检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information processing Systems

作者： Zitai Wang Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang SKLOIS Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University and SKLOIS Institute of Information Engineering CAS School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Traditional machine learning follows a close-set assumption that the training and test set share the same label space. While in many practical scenarios, it is inevitable that some test samples belong to unknown classes (open-set). To fix this issue, Open-Set Recognition (OSR), whose goal is to make correct predictions on both close-set samples and open-set samples, has attracted rising attention. In this direction, the vast majority of literature focuses on the pattern of open-set samples. However, how to evaluate model performance in this challenging task is still unsolved. In this paper, a systematic analysis reveals that most existing metrics are essentially inconsistent with the aforementioned goal of OSR: (1) For metrics extended from close-set classification, such as Open-set F-score, Youden's index, and Normalized Accuracy, a poor open-set prediction can escape from a low performance score with a superior close-set prediction. (2) Novelty detection AUC, which measures the ranking performance between close-set and open-set samples, ignores the close-set performance. To fix these issues, we propose a novel metric named OpenAUC. Compared with existing metrics, OpenAUC enjoys a concise pairwise formulation that evaluates open-set performance and close-set performance in a coupling manner. Further analysis shows that OpenAUC is free from the aforementioned inconsistency properties. Finally, an end-to-end learning method is proposed to minimize the OpenAUC risk, and the experimental results on popular benchmark datasets speak to its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

People re-detection using Adaboost with sift and color correlogram

People re-detection using Adaboost with sift and color corre...

引用

IEEE International Conference on Image processing

作者： Lei Hu Shuqiang Jiang Qingming Huang Wen Gao Chinese Academy of Sciences Beijing China Key Lab of Intelligent Information Processing Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN Institute of Computing Technology Chinese Academy and Sciences Beijing China Institute of Digital Media Peking University Beijing China

People re-detection aims at performing re-identification of people who leave the scene and reappear after some time. This is an important problem especially in video surveillance scenarios. In this paper, we present a method of people re-detection within the context of visual sequence in single-camera setup. We consider re-detection as a binary classification problem, where both global and local descriptors are employed for training strong classifier on-line with adaboost to distinguish a newly detected people as tracked or new occurrence. The strong classifier will be updated while match is ascertained. A predetermined classifier with well-chosen threshold is employed as assistant of training examples collection. We test the performance of our approach on 4 different scenes including 51 video sequences taken from the CAVIAR database and 4 video sequences shot by ourselves. The results show that our re-detection algorithm can robustly handle variations in illumination, pose, scale, and camera-view.

关键词： Cameras Layout Surveillance Color Video sequences Data mining Joining processes Histograms Information processing Computers

来源：评论

学校读者我要写书评

暂无评论

OTKGE: multi-modal knowledge graph embeddings via optimal transport 22

OTKGE: multi-modal knowledge graph embeddings via optimal tr...

引用

Proceedings of the 36th International Conference on Neural Information processing Systems

作者： Zongsheng Cao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang SKLOIS Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University and SKLOIS Institute of Information Engineering CAS School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Multi-modal knowledge graph embeddings (KGE) have caught more and more attention in learning representations of entities and relations for link prediction tasks. Different from previous uni-modal KGE approaches, multi-modal KGE can leverage expressive knowledge from a wealth of modalities (image, text, etc.), leading to more comprehensive representations of real-world entities. However, the critical challenge along this course lies in that the multi-modal embedding spaces are usually heterogeneous. In this sense, direct fusion will destroy the inherent spatial structure of different modal embeddings. To overcome this challenge, we revisit multi-modal KGE from a distributional alignment perspective and propose optimal transport knowledge graph embeddings (OTKGE). Specifically, we model the multi-modal fusion procedure as a transport plan moving different modal embeddings to a unified space by minimizing the Wasserstein distance between multi-modal distributions. Theoretically, we show that by minimizing the Wasserstein distance between the individual modalities and the unified embedding space, the final results are guaranteed to maintain consistency and comprehensiveness. Moreover, experimental results on well-established multi-modal knowledge graph completion benchmarks show that our OTKGE achieves state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-layer Joint Relay Selection and Power Allocation Scheme for Cooperative Relaying System

引用

IOP Conference Series: Materials Science and Engineering 2018年第7期322卷

作者： Hui Zhi Mengmeng He Feiyue Wang Ziju Huang Key Lab of Computing Intelligent and Signal Processing (Ministry of Education) Anhui University Hefei China College of Electronics and Information Engineering Anhui University Hefei China

A novel cross-layer joint relay selection and power allocation (CL-JRSPA) scheme over physical layer and data-link layer is proposed for cooperative relaying system in this paper. Our goal is finding the optimal relay selection and power allocation scheme to maximize system achievable rate when satisfying total transmit power constraint in physical layer and statistical delay quality-of-service (QoS) demand in data-link layer. Using the concept of effective capacity (EC), our goal can be formulated into an optimal joint relay selection and power allocation (JRSPA) problem to maximize the EC when satisfying total transmit power limitation. We first solving optimal power allocation (PA) problem with Lagrange multiplier approach, and then solving optimal relay selection (RS) problem. Simulation results demonstrate that CL-JRSPA scheme gets larger EC than other schemes when satisfying delay QoS demand. In addition, the proposed CL-JRSPA scheme achieves the maximal EC when relay located approximately halfway between source and destination, and EC becomes smaller when the QoS exponent becomes larger.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Denoiser-Guided Image Deconvolution with Arbitrary Boundaries and Incomplete Observations

SSRN

引用

SSRN 2023年

作者： He, Liangtian Gao, Shaobing Deng, Liang-Jian Wang, Yilun Wang, Chao Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei230601 China College of Computer Science Sichuan University Chengdu610065 China Chengdu611731 China American Family Insurance ChicagoIL60654 United States College of Mathematics Physics and Information Zhejiang Ocean University Zhoushan316022 China

Non-blind image deconvolution (NBID) has been a significant and long-standing research topic in the field of imaging sciences. While enduring efforts have been made over the past decades, they are extensively focusing on the scenario where the blur process is artificially assumed, e.g., typically under periodic boundary condition, as the involved matrix inversion can be efficiently tackled using the fast Fourier transforms (FFTs). However, despite its popularity, these boundary conditions are not always realistic assumptions and can lead to severe artifacts in the recovered image. Therefore, image deconvolution with arbitrary boundaries remains as a fundamental problem to be investigated. In this paper, we propose a principled framework with the aid of Plug-and-Play (PnP) scheme to address NBID in a more realistic scenario of unknown boundary. Specifically, the local and nonlocal denoiser priors with implicit optimization objectives are incorporated into a unified model, and the degradation operator is formulated as a composition of a convolution and a spatial mask. Two kinds of experiments: deconvolution, deconvolution with inpainting, all with unknown boundaries are tested. Both quantitative and qualitative evaluations demonstrate that the proposed denoiser-guided PnP framework is highly flexible and effective to cope with the general image deconvolution tasks. © 2023, The Authors. All rights reserved.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Glycan immunogenicity prediction based on Graph neural network

Glycan immunogenicity prediction based on Graph neural netwo...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Wang, Yu Wang, Hui Hou, Meijie Wang, Yaojun Bu, Dongbo Zhang, Chunming Huang, Chuncui Sun, Shiwei Institute of Computing Technology Chinese Academy of Sciences Key Lab of Intelligent Information Processing 6 Kexueyuan South Road Beijing100190 China Zhongke Big Data Academy Henan Zhengzhou450046 China University of Chinese Academy of Sciences 19 Yuquan Road Beijing100049 China Institute of Biophysics Chinese Academy of Sciences 15 Datun Road Beijing100101 China College of Information and Electrical Engineering China Agricultural University 17 Qinghua Donglu Beijing100083 China Phil Rivers Technology Beijing China

ISBN: (纸本)9781665401265

Glycans play important roles in a great variety of biological processes, and these roles are closely determined by the details of their structures. It becomes possible to acquire hidden features from glycan structures using deep learning method with the great progress in recent years. Unlike the linear chain of proteins and DNAs, branching is a unique feature of glycan structures, which makes it very difficult to directly apply deep learning models on glycans. Thus, how to comprehensively and efficiently describe glycans and use them as input to deep learning models still remains challenging. Here, a graph neural network (GNN) called GlyNet was used to obtain high-dimensional representation of glycans and predict their immunogenicity. Our method was applied in SugarBase, and it works more superiorly than the state-of-art method with accuracy increased from 91.7% to 95.6%. © 2021 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

intelligent ultrasonic distance measurer system with temperature compensation algorithm

Intelligent ultrasonic distance measurer system with tempera...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Yuwen Wu Qiang Yang Kai Tang Jianhang Zou Jianming Zhuo Naixing Feng Yijun Cai Smart Sensing Integrated Circuit Engineering Research Center of Universities in Fujian Province Xiamen University of Technology Xiamen China Xiamen Wish Information Technology Co. Ltd Xiamen China Xiamen Blue Ocean Technology Co. Ltd Xiamen China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

With regard to distance measurement in daily life, the traditional way is to measure the distance between objects through rulers. Nowadays, ultrasonic ranging, laser ranging, radar ranging, sonar ranging and other technologies have enriched the way of distance measurement. At the same time, it is possible to choose a suitable solution according to different actual environments. This paper design an intelligent ultrasonic ranging system through the research of ultrasonic characteristics and the application of existing ultrasonic ranging. The paper introduces the design ideas and process of the intelligent ultrasonic ranging system. Through the design of independent buttons, the normal mode ranging and the high-precision mode ranging are generated to achieve the division of the measurement range and accuracy. When the distance between the measured object and the intelligent ultrasonic ranging system is less than the preset value or exceeds the range of this mode, the buzzer will sound an alarm, so that the system can be used in more fields. The system detects the current ambient temperature in real time, so that the distance measurement can be compensated and modified by the temperature compensation algorithm in the system to achieve self-adaptation and reduce measurement errors.

关键词： Temperature measurement Performance evaluation Temperature distribution Laser radar Ultrasonic variables measurement Current measurement Measurement uncertainty

来源：评论

学校读者我要写书评

暂无评论

Multi-Granularity Prosodic Speech Synthesis with Grammar Information

SSRN

引用

SSRN 2024年

作者： Zhou, Jian Liu, Jiahui Fan, Cunhang Zheng, Wenming Lv, Zhao Tao, Liang Kwan, Hon Keung The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China Ministry of Education School of Biological Science and Medical Engineering Southeast University Nanjing210096 China The Department of Electrical and Computer Engineering University of Windsor WindsorN9B 3P4 Canada

Personalized speech synthesis involves learning an individual's unique speaking patterns from a reference audio to generate speech that mimics the speaker's habitual rhythm. However, the one-to-many mapping between text and speech, combined with the dynamic nature of personalized speech style characteristics in the reference audio, poses significant challenges for accurate personalized speech synthesis. In this paper, we propose a Grammar Infused Multi-granularity Prosody Network (GMG ProsodyNet) for personalized speech synthesis. Specifically, 1) We model prosodic features hierarchically at the levels of utterance, content syntax, word, and phoneme. We utilize the utterance-level prosodic feature to guide the prediction of fine-grained prosodic features according to the hierarchical property of prosodic features. We introduce a context syntax encoder to improve the prediction accuracy of duration, pitch, and energy characteristics in the synthesized audio. The proposed word-level prosodic encoder can efficiently extract valuable pitch dynamic and speech continuity features from the word spectrum. For controlling subtle prosodic nuances, we employ phoneme-level prosodic modeling. 2) We extract syntax level prosodic features from the syntax graph constructed by Graph Neural Network (GNN) with word as node, exploiting grammatical dependencies between distant words. Experimental results demonstrate that the proposed GMG ProsodyNet can effectively encode delicate and personalized prosodic features, leading to improved speech synthesis quality, fluency, and naturalness. © 2024, The Authors. All rights reserved.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Full reconstruction of simplicial complexes from binary time-series data

Research Square

引用

Research Square 2021年

作者： Wang, Huan Ma, Chuang Chen, Han-Shuang Lai, Ying-Cheng Zhang, Hai-Feng The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Science Anhui University Hefei230601 China School of Internet Anhui University Hefei230601 China School of Physics and Material Science Anhui University Hefei230601 China School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States

Previous efforts on data-based reconstruction focused on complex networks with pairwise or two-body interactions. There is a growing interest in networks with high-order or many-body interactions, raising the need to reconstruct such networks based on observational data. We develop a general framework combining statistical inference and expectation maximization to fully reconstruct 2-simplicial complexes with two- and three-body interactions based on binary time-series data from social contagion dynamics. We further articulate a two-step scheme to improve the reconstruction accuracy while significantly reducing the computational load. Through synthetic and real-world 2-simplicial complexes, we validate the framework by showing that all the connections can be faithfully identified and the full topology of the 2-simplicial complexes can be inferred. The effects of noisy data or stochastic disturbance are studied, demonstrating the robustness of the proposed framework. © 2021, CC BY.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Ekblom Promoting Adaptive Algorithm for System Identification

TechRxiv

引用

TechRxiv 2022年

作者： Huang, Xinqi Li, Yingsong Han, Xiao Tu, Huawei College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei China College of Computer Science and Technology Harbin Engineering University Harbin150001 China Department of Computer Science and Information Technology La Trobe University MelbourneVIC3086 Australia

We propose an Ekblom promoting adaptive algorithm (EPAA) which uses Ekblom norm to construct a data reusing scheme to achieve better performance under impulsive noise (IN) environments. By exerting Ekblom-norm constraint on the a posterior error vector, a sliding window cost function is created to realize the EPAA that is derived to reduce IN effects. The derivation and theoretical convergence analysis of the EPAA are presented in detail. The simulation examples are setup to illustrate the superior performance of the EPAA compared to popular data reusing algorithms for system identification under IN environments. © 2022, CC BY.

关键词： Adaptive filtering

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：