检索结果-内蒙古大学图书馆

IEEE International Conference on Data Mining (ICDM)

作者： Qingping Yang Yingpeng Hu Rongyu Cao Hongwei Li Ping Luo Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China P.A.I. Ltd. Beijing China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781665423991

Table, widely used in documents from various vertical domains, is a compact representation of data. There is always some strong demand to automatically extract key information from tables for further analysis. In addition, the set of keys that need to be extracted information is usually time-varying, which arises the issue of zero-shot keys in this situation. To increase the efficiency of these knowledge workers, in this study we aim to extract the values of a given set of keys from tables. Previous table-related studies mainly focus on relational, entity, and matrix tables. However, their methods fail on mixed-style tables, in which table headers might exist in any non-merged or merged cell, and the spatial relationships between headers and corresponding values are diverse. Here, we address this problem while taking mixed-style tables into account. To this end, we propose an end-to-end neural-based model, called information Extraction in Mixed-style Table (IEMT). IEMT first uses BERT to extract textual semantics of the given key and the words in each cell. Then, it uses multi-layer CNN to capture the spatial and textual interactions among adjacent cells. Furthermore, to improve the accuracy on zero-shot keys, we pre-train IEMT on a dataset constructed on 0.4 million tables from Wikipedia and 140 million triplets from Ownthink. Experiments with the fine-tuning step on 26,869 financial tables show that the proposed model achieves 0.9323 accuracy for zero-shot keys, obtaining more than 8% increase compared with the model without pre-training.

关键词： Conferences Semantics Bit error rate Encyclopedias Data models Internet Data mining

来源：评论

学校读者我要写书评

暂无评论

Noise optimization for artificial neural networks

arXiv

引用

arXiv 2021年

作者： Xiao, Li Zhang, Zeliang Peng, Yijie Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100090 China Department of Management Science and Information Systems Guanghua School of Management Peking University Beijing100871 China School of computer science and technology Huazhong University of Science and Technology China

Adding noises to artificial neural network(ANN) has been shown to be able to improve robustness in previous work. In this work, we propose a new technique to compute the pathwise stochastic gradient estimate with respect to the standard deviation of the Gaussian noise added to each neuron of the ANN. By our proposed technique, the gradient estimate with respect to noise levels is a byproduct of the backpropagation algorithm for estimating gradient with respect to synaptic weights in ANN. Thus, the noise level for each neuron can be optimized simultaneously in the processing of training the synaptic weights at nearly no extra computational cost. In numerical experiments, our proposed method can achieve significant performance improvement on robustness of several popular ANN structures under both black box and white box attacks tested in various computer vision datasets. code is availab.e at https://***/LX-doctorAI/ noiseoptimize © 2021, CC BY.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic diagnosis of disc herniation based on DenseNet fusion model 8

Automatic diagnosis of disc herniation based on DenseNet fus...

引用

8th International Conference on Digital Home, ICDH 2020

作者： Wang, Zimin Qin, Junyan Huang, Jinrong Wang, Yumeng Li, Ji Guilin University of Electronic Technology Guangxi Colleges and Universities Key Lab. of Intelligent Processing of Computer Image and Graphics Guilin541004 China Guilin Huigu Institute of Artificial Intelligence Industrial Technology Guilin541004 China Guilin University of Electronic Technology School of Computer Science and Information Security Guilin541004 China

ISBN: (纸本)9781728192345

Spine MRI images generally have the characteristics of low contrast and much noise. Because the variable shape of the spine edge, the traditional spine image segmentation method requires a lot of preprocessing and can not perform image segmentation automatically, which is inefficient and cannot compliant the clinical work requirements. So as to solve the above problems, this paper use deep learning algorithms to identify the spine images, and proposed a disc herniation recognition method for spinal MRI images which based on DenseNet fusion model. Use DenseNet and Inception-Resnet-V2 model fusion to get more image features and improve the image recognition accuracy. Experiments prove that this method can be used to identify the herniation of spinal intervertebral disc with high accuracy and real-time. © 2020 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

SAN-Net: Learning Generalization to Unseen Sites for Stroke Lesion Segmentation with Self-Adaptive Normalization

arXiv

引用

arXiv 2022年

作者： Yu, Weiyi Huang, Zhizhong Zhang, Junping Shan, Hongming Institute of Science and Technology for Brain-Inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200433 China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai201210 China

There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular disease. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large inter-site discrepancy among different scanners, imaging protocols, and populations, but also the variations in stroke lesion shape, size, and location. To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptive generalization on unseen sites for stroke lesion segmentation. Motivated by traditional z-score normalization and dynamic network, we devise a masked adaptive instance normalization (MAIN) to minimize inter-site discrepancies, which standardizes input MR images from different sites into a site-unrelated style by dynamically learning affine parameters from the input;i.e., MAIN can affinely transform the intensity values. Then, we leverage a gradient reversal layer to force the U-net encoder to learn site-invariant representation with a site classifier, which further improves the model generalization in conjunction with MAIN. Finally, inspired by the "pseudosymmetry" of the human brain, we introduce a simple yet effective data augmentation technique, termed symmetry-inspired data augmentation (SIDA), that can be embedded within SAN-Net to double the sample size while halving memory consumption. Experimental results on the benchmark Anatomical Tracings of Lesions After Stroke (ATLAS) v1.2 dataset, which includes MR images from 9 different sites, demonstrate that under the "leave-one-site-out" setting, the proposed SAN-Net outperforms recently published methods in terms of quantitative metrics and qualitative comparisons. © 2022, CC BY.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

EXTRACTING ABSTRACTION DIMENSIONS BY IDENTIFYING SYNTAX PATTERN FROM TEXTS

arXiv

引用

arXiv 2025年

作者： Zhou, Jian Li, Jiazheng Zhuge, Sirui Zhuge, Hai Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China King’s College London United Kingdom Publicis Sapient United Kingdom School of Computing and Information Technology Great Bay University Dongguan China Great Bay Institute for Advanced Study Dongguan China

This paper proposed an approach to automatically discovering subject dimension, action dimension, object dimension and adverbial dimension from texts to efficiently operate texts and support query in natural language. The high quality of trees guarantees that all subjects, actions, objects and adverbials and their subclass relations within texts can be represented. The independency of trees ensures that there is no redundant representation between trees. The expressiveness of trees ensures that the majority of sentences can be accessed from each tree and the rest of sentences can be accessed from at least one tree so that the tree-based search mechanism can support querying in natural language. Experiments show that the average precision, recall and F1-score of the abstraction trees constructed by the subclass relations of subject, action, object and adverbial are all greater than 80%. The application of the proposed approach to supporting query in natural language demonstrates that different types of question patterns for querying subject or object have high coverage of texts, and searching multiple trees on subject, action, object and adverbial according to the question pattern can quickly reduce search space to locate target sentences, which can support precise operation on *** Codes 68T50 (Primary) 91F20 (Secondary) © 2025, CC BY.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval

Cross-modal Scene Graph Matching for Relationship-aware Imag...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Sijin Wang Ruiping Wang Ziwei Yao Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

ISBN: (数字)9781728165530

ISBN: (纸本)9781728165547

Image-text retrieval of natural scenes has been a popular research topic. Since image and text are heterogeneous cross-modal data, one of the key challenges is how to learn comprehensive yet unified representations to express the multi-modal data. A natural scene image mainly involves two kinds of visual concepts, objects and their relationships, which are equally essential to image-text retrieval. Therefore, a good representation should account for both of them. In the light of recent success of scene graph in many CV and NLP tasks for describing complex natural scenes, we propose to represent image and text with two kinds of scene graphs: visual scene graph (VSG) and textual scene graph (TSG), each of which is exploited to jointly characterize objects and relationships in the corresponding modality. The image-text retrieval task is then naturally formulated as cross-modal scene graph matching. Specifically, we design two particular scene graph encoders in our model for VSG and TSG, which can refine the representation of each node on the graph by aggregating neighborhood information. As a result, both object-level and relationship-level cross-modal features can be obtained, which favorably enables us to evaluate the similarity of image and text in the two levels in a more plausible way. We achieve state-of-the-art results on Flickr30k and MS COCO, which verifies the advantages of our graph matching based approach for image-text retrieval.

关键词： Visualization Feature extraction Semantics Task analysis Image edge detection Pediatrics Generators

来源：评论

学校读者我要写书评

暂无评论

The research of the expansion property and chain mixing property of topological group 12

The research of the expansion property and chain mixing prop...

引用

12th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2020

作者： Zhan-Jiang, Ji Wei, Shi School of Information and Electronic Engineering Wuzhou University China Guangxi Colleges and Universities Key Lab. of Image Processing and Intelligent Information System Wuzhou University China Guangxi Colleges and Universities Key Laboratory of Professional Software Technology Wuzhou University China Party Committee Office Wuzhou Vocational College China

ISBN: (纸本)9781728170817

The expansion property and chain mixing property have an important significance in terms of theory and application. The concept of the expansion property and chain mixing property are introduced in this paper. We study their dynamical properties. The following result are obtained: (1)Letbe the hyperspace of. Ifis expansive, thenis expansive;(2)Letbe the hyperspace of. Ifis chain mixing, thenis chain mixing;(3)Letbe the hyperspace of. Ifis chain transitive, thenis chain transitive;These results enriched the theory of the expansion property and chain mixing property of topological group. © 2020 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Rethinking Collab.rative Metric Learning: Toward an Efficient Alternative without Negative Sampling

arXiv

引用

arXiv 2022年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518055 China

The recently proposed Collab.rative Metric Learning (CML) paradigm has aroused wide interest in the area of recommendation systems (RS) owing to its simplicity and effectiveness. Typically, the existing literature of CML depends largely on the negative sampling strategy to alleviate the time-consuming burden of pairwise computation. However, in this work, by taking a theoretical analysis, we find that negative sampling would lead to a biased estimation of the generalization error. Specifically, we show that the sampling-based CML would introduce a bias term in the generalization bound, which is quantified by the per-user Total Variance (TV) between the distribution induced by negative sampling and the ground truth distribution. This suggests that optimizing the sampling-based CML loss function does not ensure a small generalization error even with sufficiently large training data. Moreover, we show that the bias term will vanish without the negative sampling strategy. Motivated by this, we propose an efficient alternative without negative sampling for CML named Sampling-Free Collab.rative Metric Learning (SFCML), to get rid of the sampling bias in a practical sense. Finally, comprehensive experiments over seven benchmark datasets speak to the superiority of the proposed algorithm. © 2022, CC BY.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised classification method of SAR images using spectral clustering in contourlet domain 4

Semi-supervised classification method of SAR images using sp...

引用

2019 4th International Seminar on Computer technology, Mechanical and Electrical Engineering, ISCME 2019

作者： Jiang, Kaiwen Zhang, Degan Xu, Haixia Key Laboratory of Computer Vision and System Tianjin University of Technology Ministry of Education 300384 China Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin China School of Electronic and Information Engineering Tianjin Vocational Institute Tianjin300410 China

A new based on Semi-supervised classification theory for SAR images in contourlet domain is proposed, in this paper. Attempting to get better and faster performance, the PSO algorithm (Particle swarm optimization algorithm) and contourlet domain is proposed to instead of traditional k-means algorithm. PSO is used to find the global optimum by performing a global search in the whole solution space. And then, contourlet is applied in front of construct the similarity matrix to extract more effective eigenvalues. In section five, the proposed algorithm got better classification results than the traditional k-means algorithm which is proved by experimental results show that in terms of running time, classification accuracy and Kappa coefficient. © Published under licence by IOP Publishing Ltd.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

The research of G-chain transitive and G-chain mixing on the hyperspace of topological group action 12

The research of G-chain transitive and G-chain mixing on the...

引用

12th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2020

ISBN: (纸本)9781728170817

G-chain transitive and G-chain mixing have an important significance in terms of theory and application. According to the definition of chain transitive and chain mixing, we give the concept of G-chain transitiveand G-chain mixing in this paper. By inference, some conclusions of the hyperspace were extended to the hyperspace of topological group action. We have the following result: (1)Letbe the hyperspace of. Ifis a G-chain transitive map, thenis a G-chain transitive map;(2)Letbe the hyperspace of. Ifis a G-chain mixing map, thenis a G-chain mixing map;(3)Letbe the hyperspace ofandbe a equivariant map. All non-empty open set are invariable for. Thenis a G-exact map if and only ifis a G-exact map. These results enriched the theory of the G-chain transitive and G-chain mixing on the hyperspace of topological group action. © 2020 IEEE.

关键词： Group theory

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：