检索结果-内蒙古大学图书馆

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Li, Zhi Wu, Bo Liu, Qi Wu, Likang Zhao, Hongke Mei, Tao Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science University of Science and Technology of China China Columbia University United States School of Computer Science and Technology University of Science and Technology of China China College of Management and Economics Tianjin University China JD AI Research

ISBN: (纸本)9780999241165

Complementary recommendations, which aim at providing users product suggestions that are supplementary and compatible with their obtained items, have become a hot topic in both academia and industry in recent years. Existing work mainly focused on modeling the co-purchased relations between two items, but the compositional associations of item collections are largely unexplored. Actually, when a user chooses the complementary items for the purchased products, it is intuitive that she will consider the visual semantic coherence (such as color collocations, texture compatibilities) in addition to global impressions. Towards this end, in this paper, we propose a novel Content Attentive Neural Networks (CANN) to model the comprehensive compositional coherence on both global contents and semantic contents. Specifically, we first propose a Global Coherence Learning (GCL) module based on multi-heads attention to model the global compositional coherence. Then, we generate the semantic-focal representations from different semantic regions and design a Focal Coherence Learning (FCL) module to learn the focal compositional coherence from different semantic-focal representations. Finally, we optimize the CANN in a novel compositional optimization strategy. Extensive experiments on the large-scale real-world data clearly demonstrate the effectiveness of CANN compared with several state-of-the-art methods. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adam revisited: A weighted past gradients perspective

arXiv

引用

arXiv 2021年

作者： Zhong, Hui Chen, Zaiyi Qin, Chuan Huang, Zai Zheng, Vincent W. Xu, Tong Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Hefei230027 China Zhejiang Cainiao Supply Chain Management Co. Ltd China Advanced Digital Sciences Center Singapore

Adaptive learning rate methods have been successfully applied in many fields, especially in training deep neural networks. Recent results have shown that adaptive methods with exponential increasing weights on squared past gradients (i.e., ADAM, RMSPROP) may fail to converge to the optimal solution. Though many algorithms, such as AMSGRAD and ADAMNC, have been proposed to fix the non-convergence issues, achieving a data-dependent regret bound similar to or better than ADAGRAD is still a challenge to these methods. In this paper, we propose a novel adaptive method Weighted Adaptive Algorithm (WADA) to tackle the non-convergence issues. Unlike AMSGRAD and ADAMNC, we consider using a milder growing weighting strategy on squared past gradient, in which weights grow linearly. Based on this idea, we propose Weighted Adaptive Gradient Method Framework (WAGMF) and implement WADA algorithm on this framework. Moreover, we prove that WADA can achieve a weighted data-dependent regret bound, which could be better than the original regret bound of ADAGRAD when the gradients decrease rapidly. This bound may partially explain the good performance of ADAM in practice. Finally, extensive experiments demonstrate the effectiveness of WADA and its variants in comparison with several variants of ADAM on training convex problems and deep neural networks. Copyright © 2021, The Authors. All rights reserved.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Boosting Factorization Machines via Saliency-Guided Mixup

arXiv

引用

arXiv 2022年

作者： Wu, Chenwang Lian, Defu Ge, Yong Zhou, Min Chen, Enhong Tao, Dacheng School of Data Science University of Science and Technology of China Anhui Hefei230000 China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China Eller College of Management University of Arizona United States Huawei Noah’s Ark Lab Hong Kong JD Explore Academy in *** China University of Sydney Australia

Factorization machines (FMs) are widely used in recommender systems due to their adaptability and ability to learn from sparse data. However, for the ubiquitous non-interactive features in sparse data, existing FMs can only estimate the parameters corresponding to these features via the inner product of their embeddings. Undeniably, they cannot learn the direct interactions of these features, which limits the model’s expressive power. To this end, we first present MixFM, inspired by Mixup, to generate auxiliary training data to boost FMs. Unlike existing augmentation strategies that require labor costs and expertise to collect additional information such as position and fields, these extra data generated by MixFM only by the convex combination of the raw ones without any professional knowledge support. More importantly, if the parent samples to be mixed have non-interactive features, MixFM will establish their direct interactions. Second, considering that MixFM may generate redundant or even detrimental instances, we further put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM). Guided by the customized saliency, SMFM can generate more informative neighbor data. Through theoretical analysis, we prove that the proposed methods minimize the upper bound of the generalization error, which hold a beneficial effect on enhancing FMs. Significantly, we give the first generalization bound of FM, implying the generalization requires more data and a smaller embedding size under the sufficient representation capability. Finally, extensive experiments on five datasets confirm that our approaches are superior to baselines. Besides, the results show that"poisoning" mixed data is likewise beneficial to the FM variants. Copyright © 2022, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A novel ship detection method based on Gabor feature 5

A novel ship detection method based on Gabor feature

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Chang, Jiahui Fu, Zewen Li, Ning Chang, Jike College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng475004 China

ISBN: (纸本)9781839535635

Synthetic Aperture Radar (SAR) Systems can be used for discovery and surveillance. According to the current requirements, accurate ship detection is becoming more and more important. However, the accuracy of traditional ship detection algorithm is not satisfying in complex scene. As a consequence, this paper proposes a novel method for detecting ships within SAR imagery using Gabor feature and Two Parameter Constant False Alarm Rate (2P-CFAR) detection technique. First, feature extraction was performed by using Gabor filter. Then, combined with the extracted orientation feature, the ship recognition of SAR image is obtained by 2P-CFAR detector. Finally, false alarms among the candidate targets were removed by geometric features of the ships. To prove the rationality of this method, experiments were carried with two high-resolution Gaofen-3 satellite SAR images in open sea background. The experimental results show that the presented method has preferable performance in the accuracy of ship identification. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Paralle acceleration of multi-mode SAR imaging on GPU 5

Paralle acceleration of multi-mode SAR imaging on GPU

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Bai, Lan Guo, Zhengwei Wang, Kuan Fu, Zewen College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng475004 China

ISBN: (纸本)9781839535635

With the continuous expansion of the application field of multi-mode synthetic aperture radar (SAR) system, which can satisfy different imaging demands. In order to get SAR image, it is necessary to image the echo received by multi-mode SAR system. However, the huge computation of the imaging algorithm affects the processing efficiency of SAR system. The power of Graphics Processing Unit (GPU) can suffice the increasing demands in processing, which has been used in many common areas. The acceleration effect of GPU is very obvious compared with Central Processing Unit (CPU) platform. This paper proposed a Chirp Scaling acceleration algorithm based on GPU for multi-mode SAR, and comparison of computational time over traditional CPU and GPU platform. The experimental results shows that the GPU accelerated SAR imaging algorithm can achieve a good acceleration effect. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

A new vegetation index for cooperative inversion of winter wheat covered surface soil moisture based on sentinel-1/2 remote sensing data 5

A new vegetation index for cooperative inversion of winter w...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Zhang, Bei Zhao, Jianhui Li, Ning Guo, Zhengwei College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng475004 China

ISBN: (纸本)9781839535635

Aiming at the problem of the interfere of winter wheat on radar backscattering coefficient in surface soil moisture inversion, a new vegetation index called Fusion Vegetation Index (FVI) is defined in this study. Based on the Multi-Spectral Imager (MSI) data of Sentinel-2, and the Synthetic Aperture Radar (SAR) data of Sentinel-1, using FVI to retrieve water content of winter wheat, combined with Water Cloud model, the interference of winter wheat in soil moisture inversion was reduced. The results show that good soil moisture retrieval results can be obtained by combining with FVI. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Technical Phrase Extraction for Patent Mining: A Multi-level Approach

Technical Phrase Extraction for Patent Mining: A Multi-level...

引用

IEEE International Conference on data Mining (ICDM)

作者： Ye Liu Han Wu Zhenya Huang Hao Wang Jianhui Ma Qi Liu Enhong Chen Hanqing Tao Ke Rui Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science & School of Computer Science and Technology University of Science and Technology of China

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Recent years have witnessed a booming increase of patent applications, which provides an open chance for revealing the inner law of innovation, but in the meantime, puts forward higher requirements on patent mining techniques. Considering that patent mining highly relies on patent document analysis, this paper makes a focused study on constructing a technology portrait for each patent, i.e., to recognize technical phrases concerned in it, which can summarize and represent patents from a technology angle. To this end, we first give a clear and detailed description about technical phrases in patents based on various prior works and analyses. Then, combining characteristics of technical phrases and multi-level structures of patent documents, we develop an Unsupervised Multi-level Technical Phrase Extraction (UMTPE) model. Particularly, a novel evaluation metric called Information Retrieval Efficiency (IRE) is designed to evaluate the extracted phrases from a new perspective, which greatly supplements traditional metrics like Precision and Recall. Finally, extensive experiments on real-world patent data show the effectiveness of our UMTPE model.

关键词： Measurement Patents Technological innovation Text analysis Conferences Information retrieval data models

来源：评论

学校读者我要写书评

暂无评论

On scattering characteristics of winter wheat at different phenological period based on Sentinel-1A SAR images 5

On scattering characteristics of winter wheat at different p...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Xu, Dongya Zhao, Jianhui Li, Ning College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng475004 China

ISBN: (纸本)9781839535635

Phenophase period refers to the periodic natural phenomena of plants under the influence of environmental factors and human activities. In recent years, synthetic aperture radar (SAR) has been used to growth monitoring of crops. Due to complex morphological changes at different growth stage of crops, single-phase SAR data unable provide sufficient information to analyze scattering characteristics at different phenological period. In this paper, the scattering characteristics of winter wheat are studied, using time series dual-polarization Sentinel-1A SAR images. And winter wheat planting region in Kaifeng city Henan Province is selected as the study area. Time series C-band radar backscatter coefficient is extracted, then analyze correlation between numerical evolution and phenological change with different polarization data. The variation trend is verified by field measured data. The results show that dual-polarization SAR image is great practical significance for winter wheat phenological monitoring. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Group Multi-View Transformer for 3D Shape analysis with Spatial Encoding

arXiv

引用

arXiv 2023年

作者： Xu, Lixiang Cui, Qingzhe Hong, Richang Xu, Wei Chen, Enhong Yuan, Xin Li, Chenglong Tang, Yuanyan The College of Artificial Intelligence and Big Data Hefei University Hefei230027 China The School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China The Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China The School of Electrical and Mechanical Engineering The University of Adelaide AdelaideSA5005 Australia The School of Artificial Intelligence Anhui University Hefei230601 China The Zhuhai UM Science and Technology Research Institute FST University of Macau China

In recent years, the results of view-based 3D shape recognition methods have saturated, and models with excellent performance cannot be deployed on memory-limited devices due to their huge size of parameters. To address this problem, we introduce a compression method based on knowledge distillation for this field, which largely reduces the number of parameters while preserving model performance as much as possible. Specifically, to enhance the capabilities of smaller models, we design a high-performing large model called Group Multi-view Vision Transformer (GMViT). In GMViT, the view-level ViT first establishes relationships between view-level features. Additionally, to capture deeper features, we employ the grouping module to enhance view-level features into group-level features. Finally, the group-level ViT aggregates group-level features into complete, well-formed 3D shape descriptors. Notably, in both ViTs, we introduce spatial encoding of camera coordinates as innovative position embeddings. Furthermore, we propose two compressed versions based on GMViT, namely GMViT-simple and GMViT-mini. To enhance the training effectiveness of the small models, we introduce a knowledge distillation method throughout the GMViT process, where the key outputs of each GMViT component serve as distillation targets. Extensive experiments demonstrate the efficacy of the proposed method. The large model GMViT achieves excellent 3D classification and retrieval results on the benchmark datasets ModelNet, ShapeNetCore55, and MCB. The smaller models, GMViT-simple and GMViT-mini, reduce the parameter size by 8 and 17.6 times, respectively, and improve shape recognition speed by 1.5 times on average, while preserving at least 90% of the classification and retrieval performance. The code is available at https://***/bigdatagraph/*** Codes 68 Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Deep technology tracing for high-tech companies

arXiv

引用

arXiv 2020年

作者： Wu, Han Zhang, Kun Lv, Guangyi Liu, Qi Yu, Runlong Zhao, Weihao Chen, Enhong Ma, Jianhui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China

Technological change and innovation are vitally important, especially for high-tech companies. However, factors influencing their future research and development (R&D) trends are both complicated and various, leading it a quite difficult task to make technology tracing for high-tech companies. To this end, in this paper, we develop a novel data-driven solution, i.e., Deep Technology Forecasting (DTF) framework, to automatically find the most possible technology directions customized to each high-tech company. Specially, DTF consists of three components: Potential Competitor Recognition (PCR), Collaborative Technology Recognition (CTR), and Deep Technology Tracing (DTT) neural network. For one thing, PCR and CTR aim to capture competitive relations among enterprises and collaborative relations among technologies, respectively. For another, DTT is designed for modeling dynamic interactions between companies and technologies with the above relations involved. Finally, we evaluate our DTF framework on real-world patent data, and the experimental results clearly prove that DTF can precisely help to prospect future technology emphasis of companies by exploiting hybrid factors. Copyright © 2020, The Authors. All rights reserved.

关键词： Patents and inventions

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：