检索结果-内蒙古大学图书馆

Erratum to "Multi-View Face Synthesis via Progressive Face Flow"

学校读者我要写书评

暂无评论

IEEE transactions on image processing : a publication of the IEEE Signal processing Society 2021年 30卷 6700页

作者： Yangyang Xu Xuemiao Xu Jianbo Jiao Keke Li Cheng Xu Shengfeng He School of Computer Science and Engineering South China University of Technology Guangzhou China State Key Laboratory of Subtropical Building Science the Key Laboratory of Big Data and Intelligent Robot Ministry of Education and the Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information South China University of Technology Guangzhou China University of Oxford Oxford U.K.

In the above article [1], unfortunately, Fig. 5 was not displayed correctly with many empty images. The correct version is supplemented here.

关键词： Faces

Global semantic consistency for zero-shot learning

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wu, Fan Tian, Kai Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Department of Computer Science and Technology Tongji University Shanghai201804 China

In image recognition, there are many cases where training samples cannot cover all target classes. Zero-shot learning (ZSL) utilizes the class semantic information to classify samples of the unseen categories that have no corresponding samples contained in the training set. In this paper, we propose an end-to-end framework, called Global Semantic Consistency Network (GSC-Net for short), which makes complete use of the semantic information of both seen and unseen classes, to support effective zero-shot learning. We also adopt a soft label embedding loss to further exploit the semantic relationships among classes. To adapt GSC-Net to a more practical setting - Generalized Zero-shot Learning (GZSL), we introduce a parametric novelty detection mechanism. Our approach achieves the state-of-the-art performance on both ZSL and GZSL tasks over three visual attribute datasets, which validates the effectiveness and advantage of the proposed framework. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

DPHL:A DIA Pan-human Protein Mass Spectrometry Library for Robust Biomarker Discovery

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2020年第2期18卷 104-119页

作者： Tiansheng Zhu Yi Zhu Yue Xuan Huanhuan Gao Xue Cai Sander R.Piersma Thang V.Pham Tim Schelfhorst Richard R.G.D.Haas Irene V.Bijnsdorp Rui Sun Liang Yue Guan Ruan Qiushi Zhang Mo Hu Yue Zhou Winan J.Van Houdt Tessa Y.S.Le Large Jacqueline Cloos Anna Wojtuszkiewicz Danijela Koppers-Lalic Franziska Bottger Chantal Scheepbouwer Ruud H.Brakenhoff Geert J.L.H.van Leenders Jan N.M.Ijzermans John W.M.Martens Renske D.M.Steenbergen Nicole C.Grieken Sathiyamoorthy Selvarajan Sangeeta Mantoo Sze S.Lee Serene J.Y.Yeow Syed M.F.Alkaff Nan Xiang Yaoting Sun Xiao Yi Shaozheng Dai Wei Liu Tian Lu Zhicheng Wu Xiao Liang Man Wang Yingkuan Shao Xi Zheng Kailun Xu Qin Yang Yifan Meng Cong Lu Jiang Zhu Jin'e Zheng Bo Wang Sai Lou Yibei Dai Chao Xu Chenhuan Yu Huazhong Ying Tony K.Lim Jianmin Wu Xiaofei Gao Zhongzhi Luan Xiaodong Teng Peng Wu Shi'ang Huang Zhihua Tao Narayanan G.Iyer Shuigeng Zhou Wenguang Shao Henry Lam Ding Ma Jiafu Ji Oi L.Kon Shu Zheng Ruedi Aebersold Connie R.Jimenez Tiannan Guo Zhejiang Provincial Laboratory of Life Sciences and Biomedicine Westlake UniversityHangzhou 310024China Key Laboratory of Structural Biology of Zhejiang Province School of Life SciencesWestlake UniversityHangzhou 310024China Institute of Basic Medical Sciences Westlake Institute for Advanced StudyHangzhou 310024China School of Computer Science Shanghai Key Laboratory of Intelligent Information ProcessingFudan UniversityShanghai 200433China Thermo Fisher Scientific(BREMEN)GmbH Bremen 28195Germany OncoProteomics Laboratory Department of Medical OncologyVU University Medical CenterVU UniversityAmsterdam 1011The Netherlands Amsterdam UMC Vrije Universiteit AmsterdamUrologyCancer Center AmsterdamAmsterdam 1011The Netherlands Thermo Fisher Scientific Shanghai 201206China The Netherlands Cancer Institute Surgical OncologyAmsterdam 1011The Netherlands Amsterdam UMC Vrije Universiteit AmsterdamSurgeryCancer Center AmsterdamAmsterdam 1011The Netherlands Amsterdam UMC Vrije Universiteit AmsterdamPediatric Oncology/HematologyCancer Center AmsterdamAmsterdam 1011The Netherlands Amsterdam UMC Vrije Universiteit AmsterdamHematologyCancer Center AmsterdamAmsterdam 1011The Netherlands Amsterdam UMC Vrije Universiteit AmsterdamMedical OncologyCancer Center AmsterdamAmsterdam 1011The Netherlands Amsterdam UMC Vrije Universiteit AmsterdamNeurosurgeryCancer Center AmsterdamAmsterdam 1011The Netherlands Amsterdam UMC Vrije Universiteit AmsterdamPathologyCancer Center AmsterdamAmsterdam 1011The Netherlands Amsterdam UMC Vrije Universiteit AmsterdamOtolaryngology/Head and Neck SurgeryCancer Center AmsterdamAmsterdam 1011The Netherlands Erasmus MC University Medical Center PathologyRotterdam 1016LVThe Netherlands Erasmus MC University Medical Center SurgeryRotterdam 1016LVThe Netherlands Erasmus MC University Medical Center Medical OncologyRotterdam 1016LVThe Netherlands Department of Anatomical Pathology Singapore General HospitalSingapore 169608Singapore Division of Medical Scie

To address the increasing need for detecting and validating protein biomarkers in clinical specimens,mass spectrometry(MS)-based targeted proteomic techniques,including the selected reaction monitoring(SRM),parallel reaction monitoring(PRM),and massively parallel dataindependent acquisition(DIA),have been *** optimal performance,they require the fragment ion spectra of targeted peptides as prior *** this report,we describe a MS pipeline and spectral resource to support targeted proteomics studies for human tissue *** build the spectral resource,we integrated common open-source MS computational tools to assemble a freely accessible computational workflow based on *** then applied the workflow to generate DPHL,a comprehensive DIA pan-human library,from 1096 data-dependent acquisition(DDA)MS raw files for 16 types of cancer *** extensive spectral resource was then applied to a proteomic study of 17 prostate cancer(PCa)***,PRM validation was applied to a larger study of 57 PCa patients and the differential expression of three proteins in prostate tumor was *** a second application,the DPHL spectral resource was applied to a study consisting of plasma samples from 19 diffuse large B cell lymphoma(DLBCL)patients and 18 healthy control *** expressed proteins between DLBCL patients and healthy control subjects were detected by DIA-MS and confirmed by *** data demonstrate that the DPHL supports DIA and PRM MS pipelines for robust protein biomarker *** is freely accessible at https://***/page/***?id=IPX0001400000.

关键词： Data-independent acquisition Parallel reaction monitoring Spectral library Prostate cancer Diffuse large B cell lymphoma

iSplit LBI: Individualized partial ranking with ties via split LBI

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Qianqian Sun, Xinwei Yang, Zhiyong Cao, Xiaochun Huang, Qingming Yao, Yuan Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Microsoft Research Asia State Key Laboratory of Information Security Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management CAS Peng Cheng Laboratory Department of Mathematics Hong Kong University of Science and Technology Hong Kong

Due to the inherent uncertainty of data, the problem of predicting partial ranking from pairwise comparison data with ties has attracted increasing interest in recent years. However, in real-world scenarios, different individuals often hold distinct preferences. It might be misleading to merely look at a global partial ranking while ignoring personal diversity. In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective. Particularly, we formulate a unified framework which not only can be used for individualized partial ranking prediction, but also be helpful for abnormal user selection. This is realized by a variable splitting-based algorithm called iSplitLBI. Specifically, our algorithm generates a sequence of estimations with a regularization path, where both the hyperparameters and model parameters are updated. At each step of the path, the parameters can be decomposed into three orthogonal parts, namely, abnormal signals, personalized signals and random noise. The abnormal signals can serve the purpose of abnormal user selection, while the abnormal signals and personalized signals together are mainly responsible for individual partial ranking prediction. Extensive experiments on simulated and real-world datasets demonstrate that our new approach significantly outperforms state-of-the-art alternatives. The code is now availiable at https://***/qianqianxu010/ NeurIPS2019-iSplitLBI. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

Mitigate the obstructing effect of vehicles on the propagation of VANETs safety-related information

学校读者我要写书评

暂无评论

Mitigate the obstructing effect of vehicles on the propagati...

作者： Huang, Rui Wu, Jing Long, Chengnian Zhu, Yanmin Li, Bo Lin, Yi-Bing Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Department of Computer Science School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Computer Science and Information Engineering National Chiao Tung University Taiwan

As physical obstacles, vehicles have significant impacts on the efficient propagations of safety-related information in vehicular ad hoc networks (VANETs) by frequently obstructing the LOS links between transmitters and receivers. Obstructing effect will diminish the effective coverage of safety-related information and incur severe impact on road safety. However, this impact has not been addressed effectively. In this paper, we first present the definition of broadcast efficiency as the metric for quantizing the obstructing effect. We investigate the optimization issue for mitigating the impact of obstructing effect on the propagation of safety-related information and propose a graph theory-based optimization algorithm. For a distributed implementation of this optimization in VANETs, we further propose the maximum broadcast efficiency relaying (MBER) algorithm. MBER maximizes the effective coverage of information, meanwhile, meets delay and reliability constraints by incorporating broadcast efficiency and propagation distance in relay contention. Simulation results demonstrate that MBER promotes the effective coverage of safety-related information in VANETs with varying vehicular distribution. © 1967-2012 IEEE.

关键词： Vehicular ad hoc networks

Harmonized multimodal learning with Gaussian process latent variable models

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Song, Guoli Wang, Shuhui Huang, Qingming Tian, Qi School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Noah's Ark Lab Shenzhen518129 China Department of Computer Science University of Texas at San Antonio San AntonioTX78249 United States

Multimodal learning aims to discover the relationship between multiple modalities. It has become an important research topic due to extensive multimodal applications such as cross-modal retrieval. This paper attempts to address the modality heterogeneity problem based on Gaussian process latent variable models (GPLVMs) to represent multimodal data in a common space. Previous multimodal GPLVM extensions generally adopt individual learning schemes on latent representations and kernel hyperparameters, which ignore their intrinsic relationship. To exploit strong complementarity among different modalities and GPLVM components, we develop a novel learning scheme called Harmonization, where latent model parameters are jointly learned from each other. Beyond the correlation fitting or intra-modal structure preservation paradigms widely used in existing studies, the harmonization is derived in a model-driven manner to encourage the agreement between modality-specific GP kernels and the similarity of latent representations. We present a range of multimodal learning models by incorporating the harmonization mechanism into several representative GPLVM-based approaches. Experimental results on four benchmark datasets show that the proposed models outperform the strong baselines for cross-modal retrieval tasks, and that the harmonized multimodal learning method is superior in discovering semantically consistent latent representation. Copyright © 2019, The Authors. All rights reserved.

关键词： Gaussian distribution

POSTER: STAR (Space-Time Adaptive and Reductive) Algorithms for Real-World Space-Time Optimality

学校读者我要写书评

暂无评论

ACM SIGPLAN Notices 2017年第8期52卷 455-456页

作者： Tang, Yuan You, Ronghui School of Computer Science School of Software Fudan University Shanghai Key Lab. of Intelligent Information Processing State Key Lab. of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

It's important to hit a space-time balance for a real-world algorithm to achieve high performance on modern shared-memory multi-core or many-core systems. However, a large class of dynamic programs with more than $O(1)$ dependency achieve optimality either in space or time, but not both. In the literature, the problem is known as the fundamental space-time tradeoff. By exploiting properly on the runtime system, we show that our STAR (Space-Time Adaptive and Reductive) technique can help these dynamic programs to achieve sublinear parallel time bounds while still maintaining work-, space-, and cache-optimality in a processor- and cache-oblivious fashion. © 2017 ACM.

关键词： Real time systems

Edit probability for scene text recognition

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Bai, Fan Cheng, Zhanzhan Niu, Yi Pu, Shiliang Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Hikvision Research Institute China

We consider the scene text recognition problem under the attention-based encoder-decoder framework, which is the state of the art. The existing methods usually employ a frame-wise maximal likelihood loss to optimize the models. When we train the model, the misalignment between the ground truth strings and the attention’s output sequences of probability distribution, which is caused by missing or superfluous characters, will confuse and mislead the training process, and consequently make the training costly and degrade the recognition accuracy. To handle this problem, we propose a novel method called edit probability (EP) for scene text recognition. EP tries to effectively estimate the probability of generating a string from the output sequence of probability distribution conditioned on the input image, while considering the possible occurrences of missing/superfluous characters. The advantage lies in that the training process can focus on the missing, superfluous and unrecognized characters, and thus the impact of the misalignment problem can be alleviated or even overcome. We conduct extensive experiments on standard benchmarks, including the IIIT-5K, Street View Text and ICDAR datasets. Experimental results show that the EP can substantially boost scene text recognition performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Probability distributions

JeCache: Just-Enough Data Caching with Just-in-Time Prefetching for Big Data Applications 37

学校读者我要写书评

暂无评论

JeCache: Just-Enough Data Caching with Just-in-Time Prefetch...

37th IEEE International Conference on Distributed Computing Systems, ICDCS 2017

作者： Luo, Yifeng Shi, Jia Zhou, Shuigeng School of Computer Science and Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9781538617915

Big data clusters introduce an intermediate cache layer between the computing frameworks and the underlying distributed file systems, to enable upper-level applications or end users to efficiently access big datasets in cache and effectively share them among different computing frameworks. As caches are shared by multiple applications or end users, directly applying existing on-demand caching strategies will result in intense conflicts, when big datasets are cached as a whole. Meanwhile, big data applications usually involve massive numbers of file scans, cached-in data blocks may have little chance of being accessed before they are cached out to make way for other on-demand data blocks. Thus, it is unwise to cache data blocks long before they are actually accessed. In this paper, we propose a novel just-enough big data caching scheme for just-in-time block prefetching to improve the cache effectiveness of big data clusters. With just-in-time block prefetching, a block is cached in just before the task begins to process the block, rather than being cached in along with other blocks of the same dataset being processed. We monitor block accesses to measure the average processing time of data blocks, and then estimate the minimal number of blocks that should be kept in cache for a big dataset, so that the speed of data processing matches with that of data prefetching, and each upper-level task can obtain its input blocks from cache just in time. Our experimental results show that the proposed cache method can restrain over-requirement of cache resources in big data applications, and provides the same performance improvement as when all data blocks are cached. © 2017 IEEE.

关键词： Big data