检索结果-内蒙古大学图书馆

SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fan, Zhaoxin Song, Zhenbo Liu, Hongyan Lu, Zhiwu He, Jun Du, Xiaoyong Key Laboratory of Data Engineering Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Management Science and Engineering Tsinghua University Beijing100084 China

Simultaneous Localization and Mapping (SLAM) and Autonomous Driving are becoming increasingly more important in recent years. Point cloud-based large scale place recognition is the spine of them. While many models have been proposed and have achieved acceptable performance by learning short-range local features, they always skip long-range contextual properties. Moreover, the model size also becomes a serious shackle for their wide applications. To overcome these challenges, we propose a super light-weight network model termed SVT-Net. On top of the highly efficient 3D Sparse Convolution (SP-Conv), an Atom-based Sparse Voxel Transformer (ASVT) and a Cluster-based Sparse Voxel Transformer (CSVT) are proposed respectively to learn both short-range local features and long-range contextual features. Consisting of ASVT and CSVT, SVT-Net can achieve state-of-the-art performance in terms of both recognition accuracy and running speed with a super-light model size (0.9M parameters). Meanwhile, for the purpose of further boosting efficiency, we introduce two simplified versions, which also achieve state-of-the-art performance and further reduce the model size to 0.8M and 0.4M respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

A High-Speed Stable Polarization Encoder for Quantum key Distribution

学校读者我要写书评

暂无评论

A High-Speed Stable Polarization Encoder for Quantum Key Dis...

Pacific Rim Conference on Lasers and Electro-Optics (CLEO/Pacific Rim)

作者： Ju Li Zexu Wang Changlei Wang Feifei Yin Kun Xu Huaxing Xu Yitang Dai State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing China National Engineering Research Center for Public Safety Risk Perception and Control by Big Data China Academy of Electronics and Information Technology Beijing China CETC Academy of Electronics and Information Technology Group Co. Ltd. Beijing China

We report a high-speed polarization encoder which can be applied for quantum key distribution, resulting in an average bit error rate (BER) below 0.1% at a repetition frequency of 10 GHz under interference-free measur... 详细信息

ISBN: (数字)9798350372076

ISBN: (纸本)9798350372083

关键词： Frequency modulation Satellites Protocols Bit error rate Measurement uncertainty Sagnac interferometers Lasers and electrooptics

USED: Universal Speaker Extraction and Diarization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ao, Junyi Yıldırım, Mehmet Sinan Tao, Ruijie Ge, Meng Wang, Shuai Qian, Yanmin Li, Haizhou Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore119077 Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore117549 Singapore Shenzhen Research Institute of Big Data Shenzhen518172 China Auditory Cognition and Computational Acoustics Lab Department of Computer Science and Engineering China MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker’s voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating ‘who spoke when’. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about ‘who spoke what and when’, which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain, whereas diarization is in the temporal domain. It is logical to believe that speaker activities obtained from speaker diarization can benefit speaker extraction, while the extracted speech offers more accurate speaker activity detection than the speech mixture. In this paper, we propose a unified model called Universal Speaker Extraction and Diarization (USED) to address output inconsistency and scenario mismatch issues. It is designed to manage speech mixtures with varying overlap ratios and variable number of speakers. We show that the USED model significantly outperforms the competitive baselines for speaker extraction and diarization tasks on LibriMix and SparseLibriMix datasets. We further validate the diarization performance on CALLHOME, a dataset based on real recordings, and experimental results indicate that our model surpasses recently proposed approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Frequency domain analysis

Identify-Based Outsourcing data Auditing Scheme with Lattice 3rd

学校读者我要写书评

暂无评论

Identify-Based Outsourcing Data Auditing Scheme with Lattice

3rd International Conference on Frontiers in Cyber Security, FCS 2020

作者： Wang, Han Wang, Xu An Liu, Jiasen Lin, Chuan Guizhou Provincial Key Laboratory of Public Big Data GuiZhou University GuiyangGuizhou550025 China Key Laboratory of Network and Information Security under PAP Engineering University of PAP Xi’an710086 China

ISBN: (纸本)9789811597381

To reduce the burden and overhead of local storage, more and more organizations and individuals chosen to outsourcing data to cloud servers. Cloud users can access cloud data through any network. At the same time, as users lose actual control over the data, the data security in the cloud server is exposed to great risks. Therefore, how to ensure the integrity and security of cloud data has become an open issue. Around this problem, researchers have put forward many plans. However, these schemes are based on traditional cryptography, they cannot resist quantum attacks and have high computational complexity. It cannot meet the needs of interconnection of everything in the future. To solve this problem, we propose an identity-based outsourcing data integrity auditing scheme with lattice, which has forward security. Our proposed scheme is based on lattice cryptosystem, which not only has higher security and computational efficiency, but also has forward security. In the proposed scheme, the data owner can designate a proxy to outsource the data, thus reducing the local computing burden. In addition, we analyze the security of the scheme through the assumption of ISIS problem, which shows the theoretical security of the scheme. Theoretical analysis and comparison indicate that our proposed scheme is more secure and practical. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Cloud storage

Four Diagnostic Description Extraction in Clinical Records of Traditional Chinese Medicine with Batch data Oversampling 21

学校读者我要写书评

暂无评论

Four Diagnostic Description Extraction in Clinical Records o...

21st Chinese National Conference on Computational Linguistic, CCL 2022

作者： Wang, Yaqiang Li, Kailun Jiang, Yongguang Shu, Hongping College of Software Engineering Chengdu University of Information Technology China Institute for Data Science and Engineering Chengdu University of Information Technology China Sichuan Key Laboratory of Software Automatic Generation and Intelligent Service China Department of Preclinical Medicine Chengdu University of Traditional Chinese Medicine China

Four diagnostic description extraction in clinical records of traditional Chinese medicine (TCM) has important application value in improving the quality and efficiency of TCM clinical syndrome differentiation and treatment. However, the extraction task is yet to be explored, and imbalanced class distribution is one of the key challenges of this task. As a first exploration of this task, we firstly constructed a TCM clinical four diagnostic description extraction corpus and then solved the domain adaptation by fine-tuning the general domain pre-trained language model based on unlabeled TCM clinical records. At last, we trained our proposed four diagnostic description extraction model by utilizing a small labeled dataset through a well-designed batch data oversampling algorithm. The experimental results show that the performance of the proposed method in this paper is better than that of the compared methods, and the proposed method improves the extraction performance F1 score of the rare class by 2.13% on average. © 2022 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License.

关键词： Extraction

Attention Field Size Alters Patterns of Population Receptive Fields in the Early Visual Cortex

学校读者我要写书评

暂无评论

Neuroscience Bulletin 2022年第2期38卷 205-208页

作者： Bo Liu Xiaochun Wang Le Wang Qiaojun Qu Wei Zhang Bin Wang Jie Xiang Ting Yan Tianyi Yan Hui Zhang College of Medical Imaging Shanxi Medical UniversityTaiyuan 030001China Department of Radiology First Clinical Medical CollegeShanxi Medical UniversityTaiyuan 030001China College of Information and Computer Taiyuan University of TechnologyTaiyuan 030001China Intelligent Imaging Big Data and Functional Nano-imaging Engineering Research Center of Shanxi Province Shanxi Medical UniversityTaiyuan 030001China Translational Medicine Research Center Shanxi Medical UniversityTaiyuan 030001China School of Life Science Beijing Institute of TechnologyBeijing 100081China Ministry of Industry and Information Technology Key Laboratory of Convergence Medical Engineering System and Healthcare TechnologyBeijing Institute of TechnologyBeijing 100081China

Dear Editor,Visual spatial attention is a cognitive process by which prior information about the relevance of spatial locations is used to improve perceptual performance[1].Visual attention is spread across the attention field(AF),a range within visual *** AF reshapes the distribution of activity throughout the visual pathway,including the early visual cortex(EVC)and all areas along the dorsal and ventral visual cortical pathways[2,3].Importantly,the effect of attention depends not only on the spatial position of the AF but also on its size[4].

关键词： Visual Cortex visual

A SCATC-Based Blockchain Index Structure 14th

学校读者我要写书评

暂无评论

A SCATC-Based Blockchain Index Structure

14th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2021

作者： Xing, Xiaogang Chen, Yuling Li, Tao Xin, Yang Sun, Hongwei State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing100876 China National Engineering Laboratory for Disaster Backup Recovery Beijing100876 China Blockchain Laboratory of Agricultural Vegetables Weifang University of Science and Technology WeiFang262700 China

ISBN: (纸本)9783030898137

Blockchain technology has the characteristics of decentralization and tamper resistance, which can store data safely and reduce the cost of trust effectively. However, the existing blockchain system has weak performance in data management, and only supports traversal queries with transaction hashes as keywords. The query method based on the account transaction trace chain (ATTC) improves the query efficiency of historical transactions of the account. However, the efficiency of querying accounts with longer transaction chains has not been effectively improved. Given the inefficiency and single method of the ATTC index in the query, we propose a subchain-based account transaction chain (SCATC) index structure. First, the account transaction chain is divided into subchains, and the last block of each subchain is connected by a hash pointer. The block-by-block query mode in ATTC is converted to the subchain-by-subchain query mode, which shortens the query path;then, the query algorithm is given for the SCATC index structure. Simulation analysis shows that the SCATC index structure significantly improves query efficiency. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Blockchain

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China Peng Cheng Laboratory China

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a diversity control regularization term to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML. © 2022, CC BY-NC-SA.

关键词： Embeddings

PicT: A SlimWeakly Supervised Vision Transformer for Pavement Distress Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tang, Wenhao Huang, Sheng Zhang, Xiaoxian Huangfu, Luwen School of Big Data & Software Engineering Chongqing University Chongqing China School of Big Data & Software Engineering Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Chongqing China Fowler College of Business Center for Human Dynamics in the Mobile Age San Diego State University San DiegoCA United States

Automatic pavement distress classification facilitates improving the efficiency of pavement maintenance and reducing the cost of labor and resources. A recently influential branch of this task divides the pavement image into patches and infers the patch labels for addressing these issues from the perspective of multi-instance learning. However, these methods neglect the correlation between patches and suffer from a low efficiency in the model optimization and inference. As a representative approach of vision Transformer, Swin Transformer is able to address both of these issues. It first provides a succinct and efficient framework for encoding the divided patches as visual tokens, then employs self-attention to model their relations. Built upon Swin Transformer, we present a novel vision Transformer named Pavement Image Classification Transformer (PicT) for pavement distress classification. In order to better exploit the discriminative information of pavement images at the patch level, the Patch Labeling Teacher is proposed to leverage a teacher model to dynamically generate pseudo labels of patches from image labels during each iteration, and guides the model to learn the discriminative features of patches via patch label inference in a weakly supervised manner. The broad classification head of Swin Transformer may dilute the discriminative features of distressed patches in the feature aggregation step due to the small distressed area ratio of the pavement image. To overcome this drawback, we present a Patch Refiner to cluster patches into different groups and only select the highest distress-risk group to yield a slim head for the final image classification. We evaluate our method on a large-scale bituminous pavement distress dataset named CQU-BPDD. Extensive results demonstrate the superiority of our method over baselines and also show that PicT outperforms the second-best performed model by a large margin of +2.4% in P@R on detection task, +3.9% in F 1 on recogni

关键词： Image classification