检索结果-内蒙古大学图书馆

Collaborative self-attention for recommender systems

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yao, Kai-Lang Li, Wu-Jun National Key Laboratory for Novel Software Technology Deptpartment of Computer Science and Technology Nanjing University China

Recommender systems (RS), which have been an essential part in a wide range of applications, can be formulated as a matrix completion (MC) problem. To boost the performance of MC, matrix completion with side information, called inductive matrix completion (IMC), was further proposed. In real applications, the factorized version of IMC is more favored due to its efficiency of optimization and implementation. Regarding the factorized version, traditional IMC method can be interpreted as learning an individual representation for each feature, which is independent from each other. Moreover, representations for the same features are shared across all users/items. However, the independent characteristic for features and shared characteristic for the same features across all users/items may limit the expressiveness of the model. The limitation also exists in variants of IMC, such as deep learning based IMC models. To break the limitation, we generalize recent advances of self-attention mechanism to IMC and propose a context-aware model called collaborative self-attention (CSA), which can jointly learn context-aware representations for features and perform inductive matrix completion process. Extensive experiments on three large-scale datasets from real RS applications demonstrate effectiveness of CSA. Copyright © 2019, The Authors. All rights reserved.

关键词： Recommender systems

Context-Aware Point-of-Interest Recommendation Algorithm with Interpretability 15th

学校读者我要写书评

暂无评论

Context-Aware Point-of-Interest Recommendation Algorithm wit...

15th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2019

作者： Zhang, Guoming Qi, Lianyong Zhang, Xuyun Xu, Xiaolong Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Information Science and Engineering Qufu Normal University Qufu China Department of Electrical Computer Engineering The University of Auckland Auckland New Zealand School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Health Statistics and Information Center of Jiangsu Province Nanjing China

ISBN: (纸本)9783030301453

With the rapid development of mobile Internet, smart devices, and positioning technologies, location-based social networks (LBSNs) are growing rapidly. In LBSNs, point-of-interest (POI) recommendation is a crucial personalized location service that has become a research hotspot. To address extreme sparsity of user check-in data, a growing line of research exploits spatial-temporal information, social relationship, content information, popularity, and other factors to improve recommendation performance. However, the temporal and spatial transfers of user preferences are seldom mentioned in existing works, and interpretability, which is an important factor to enhance credibility of recommendation result, is overlooked. To cope with these issues, we propose a context-aware POI recommendation framework, which integrates users’ long-term static and time-varying preferences to improve recommendation performance and provide explanations. Experimental results over two real-world LBSN datasets demonstrate that the proposed solution has better performance than other advanced POI recommendation approaches. © 2019, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Location

The 2D Materials Roadmap

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ren, Wencai Bøggild, Peter Redwing, Joan Marie Novoselov, Kostya Sun, Luzhao Qi, Yue Jia, Kaicheng Liu, Zhongfan Burton, Oliver Alexander-Webber, Jack Hofmann, Stephan Cao, Yang Long, Yu Yang, Quan-Hong Li, Dan Choi, Soo Ho Kim, Ki Kang Lee, Young Hee Li, Mian Huang, Qing Gogotsi, Yury Clark, Nicholas Carl, Amy Gorbachev, Roman Olsen, Thomas Rosen, Johanna Thygesen, Kristian Sommer Efetov, Dmitri K. Jessen, Bjarke S. Yankowitz, Matthew Barrier, Julien Kumar, Roshan Krishna Koppens, Frank H.L. Deng, Hui Li, Xiaoqin Dai, Siyuan Basov, D.N. Wang, Xinran Das, Saptarshi Duan, Xiangfeng Yu, Zhihao Borsch, Markus Ferrari, Andrea C. Huber, Rupert Kira, Mackillo Xia, Fengnian Wang, Xiao Wu, Zhong-Shuai Feng, Xinliang Simon, Patrice Cheng, Hui-Ming Liu, Bilu Xie, Yi Jin, Wanqin Nair, Rahul Raveendran Xu, Yan Zhang, Qing Katiyar, Ajit K. Ahn, Jong-Hyun Aharonovich, Igor Hersam, Mark C. Roche, Stephan Hua, Qilin Shen, Guozhen Ren, Tianling Zhang, Hao-Bin Koo, Chong Min Koratkar, Nikhil Pellegrini, Vittorio Young, Robert J. Qu, Bill Lemme, Max Pollard, Andrew J. Shenyang National Laboratory for Materials Science Institute of Metal Research Chinese Academy of Sciences 72 Wenhua Road Shenyang110016 China Technical University of Denmark Denmark The Pennsylvania State University United States University of Manchester United Kingdom Institute for Functional Intelligent Materials National University of Singapore Singapore Beijing Graphene Institute China University of Cambridge United Kingdom Department of Chemical Engineering The University of Melbourne Victoria Australia Nanoyang Group Tianjin Key Laboratory of Advanced Carbon and Electrochemical Energy Storage School of Chemical Engineering and Technology Tianjin University Tianjin300072 China The Hong Kong University of Science and Technology Hong Kong Center for Integrated Nanostructure Physics Institute for Basic Science Suwon16419 Korea Republic of Sungkyunkwan University Suwon16419 Korea Republic of Zhejiang Key Laboratory of Data-Driven High-Safety Energy Materials and Applications Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences China Drexel University United States Linköping University Sweden Ludwig-Maximilians-Universität München Germany University of Washington United States ICFO The Institute of Photonic Sciences Castelldefels Barcelona08860 Spain University of Michigan United States University of Texas Austin United States Auburn University United States Columbia University United States State Key Laboratory of Catalysis Dalian Institute of Chemical Physics Chinese Academy of Sciences Dalian China University of California Los Angeles United States Suzhou Laboratory Suzhou China School of Integrated Circuit Science and Engineering Nanjing University of Posts and Telecommunications Nanjing210023 China Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States University of Regensburg Germany Department of Electrical and Computer Engineering Yale University New Have

Over the past two decades, 2D materials have rapidly evolved into a diverse and expanding family of material platforms. Many members of this materials class have demonstrated their potential to deliver transformative impact on fundamental research and technological applications across different fields. In this roadmap, we provide an overview of the key aspects of 2D material research and development, spanning synthesis, properties and commercial applications. We specifically present roadmaps for high impact 2D materials, including graphene and its derivatives, transition metal dichalcogenides, MXenes as well as their heterostructures and moiré systems. The discussions are organized into thematic sections covering emerging research areas (e.g., twisted electronics, moiré nano-optoelectronics, polaritronics, quantum photonics, and neuromorphic computing), breakthrough applications in key technologies (e.g., 2D transistors, energy storage, electrocatalysis, filtration and separation, thermal management, flexible electronics, sensing, electromagnetic interference shielding, and composites) and other important topics (computational discovery of novel materials, commercialization and standardization). This roadmap focuses on the current research landscape, future challenges and scientific and technological advances required to address, with the intent to provide useful references for promoting the development of 2D materials. © 2025, CC BY.

关键词： Integrated optoelectronics

Enhanced Sparse Model for Blind Deblurring 16th

学校读者我要写书评

暂无评论

Enhanced Sparse Model for Blind Deblurring

16th European Conference on computer Vision, ECCV 2020

作者： Chen, Liang Fang, Faming Lei, Shen Li, Fang Zhang, Guixu Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University Shanghai China School of Software Engineering East China Normal University Shanghai China School of Mathematical Sciences East China Normal University Shanghai China

ISBN: (纸本)9783030585945

Existing arts have shown promising efforts to deal with the blind deblurring task. However, most of the recent works assume the additive noise involved in the blurring process to be simple-distributed (i.e. Gaussian or Laplacian), while the real-world case is proved to be much more complicated. In this paper, we develop a new term to better fit the complex natural noise. Specifically, we use a combination of a dense function (i.e. l2) and a newly designed enhanced sparse model termed as le, which is developed from two sparse models (i.e. l1 and l0), to fulfill the task. Moreover, we further suggest using le to regularize image gradients. Compared to the widely-adopted l0 sparse term, le can penalize more insignificant image details (Fig. 1). Based on the half-quadratic splitting method, we provide an effective scheme to optimize the overall formulation. Comprehensive evaluations on public datasets and real-world images demonstrate the superiority of the proposed method against state-of-the-art methods in terms of both speed and accuracy. © 2020, Springer Nature Switzerland AG.

关键词： Additive noise

Quantum Experiments and Hypergraphs: Multi-Photon Sources for Quantum Interference, Quantum Computation and Quantum Entanglement

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gu, Xuemei Chen, Lijun Krenn, Mario State Key Laboratory for Novel Software Technology Nanjing University 163 Xianlin Avenue Qixia District Nanjing City210023 China Department of Chemistry & Computer Science University of Toronto Canada & Vector Institute for Artificial Intelligence Toronto Canada

We introduce the concept of hypergraphs to describe quantum optical experiments with probabilistic multi-photon sources. Every hyperedge represents a correlated photon source, and every vertex stands for an optical output path. Such general graph description provides new insights for producing complex high-dimensional multi-photon quantum entangled states, which go beyond limitations imposed by pair creation via spontaneous parametric down-conversion. Furthermore, properties of hypergraphs can be investigated experimentally. For example, the NP-Complete problem of deciding whether a hypergraph has a perfect matchin can be answered by experimentally detecting multi-photon events in quantum experiments. By introducing complex weights in hypergraphs, we show a general many-particle quantum interference and manipulating entanglement in a pictorial way. Our work paves the path for the development of multi-photon high-dimensional state generation and might inspire new applications of quantum computations using hypergraph mappings. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph theory

ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xiong, Fu Xiao, Yang Cao, Zhiguo Wang, Yancheng Zhou, Joey Tianyi Wu, Jianxin National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Institute of High Performance Computing A*STAR Singapore Singapore National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

Face verification can be regarded as a 2-class fine-grained visual recognition problem. Enhancing the feature’s discriminative power is one of the key problems to improve its performance. Metric learning technology is often applied to address this need, while achieving a good tradeoff between underfitting and overfitting plays the vital role in metric learning. Hence, we propose a novel ensemble cascade metric learning (ECML) mechanism. In particular, hierarchical metric learning is executed in the cascade way to alleviate underfitting. Meanwhile, at each learning level, the features are split into non-overlapping groups. Then, metric learning is executed among the feature groups in the ensemble manner to resist overfitting. Considering the feature distribution characteristics of faces, a robust Mahalanobis metric learning method (RMML) with closed-form solution is additionally proposed. It can avoid the computation failure issue on inverse matrix faced by some well-known metric learning approaches (e.g., KISSME). Embedding RMML into the proposed ECML mechanism, our metric learning paradigm (EC-RMML) can run in the one-pass learning manner. Experimental results demonstrate that EC-RMML is superior to state-of-the-art metric learning methods for face verification. And, the proposed ensemble cascade metric learning mechanism is also applicable to other metric learning approaches. Copyright © 2020, The Authors. All rights reserved.

关键词： Inverse problems

Crosslink-net: Double-branch encoder segmentation network via fusing vertical and horizontal convolutions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Qian Qi, Lei Zhou, Luping Wang, Lei Yin, Yilong Shi, Yinghuan Wang, Wuzhang Gao, Yang School of Data and Computer Science Shandong Women's University Jinan250300 China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Engineering Southeast University Nanjing211189 China The School of Electrical and Information Engineering University of Sydney NSW2006 Australia The School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia The School of Soft Shandong University Jinan250100 China Department of Respiratory and Critical Care Medicine Shandong Chest Hospital Jinan250013 China

Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels in the double-branch encoder, so features learned by the two branches can be expected to complement each other. 2) Considering that spatial attention can help models to better focus on the target region in a large-sized image, we develop an attention loss to further emphasize the segmentation on small-sized targets. Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net. The experiments validate the effectiveness of our model on four datasets. The code is released at https://***/Qianyu1226/*** Codes 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

Parametric Model Estimation for 3D Clothed Humans from Point Clouds

学校读者我要写书评

暂无评论

Parametric Model Estimation for 3D Clothed Humans from Point...

International Symposium on Mixed and Augmented Reality (ISMAR)

作者： Kangkan Wang Huayu Zheng Guofeng Zhang Jian Yang Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of CAD&CG Zhejiang University China

This paper presents a novel framework to estimate parametric model- s for 3D clothed humans from partial point clouds. It is a challenging problem due to factors such as arbitrary human shape and pose, large variations in clothing details, and significant missing data. Existing methods mainly focus on estimating the parametric model of undressed bodies or reconstructing the non-parametric 3D shapes from point clouds. In this paper, we propose a hierarchical regression framework to learn the parametric model of detailed human shapes from partial point clouds of a single depth frame. Benefiting from the favorable ability of deep neural networks to model nonlinearity, the proposed framework cascades several successive regression networks to estimate the parameters of detailed 3D human body models in a coarse-to-fine manner. Specifically, the first global regression network extracts global deep features of point clouds to obtain an initial estimation of the undressed human model. Based on the initial estimation, the local regression network then refines the undressed human model by using the local features of neighborhood points of human joints. Finally, the clothing details are inferred as an additive displacement on the refined undressed model using the vertex-level regression network. The experimental results demonstrate that the proposed hierarchical regression approach can accurately predict detailed human shapes from partial point clouds and outperform prior works in the recovery accuracy of 3D human models.

关键词： Deep learning Solid modeling Three-dimensional displays Shape Clothing Estimation Predictive models

Cross-modality brain tumor segmentation via bidirectional global-to-local unsupervised domain adaptation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： He, Kelei Ji, Wen Zhou, Tao Li, Zhuoyuan Huo, Jing Zhang, Xin Gao, Yang Shen, Dinggang Zhang, Bing Zhang, Junfeng Medical School of Nanjing University Nanjing China The National Institute of Healthcare Data Science Nanjing University Nanjing China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China Department of Radiology Nanjing Drum Tower Hospital Nanjing University Medical School China School of Biomedical Engineering ShanghaiTech University Shanghai China Department of Research and Development Shanghai United Imaging Intelligence Co. Ltd. Shanghai China Department of Artificial Intelligence Korea University Seoul Korea Republic of

Accurate segmentation of brain tumors from multi-modal Magnetic Resonance (MR) images is essential in brain tumor diagnosis and treatment. However, due to the existence of domain shifts among different modalities, the performance of networks decreases dramatically when training on one modality and performing on another, e.g., train on T1 image while perform on T2 image, which is often required in clinical applications. This also prohibits a network from being trained on labeled data and then transferred to unlabeled data from a different domain. To overcome this, unsupervised domain adaptation (UDA) methods provide effective solutions to alleviate the domain shift between labeled source data and unlabeled target data. In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under an UDA scheme. Specifically, A bidirectional image synthesis and segmentation module is proposed to segment the brain tumor using the intermediate data distributions generated for the two domains, which includes an image-to-image translator and a shared-weighted segmentation network. Further, a global-to-local consistency learning module is proposed to build robust representation alignments in an integrated way. Extensive experiments on a multi-modal brain MR benchmark dataset demonstrate that the proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin, while a comprehensive ablation study validates the effectiveness of each key component. The implementation code of our method will be released at https://***/KeleiHe/BiGL. © 2021, CC BY-NC-SA.

关键词： Generative adversarial networks