检索结果-内蒙古大学图书馆

Hierarchical taxonomy-aware and attentional graph capsule RCNNs for large-scale multi-label text classification

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Peng, Hao Li, Jianxin Gong, Qiran Wang, Senzhang He, Lifang Li, Bo Wang, Lihong Yu, Philip S. Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 State Key Laboratory of Software Development Environment Beihang University Beijing100083 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Department of Biostatistics and Epidemiology University of Pennsylvania PhiladelphiaPA19104 United States National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100029 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance semantics or the sequential semantics, but how to consider them both coherently is less studied. In addition, most existing methods treat output labels as independent medoids, but ignore the hierarchical relations among them, leading to useful semantic information loss. In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification. Specifically, we first propose to model each document as a word order preserved graph-of-words and normalize it as a corresponding words-matrix representation which preserves both the non-consecutive, long-distance and local sequential semantics. Then the words-matrix is input to the proposed attentional graph capsule recurrent CNNs for more effectively learning the semantic features. To leverage the hierarchical relations among the class labels, we propose a hierarchical taxonomy embedding method to learn their representations, and define a novel weighted margin loss by incorporating the label representation similarity. Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

Feature map pooling for cross-view gait recognition based on silhouette sequence images

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Chen, Qiang Wang, Yunhong Liu, Zheng Liu, Qingjie Huang, Di Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

In this paper, we develop a novel convolutional neural network based approach to extract and aggregate useful information from gait silhouette sequence images instead of simply representing the gait process by averaging silhouette images. The network takes a pair of arbitrary length sequence images as inputs and extracts features for each silhouette independently. Then a feature map pooling strategy is adopted to aggregate sequence features. Subsequently, a network which is similar to Siamese network is designed to perform recognition. The proposed network is simple and easy to implement and can be trained in an end-to-end manner. Cross-view gait recognition experiments are conducted on OU-ISIR large population dataset. The results demonstrate that our network can extract and aggregate features from silhouette sequence effectively. It also achieves significant equal error rates and comparable identification rates when compared with the state of the art. Copyright © 2017, The Authors. All rights reserved.

关键词： Gait analysis

Receptive field block net for accurate and fast object detection

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Liu, Songtao Huang, Di Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their pow- erful feature representations but suffering from high computational costs. Conversely, some lightweight model based detectors fulfil real time pro- cessing, while their accuracies are often criticized. In this paper, we ex- plore an alternative to build a fast and accurate detector by strengthen- ing lightweight features using a hand-crafted mechanism. Inspired by the structure of Receptive Fields (RFs) in human visual systems, we propose a novel RF Block (RFB) module, which takes the relationship between the size and eccentricity of RFs into account, to enhance the feature discriminability and robustness. We further assemble RFB to the top of SSD, constructing the RFB Net detector. To evaluate its effectiveness, experiments are conducted on two major benchmarks and the results show that RFB Net is able to reach the performance of advanced very deep detectors while keeping the real-time speed. Code is available at https://***/ruinmessi/RFBNet. Copyright © 2017, The Authors. All rights reserved.

关键词： Object detection

A Parametric Time Frequency-Conditional Granger Causality Method Using Ultra-regularized Orthogonal Least Squares and Multiwavelets for Dynamic Connectivity Analysis in EEGs

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Yang Lei, Mengying Cui, Weigang Guo, Yuzhu Wei, Hua-Liang Department of Automation Sciences and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Advanced Innovation Center for Big Date-based Precision Medicine Beihang University Beijing China Department of Automation Sciences and Electrical Engineering Beihang University Beijing China Department of Automatic Control and Systems Engineering University of Sheffield SheffieldS1 3DJ United Kingdom

— Objective: This study proposes a new parametric TF (time-frequency)-CGC (conditional Granger causality) method for high-precision connectivity analysis over time and frequency in multivariate coupling nonstationary systems, and applies it to scalp and source EEG signals to reveal dynamic interaction patterns in oscillatory neocortical sensorimotor networks. Methods: The Geweke’s spectral measure is combined with the TVARX (time-varying autoregressive with exogenous input) modelling approach, which uses multiwavelets and ultra-regularized orthogonal least squares (UROLS) algorithm aided by APRESS (adjustable prediction error sum of squares), to obtain high-resolution time-varying CGC representations. The UROLS-APRESS algorithm, which adopts both the regularization technique and the ultra-least squares criterion to measure not only the signal data themselves but also the weak derivatives of them, is a novel powerful method in constructing time-varying models with good generalization performance, and can accurately track smooth and fast changing causalities. The generalized measurement based on CGC decomposition is able to eliminate indirect influences in multivariate systems. Results: The proposed method is validated on two simulations and then applied to multichannel motor imagery (MI)-EEG signals at scalp- and source-level, where the predicted distributions are well recovered with high TF precision, and the detected connectivity patterns of MI-EEG data are physiologically and anatomically interpretable and yield new insights into the dynamical organization of oscillatory cortical networks. Conclusion: Experimental results confirm the effectiveness of the proposed TF-CGC method in tracking rapidly varying causalities of EEG-based oscillatory networks. Significance: The novel TF-CGC method is expected to provide important information of neural mechanisms of perception and cognition. Copyright © 2018, The Authors. All rights reserved.

关键词： Statistical tests

Inland port location planning based on user equilibrium 17

学校读者我要写书评

暂无评论

Inland port location planning based on user equilibrium

17th COTA International Conference of Transportation Professionals: Transportation Reform and Change - Equity, Inclusiveness, Sharing, and Innovation, CICTP 2017

作者： Wei, Jingyi Tian, Daxin Rong, Hui Guo, Peng Wang, Wenyang Gong, Jinfeng Wang, Yunpeng Liu, He Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang Univ. Beijing100191 China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang Univ. Beijing100191 China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Nanjing210096 China Automotive Engineering Research Institute China Automotive Technology and Research Center Tianjin300300 China Quartermaster Equipment Institute of the General Logistics Dept. Of CPLA Beijing100010 China

ISBN: (数字)9780784480915

ISBN: (纸本)9780784480915

With stable development of container transportation in shipping industry, the transit shipment from road to railway of inland ports plays a significant role in multimodal transport. This paper presents the method of inland port location planning based on user equilibrium. In the study, the virtual connection simulating the process of transfer in inland ports is conducted to measure the fitness of inland port location through the cargo volume on virtual connection. At last, the methodology was applied into practical experiment with the results showing that the method can locate the suit inland port location. © ASCE.

关键词： Location

Diabetic foot ulcers segmentation challenge report: Benchmark and analysis

学校读者我要写书评

暂无评论

Medical image analysis 2024年 94卷 103153页

作者： Moi Hoon Yap Bill Cassidy Michal Byra Ting-Yu Liao Huahui Yi Adrian Galdran Yung-Han Chen Raphael Brüngel Sven Koitka Christoph M Friedrich Yu-Wen Lo Ching-Hui Yang Kang Li Qicheng Lao Miguel A González Ballester Gustavo Carneiro Yi-Jen Ju Juinn-Dar Huang Joseph M Pappachan Neil D Reeves Vishnu Chandrabalan Darren Dancey Connah Kendrick Department of Computing and Mathematics Manchester Metropolitan University John Dalton Building Chester Street Manchester M1 5GD United Kingdom Lancashire Teaching Hospitals NHS Trust Preston PR2 9HT United Kingdom. Electronic address: m.yap@mmu.ac.uk. Department of Computing and Mathematics Manchester Metropolitan University John Dalton Building Chester Street Manchester M1 5GD United Kingdom. Institute of Fundamental Technological Research Polish Academy of Sciences Warsaw Poland RIKEN Center for Brain Science Wako Japan. Department of Computer Science National Tsing Hua University No. 101 Section 2 Kuang-Fu Road Hsinchu Taiwan. West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu China. BCN Medtech Universitat Pompeu Fabra Barcelona Spain AIML University of Adelaide Australia. Institute of Electronics National Yang Ming Chiao Tung University No. 1001 University Road Hsinchu 300 Taiwan. Department of Computer Science University of Applied Sciences and Arts Dortmund (FH Dortmund) Emil-Figge-Str. 42 44227 Dortmund Germany Institute for Medical Informatics Biometry and Epidemiology (IMIBE) University Hospital Essen Zweigertstr. 37 45130 Essen Germany Institute for Artificial Intelligence in Medicine (IKIM) University Hospital Essen Girardetstr. 2 45131 Essen Germany. Institute for Artificial Intelligence in Medicine (IKIM) University Hospital Essen Girardetstr. 2 45131 Essen Germany Institute of Diagnostic and Interventional Radiology and Neuroradiology University Hospital Essen Hufelandstr. 55 45147 Essen Germany. Institute for Medical Informatics Biometry and Epidemiology (IMIBE) University Hospital Essen Zweigertstr. 37 45130 Essen Germany. West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu China Shanghai Artificial Intelligence Laboratory Shanghai China. School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China BCN Medtech Universit

Monitoring the healing progress of diabetic foot ulcers is a challenging process. Accurate segmentation of foot ulcers can help podiatrists to quantitatively measure the size of wound regions to assist prediction of healing status. The main challenge in this field is the lack of publicly available manual delineation, which can be time consuming and laborious. Recently, methods based on deep learning have shown excellent results in automatic segmentation of medical images, however, they require large-scale datasets for training, and there is limited consensus on which methods perform the best. The 2022 Diabetic Foot Ulcers segmentation challenge was held in conjunction with the 2022 International Conference on Medical Image computing and Computer Assisted Intervention, which sought to address these issues and stimulate progress in this research domain. A training set of 2000 images exhibiting diabetic foot ulcers was released with corresponding segmentation ground truth masks. Of the 72 (approved) requests from 47 countries, 26 teams used this data to develop fully automated systems to predict the true segmentation masks on a test set of 2000 images, with the corresponding ground truth segmentation masks kept private. Predictions from participating teams were scored and ranked according to their average Dice similarity coefficient of the ground truth masks and prediction masks. The winning team achieved a Dice of 0.7287 for diabetic foot ulcer segmentation. This challenge has now entered a live leaderboard stage where it serves as a challenging benchmark for diabetic foot ulcer segmentation.

关键词： Convolutional neural networks Deep learning Diabetic foot ulcers Metrics Segmentation

Forecasting transportation network speed using deep capsule networks with nested LSTM models

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Ma, Xiaolei Li, Yi Cui, Zhiyong Wang, Yinhai School of Transportation Science and Engineering Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Department of Civil and Environmental Engineering University of Washington Seattle98195 United States

Accurate and reliable traffic forecasting for complicated transportation networks is of vital importance to modern transportation management. The complicated spatial dependencies of roadway links and the dynamic temporal patterns of traffic states make it particularly challenging. To address these challenges, we propose a new capsule network (CapsNet) to extract the spatial features of traffic networks and utilize a nested LSTM (NLSTM) structure to capture the hierarchical temporal dependencies in traffic sequence data. A framework for network-level traffic forecasting is also proposed by sequentially connecting CapsNet and NLSTM. On the basis of literature review, our study is the first to adopt CapsNet and NLSTM in the field of traffic forecasting. An experiment on a Beijing transportation network with 278 links shows that the proposed framework with the capability of capturing complicated spatiotemporal traffic patterns outperforms multiple state-of-the-art traffic forecasting baseline models. The superiority and feasibility of CapsNet and NLSTM are also demonstrated, respectively, by visualizing and quantitatively evaluating the experimental results. Copyright © 2018, The Authors. All rights reserved.

关键词： Long short-term memory

Learning face age progression: A pyramid architecture of GANs

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yang, Hongyu Huang, Di Wang, Yunhong Jain, Anil K. Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China Michigan State University United States

The two underlying requirements of face age progression, i.e. aging accuracy and identity permanence, are not well studied in the literature. In this paper, we present a novel generative adversarial network based approach. It separately models the constraints for the intrinsic subject-specific characteristics and the age-specific facial changes with respect to the elapsed time, ensuring that the generated faces present desired aging effects while simultaneously keeping personalized properties stable. Further, to generate more lifelike facial details, high-level age-specific features conveyed by the synthesized face are estimated by a pyramidal adversarial discriminator at multiple scales, which simulates the aging effects in a finer manner. The proposed method is applicable to diverse face samples in the presence of variations in pose, expression, makeup, etc., and remarkably vivid aging effects are achieved. Both visual fidelity and quantitative evaluations show that the approach advances the state-of-the-art. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

One-pass error bounded trajectory simplification

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Lin, Xuelian Ma, Shuai Zhang, Han Wo, Tianyu Huai, Jinpeng SKLSDE Lab Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China

Nowadays, various sensors are collecting, storing and transmitting tremendous trajectory data, and it is known that raw trajectory data seriously wastes the storage, network band and computing resource. Line simplification (LS) algorithms are an effective approach to attacking this issue by compressing data points in a trajectory to a set of continuous line segments, and are commonly used in practice. However, existing LS algorithms are not sufficient for the needs of sensors in mobile devices. In this study, we first develop a one-pass error bounded trajectory simplification algorithm (OPERB), which scans each data point in a trajectory once and only once. We then propose an aggressive one-pass error bounded trajectory simplification algorithm (OPERB-A), which allows interpolating new data points into a trajectory under certain conditions. Finally, we experimentally verify that our approaches (OPERB and OPERB-A) are both efficient and effective, using four real-life trajectory datasets. Copyright © 2017, The Authors. All rights reserved.

关键词： Trajectories