities. As the fundamental technology of ISAC, ISAC signal directly impacts the performance of sensing and communication. This article systematically reviews the literature on ISAC signals from the perspective of mobile communication systems, including ISAC signal design, ISAC signal processing and ISAC signal optimization. We first review the ISAC signal design based on 5G, 5G-A and 6G mobile communication systems. Then, radar signal processing methods are reviewed for ISAC signals, mainly including the channel information matrix method, spectrum lines estimator method and super resolution method. In terms of signal optimization, we summarize peak-to-average power ratio (PAPR) optimization, interference management, and adaptive signal optimization for ISAC signals. This article may provide the guidelines for the research of ISAC signals in 5G-A and 6G mobile communication *** Codes 94-02 Copyright © 2023, The Authors. All rights reserved.

关键词： Orthogonal frequency division multiplexing

Match2: A Matching over Matching Model for Similar Question Identification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Zizhen Fan, Yixing Guo, Jiafeng Yang, Liu Zhang, Ruqing Lan, Yanyan Cheng, Xueqi Jiang, Hui Wang, Xiaozhao University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Massachusetts Amherst MA United States Alibaba Group Beijing China

Community Question Answering (CQA) has become a primary means for people to acquire knowledge, where people are free to ask questions or submit answers. To enhance the efficiency of the service, similar question identification becomes a core task in CQA which aims to find a similar question from the archived repository whenever a new question is asked. However, it has long been a challenge to properly measure the similarity between two questions due to the inherent variation of natural language, i.e., there could be different ways to ask a same question or different questions sharing similar expressions. To alleviate this problem, it is natural to involve the existing answers for the enrichment of the archived questions. Traditional methods typically take a one-side usage, which leverages the answer as some expanded representation of the corresponding question. Unfortunately, this may introduce unexpected noises into the similarity computation since answers are often long and diverse, leading to inferior performance. In this work, we propose a two-side usage, which leverages the answer as a bridge of the two questions. The key idea is based on our observation that similar questions could be addressed by similar parts of the answer while different questions may not. In other words, we can compare the matching patterns of the two questions over the same answer to measure their similarity. In this way, we propose a novel matching over matching model, namely Match2, which compares the matching patterns between two question-answer pairs for similar question identification. Empirical experiments on two benchmark datasets demonstrate that our model can significantly outperform previous state-of-the-art methods on the similar question identification *** CONCEPTS •Information systems → Question answering;Copyright © 2020, The Authors. All rights reserved.

关键词：

Provably Robust Node Classification via Low-Pass Message Passing

学校读者我要写书评

暂无评论

Provably Robust Node Classification via Low-Pass Message Pas...

IEEE International Conference on data Mining (ICDM)

作者： Yiwei Wang Shenghua Liu Minji Yoon Hemank Lamba Wei Wang Christos Faloutsos Bryan Hooi School of Computing National University of Singapore Singapore Institute of Computing Technology Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science & Technology CAS and University of Chinese Academy of Sciences Beijing China Carnegie Mellon University United States

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Graph Convolutional networks (GCNs) have achieved state-of-the-art performance on node classification. However, recent works have shown that GCNs are vulnerable to adversarial attacks, such as additions or deletions of adversarially-chosen edges in the graph, in order to mislead the node classification algorithms. How can we design robust GCNs that are resistant to such adversarial attacks? More challengingly, how can we do this in a way that is provably robust? We propose a robust node classification approach based on a low-pass `message passing' mechanism, that (a) reduces the effectiveness of adversarial attacks in experiments, and (b) provides theoretical guarantees against adversarial attacks. Our approach can be embedded into the existing GCN architectures to enhance their robustness. Empirical results show that our loss-pass method effectively improves the performance of multiple GCNs under miscellaneous perturbations and helps them to achieve superior performance on various graphs.

关键词： Resistance Perturbation methods Message passing Reliability engineering Robustness Task analysis Optimization

VFGCN: A Vertical Federated Learning Framework With Privacy Preserving for Graph Convolutional network

学校读者我要写书评

暂无评论

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Wang, Gang Li, Qingming Liu, Ximeng Yan, Xiaoran Dong, Qingkuan Wu, Huiwen Kong, Xiangjie Zhou, Li Zhejiang Lab HangZhou310000 China Zhejiang University College of Computer Science and Technology Hangzhou310058 China Fuzhou University Key Laboratory of Information Security of Network Systems College of Computer and Big Data Fuzhou350108 China Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China Zhejiang University of Technology College of Computer Science and Technology Hangzhou310023 China Dalian University of Technology School of Software Dalian116620 China

Due to the robust representational capabilities of graph data, employing graph neural networks for its processing has demonstrated superior performance over conventional deep learning algorithms. Graph data encompasses abundant features and structural information;however, its large-scale collection is often challenging in practice. This difficulty arises because data predominantly exists in isolated compartments, making it arduous to harmonize information across various organizations or to enable multiple organizations to collaborate effectively while safeguarding local data privacy. In light of an extreme data distribution scenario, where each client possesses distinct nodes with partially overlapping segments yet divergent data features, we introduce a dual-cloud server architecture. This framework encompasses the design of four secure subprotocols: ReEnc (secure re-encryption), SecPSI (secure outsourcing of PSI), SecWeight (secure weight calculation), and SecAgg (secure aggregation). Together, these components facilitate a vertical federated learning framework for graph convolutional networks, ensuring privacy preservation. We provide a security proof for the entire system and extensive evaluation on three benchmark datasets (Cora, Citeseer, and Pubmed) illustrates that our Vertical Federated Graph Convolutional network (VFGCN) surpasses existing privacy-preserving methodologies. © 2004-2012 IEEE.

关键词： Privacy by design