检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wu, Zhe Su, Li Huang, Qingming Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pretrained convolutional neural networks (CNNs). Compared to high-level features, low-level features contribute less to performance but cost more computations because of their larger spatial resolutions. In this paper, we propose a novel Cascaded Partial Decoder (CPD) framework for fast and accurate salient object detection. On the one hand, the framework constructs partial decoder which discards larger resolution features of shallower layers for acceleration. On the other hand, we observe that integrating features of deeper layers obtain relatively precise saliency map. Therefore we directly utilize generated saliency map to refine the features of backbone network. This strategy efficiently suppresses distractors in the features and significantly improves their representation ability. Experiments conducted on five benchmark datasets exhibit that the proposed model not only achieves state-of-the-art performance but also runs much faster than existing models. Besides, the proposed framework is further applied to improve existing multi-level feature aggregation models and significantly improve their efficiency and accuracy. Copyright © 2019, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Seq-setnet: Exploring sequence sets for inferring structures

arXiv

引用

arXiv 2019年

作者： Ju, Fusong Zhu, Jianwei Wei, Guozheng Zhang, Qi Sun, Shiwei Bu, Dongbo Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Sequence set is a widely-used type of data source in a large variety of fields. A typical example is protein structure prediction, which takes an multiple sequence alignment (MSA) as input and aims to infer structural information from it. Almost all of the existing approaches exploit MSAs in an indirect fashion, i.e., they transform MSAs into position-specific scoring matrices (PSSM) that represent the distribution of amino acid types at each column. PSSM could capture columnwise characteristics of MSA, however, the column-wise characteristics embedded in each individual component sequence were nearly totally neglected. The drawback of PSSM is rooted in the fact that an MSA is essentially an unordered sequence set rather than a matrix. Specifically, the interchange of any two sequences will not affect the whole MSA. In contrast, the pixels in an image essentially form a matrix since any two rows of pixels cannot be interchanged. Therefore, the traditional deep neural networks designed for image processing cannot be directly applied on sequence sets. Here, we proposed a novel deep neural network framework (called Seq-SetNet) for sequence set processing. By employing a symmetric function module to integrate features calculated from preceding layers, Seq-SetNet are immune to the order of sequences in the input MSA. This advantage enables us to directly and fully exploit MSAs by considering each component protein individually. We evaluated Seq-SetNet by using it to extract structural information from MSA for protein secondary structure prediction. Experimental results on popular benchmark sets suggests that Seq-SetNet outperforms the stateof- the-art approaches by 3.6% in precision. These results clearly suggest the advantages of Seq-SetNet in sequence set processing and it can be readily used in a wide range of fields, say natural language processing. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning Target-Oriented Dual Attention for Robust RGB-T Tracking

Learning Target-Oriented Dual Attention for Robust RGB-T Tra...

引用

IEEE International Conference on Image processing

作者： Rui Yang Yabin Zhu Xiao Wang Chenglong Li Jin Tang Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China Institute of Physical Science and Information Technology Anhui University Hefei China

ISBN: (纸本)9781538662502;9781538662496

RGB-Thermal object tracking attempts to locate target object using complementary visual and thermal infrared data. Existing RGB-T trackers fuse different modalities by robust feature representation learning or adaptive modal weighting. However, how to integrate dual attention mechanism for visual tracking is still a subject that has not been studied yet. In this paper, we propose two visual attention mechanisms for robust RGB-T object tracking. Specifically, the local attention is implemented by exploiting the common visual attention of RGB and thermal data to train deep classifiers. We also introduce the global attention, which is a multimodal target-driven attention estimation network. It can provide global proposals for the classifier together with local proposals extracted from previous tracking result. Extensive experiments on two RGB-T benchmark datasets validated the effectiveness of our proposed algorithm.

关键词： Target tracking Visualization Training Feature extraction Proposals Object tracking Estimation

来源：评论

学校读者我要写书评

暂无评论

Fusing magnitude and phase features with multiple face models for robust face recognition

引用

Frontiers of Computer Science 2018年第6期12卷 1173-1191页

作者： Yan LI Shiguang SHAN Ruiping WANG Zhen CUI Xilin CHEN Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology (ICT)CASBeijing100190China University of Chinese Academy of Sciences Beijing 100049China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China

High accuracy face recognition is of great importance for a wide variety of real-world applications. Although significant progress has been made in the last decades, fully automatic face recognition systems have not yet approached the goal of surpassing the human vision system, even in controlled conditions. In this paper, we propose an approach for robust face recognition by fusing two complementary features: one is Gabor magnitude of multiple scales and orientations and the other is Fourier phase encoded by spatial pyramid based local phase quantization (SPLPQ). To reduce the high dimensionality of both features, block-wise fisher discriminant analysis (BFDA) is applied and further combined by score-level fusion. Moreover, inspired by the biological cognitive mechanism, multiple face models are exploited to further boost the robustness of the proposed approach. We evaluate the proposed approach on three challenging databases, i.e., FRGC ver2.0, LFW, and CFW-p, that address two face classification scenarios, i.e., verification and identification. Experimental results consistently exhibit the complementarity of the two features and the performance boost gained by the multiple face models. The proposed approach achieved approximately 96% verification rate when FAR was 0.1% on FRGC ver2.0 Exp.4, impressively surpassing all the best known results.

关键词： face recognition fisher discriminant analysis fusion Gabor magnitude feature multiple face models spatial pyramid based local phase quantization

来源：评论

学校读者我要写书评

暂无评论

Warm up cold-start advertisements: Improving CTR predictions via learning to learn ID embeddings

arXiv

引用

arXiv 2019年

作者： Pan, Feiyang Li, Shuokai Ao, Xiang Tang, Pingzhong He, Qing Institute of Computing Technology Chinese Academy of Sciences IIIS Tsinghua University Key Lab of Intelligent Information Processing of Chinese Academy of Sciences University of Chinese Academy of Sciences China

Click-through rate (CTR) prediction has been one of the most central problems in computational advertising. Lately, embedding techniques that produce low-dimensional representations of ad IDs drastically improve CTR prediction accuracies. However, such learning techniques are data demanding and work poorly on new ads with little logging data, which is known as the cold-start problem. In this paper, we aim to improve CTR predictions during both the cold-start phase and the warm-up phase when a new ad is added to the candidate pool. We propose Meta-Embedding, a meta-learningbased approach that learns to generate desirable initial embeddings for new ad IDs. The proposed method trains an embedding generator for new ad IDs by making use of previously learned ads through gradient-based meta-learning. In other words, our method learns how to learn better embeddings. When a new ad comes, the trained generator initializes the embedding of its ID by feeding its contents and attributes. Next, the generated embedding can speed up the model fitting during the warm-up phase when a few labeled examples are available, compared to the existing initialization methods. Experimental results on three real-world datasets showed that Meta-Embedding can significantly improve both the cold-start and warm-up performances for six existing CTR prediction models, ranging from lightweight models such as Factorization Machines to complicated deep models such as PNN and DeepFM. All of the above apply to conversion rate (CVR) predictions as well. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Moiré cavity quantum electrodynamics

引用

Science Advances 2025年第21期11卷 eadv8115页

作者： Wang, Yu-Tong Ye, Qi-Hang Yan, Jun-Yong Qiao, Yufei Liu, Yu-Xin Ye, Yong-Zheng Chen, Chen Cheng, Xiao-Tian Li, Chen-Hui Zhang, Zi-Jian Huang, Cheng-Nian Meng, Yun Zou, Kai Zhan, Wen-Kang Zhao, Chao Hu, Xiaolong Tee, Clarence Augustine T.H. Sha, Wei E.I. Huang, Zhixiang Liu, Huiyun Jin, Chao-Yuan Ying, Lei Liu, Feng State Key Laboratory of Extreme Photonics and Instrumentation College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China School of Physics Zhejiang Key Laboratory of Micro-nano Quantum Chips and Quantum Control Zhejiang University Hangzhou310027 China International Joint Innovation Center Zhejiang University Haining314400 China School of Precision Instrument and Optoelectronic Engineering Tianjin University Tianjin300072 China Key Laboratory of Optoelectronic Information Science and Technology Ministry of Education Tianjin300072 China Laboratory of Solid State Optoelectronics Information Technology Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Science Beijing101804 China College of Physics and Electrical Information Engineering Zhejiang Normal University Hangzhou310058 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230039 China Department of Electronic and Electrical Engineering University College London LondonWC1E 7JE United Kingdom ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Zhejiang Hangzhou311200 China

Quantum emitters are a key component in photonic quantum technologies. Enhancing single-photon emission by engineering their photonic environment is essential for improving overall efficiency in quantum information processing. However, this enhancement is often limited by the need for ultraprecise emitter placement within conventional photonic cavities. Inspired by the fascinating physics of moiré pattern, we propose a multilayer moiré photonic crystal with a robust isolated flatband. Theoretical analysis reveals that, with nearly infinite photonic density of states, the moiré cavity simultaneously has a high Purcell factor and large tolerance over the emitter’s position, breaking the constraints of conventional cavities. We then experimentally demonstrate various cavity quantum electrodynamic phenomena with a quantum dot in moiré cavity. A large tuning range (up to 40-fold) of quantum dot’s radiative lifetime is achieved through strong Purcell enhancement and inhibition effects. Our findings open the door for moiré flatband cavity–enhanced quantum light sources and quantum nodes for the quantum internet. Copyright © 2025 The Authors, some rights reserved.

关键词： Quantum electronics

来源：评论

学校读者我要写书评

暂无评论

Predicting compositional time series via autoregressive Dirichlet estimation

引用

中国科学（信息科学） 2018年第9期61卷 268-270页

作者： Ganbin ZHOU Ping LUO Qing HE Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

In recent years,compositional time series (CTS) prediction has become a widely applied data analysis method for modeling tactile sequence data [1],hydrological time series data using a four-stage algorithm (denoising,decomposition,components prediction and ensemble) [2],and daily and monthly extreme temperature data [3,4].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Drug3D-DTI: Improved Drug-target Interaction Prediction by Incorporating Spatial information of Small Molecules

Drug3D-DTI: Improved Drug-target Interaction Prediction by I...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhirui Liao Xiaodi Huang Hiroshi Mamitsuka Shanfeng Zhu School of Computer Science Fudan University Shanghai China Institute of Artificial Intelligence Biomedicine Nanjing University Nanjing China School of Computing Mathematics and Engineering Charles Sturt University Albury NSW Australia Bioinformatics Center Institute for Chemical Research Kyoto University Uji Kyoto Japan Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University) Ministry of Education China MOE Frontiers Center for Brain Science Fudan University Shanghai China Zhangjiang Fudan International Innovation Center Shanghai China Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9781665429825

A number of machine learning (ML) approaches for drug discovery have been available that rely only on sequential (1D) and planar (2D) information without effectively using the 3D information for generating features of drugs. However, 3D information of small molecules can reflect relative position of atoms more directly, which affects molecular properties. In this work, we present a new deep learning model called Drug3D-DTI for drug-target interaction prediction. Drug3D-DTI takes advantage of molecular spatial information, i.e., atom proximity in three-dimensional (3D) structures. We comprehensively evaluated the performance of Drug3D-DTI on two datasets with two tasks of regression and classification. In particular, we compared Drug3D-DTI with several existing methods including the two cutting-edge methods for compound-protein interaction prediction. From the experimental results, Drug3D-DTI clearly outperformed other methods under all settings. Further, this performance improvement was validated by ablation experiments and a case study. The implementation of Drug3D-DTI is available at (https://***/zhiruiliao/Drug3D-DTI).

关键词： Drugs Proteins Deep learning Solid modeling Three-dimensional displays Conferences Predictive models

来源：评论

学校读者我要写书评

暂无评论

Learning data-adaptive non-parametric kernels

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

来源：评论

学校读者我要写书评

暂无评论

RGB-T image saliency detection via collaborative graph learning

arXiv

引用

arXiv 2019年

作者： Tu, Zhengzheng Xia, Tian Li, Chenglong Wang, Xiaoxiao Ma, Yan Tang, Jin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Institute of Physical Science and Information Technology Anhui University Hefei China

Image saliency detection is an active research topic in the community of computer vision and multimedia. Fusing complementary RGB and thermal infrared data has been proven to be effective for image saliency detection. In this paper, we propose an effective approach for RGB-T image saliency detection. Our approach relies on a novel collaborative graph learning algorithm. In particular, we take superpixels as graph nodes, and collaboratively use hierarchical deep features to jointly learn graph affinity and node saliency in a unified optimization framework. Moreover, we contribute a more challenging dataset for the purpose of RGB-T image saliency detection, which contains 1000 spatially aligned RGB-T image pairs and their ground truth annotations. Extensive experiments on the public dataset and the newly created dataset suggest that the proposed approach performs favorably against the state-of-the-art RGB-T saliency detection methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

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：