2020 25th International Conference on Pattern Recognition (ICPR)最新文献_第6页

Temporal Pattern Detection in Time-Varying Graphical Models 时变图形模型中的时间模式检测

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9413203

Federico Tomasi, Veronica Tozzo, A. Barla

{"title":"Temporal Pattern Detection in Time-Varying Graphical Models","authors":"Federico Tomasi, Veronica Tozzo, A. Barla","doi":"10.1109/ICPR48806.2021.9413203","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9413203","url":null,"abstract":"Graphical models allow to describe the interplay among variables of a system through a compact representation, suitable when relations evolve over time. For example, in a biological setting, genes interact differently depending on external environmental or metabolic factors. To incorporate this dynamics a viable strategy is to estimate a sequence of temporally related graphs assuming similarity among samples in different time points. While adjacent time points may direct the analysis towards a robust estimate of the underlying graph, the resulting model will not incorporate long-term or recurrent temporal relationships. In this work we propose a dynamical network inference model that leverages on kernels to consider general temporal patterns (such as circadian rhythms or seasonality). We show how our approach may also be exploited when the recurrent patterns are unknown, by coupling the network inference with a clustering procedure that detects possibly non-consecutive similar networks. Such clusters are then used to build similarity kernels. The convexity of the functional is determined by whether we impose or infer the kernel. In the first case, the optimisation algorithm exploits efficiently proximity operators with closed-form solutions. In the other case, we resort to an alternating minimisation procedure which jointly learns the temporal kernel and the underlying network. Extensive analysis on synthetic data shows the efficacy of our models compared to state-of-the-art methods. Finally, we applied our approach on two realworld applications to show how considering long-term patterns is fundamental to have insights on the behaviour of a complex system.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"1993 1","pages":"4481-4488"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82388610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

DeepBEV: A Conditional Adversarial Network for Bird's Eye View Generation DeepBEV:一种用于鸟瞰生成的条件对抗网络

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412516

Helmi Fraser, Sen Wang

引用次数: 1

Rethinking ReID: Multi-Feature Fusion Person Re-identification Based on Orientation Constraints 基于取向约束的多特征融合人物再识别

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9413212

M. Ai, Guozhi Shan, Bo Liu, Tianyan Liu

{"title":"Rethinking ReID: Multi-Feature Fusion Person Re-identification Based on Orientation Constraints","authors":"M. Ai, Guozhi Shan, Bo Liu, Tianyan Liu","doi":"10.1109/ICPR48806.2021.9413212","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9413212","url":null,"abstract":"Person re-identification (ReID) aims to identify the specific pedestrian in a series of images or videos. Recently, ReID is receiving more and more attention in the fields of computer vision research and application like intelligent security. One major issue downgrading the ReID model performance lies in that various subjects in the same body orientations look too similar to distinguish by the model, while the same subject viewed in different orientations looks rather different. However, most of the current studies do not particularly differentiate pedestrians in orientation when designing the network, so we rethink this problem particularly from the perspective of person orientation and propose a new network structure by including two branches: one handling samples with the same body orientations and the other handling samples with different body orientations. Correspondingly, we also propose an orientation classifier that can accurately distinguish the orientation of each person. At the same time, the three-part loss functions are introduced for orientation constraint and combined to optimize the network simultaneously. Also, we use global and local features int the training stage in order to make use of multi-level information. Therefore, our network can derive its efficacy from orientation constraints and multiple features. Experiments show that our method not only has competitive performance on multiple datasets, but also can let retrieval results aligned with the orientation of the query sample rank higher, which may have great potential in the practical applications.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"89 1","pages":"1904-1911"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82261466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Recurrent-Convolutional Model for Automated Segmentation of Craniomaxillofacial CT Scans 颅颌面CT扫描自动分割的深度递归卷积模型

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9413084

Francesca Murabito, S. Palazzo, Federica Proietto Salanitri, F. Rundo, Ulas Bagci, D. Giordano, R. Leonardi, C. Spampinato

引用次数: 3

Attention Based Coupled Framework for Road and Pothole Segmentation 基于注意力的道路和坑洞分割耦合框架

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412368

Shaik Masihullah, Ritu Garg, Prerana Mukherjee, Anupama Ray

引用次数: 7

GAP: Quantifying the Generative Adversarial Set and Class Feature Applicability of Deep Neural Networks 量化深度神经网络的生成对抗集和类特征适用性

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412665

Edward Collier, S. Mukhopadhyay

引用次数: 2

Feature Extraction and Selection via Robust Discriminant Analysis and Class Sparsity 基于鲁棒判别分析和类稀疏性的特征提取与选择

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412683

A. Khoder, F. Dornaika

引用次数: 1

One step clustering based on a-contrario framework for detection of alterations in historical violins 基于反向框架的一步聚类检测历史小提琴的变化

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412129

Alireza Rezaei, S. L. Hégarat-Mascle, Emanuel Aldea, Piercarlo Dondi, M. Malagodi

{"title":"One step clustering based on a-contrario framework for detection of alterations in historical violins","authors":"Alireza Rezaei, S. L. Hégarat-Mascle, Emanuel Aldea, Piercarlo Dondi, M. Malagodi","doi":"10.1109/ICPR48806.2021.9412129","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412129","url":null,"abstract":"Preventive conservation is an important practice in Cultural Heritage. The constant monitoring of the state of conservation of an artwork helps us reduce the risk of damage and number of necessary interventions. In this work, we propose a probabilistic approach for the detection of alterations on the surface of historical violins based on an a-contrario framework. Our method is a one step NFA clustering solution which considers grey-level and spatial density information in one background model. The proposed method is robust to noise and avoids parameter tuning and any assumption about the quantity of the worn-out areas. We have used as input UV induced fluorescence (UVIFL) images for considering details not perceivable with visible light. Tests were conducted on image sequences included in the “Violins UVIFL imagery” dataset. Results illustrate the ability of the algorithm to distinguish the worn area from the surrounding regions. Comparisons with state-of-the-art clustering methods show improved overall precision and recall.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"69 1","pages":"9348-9355"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76531316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Hyperspectral Imaging for Analysis and Classification of Plastic Waste 塑料垃圾的高光谱成像分析与分类

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412737

Jakub Kraśniewski, Lukasz Dabala, M. Lewandowski

引用次数: 0

Classification of spatially enriched pixel time series with convolutional neural networks 基于卷积神经网络的空间丰富像素时间序列分类

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412892

Mohamed Chelali, Camille Kurtz, A. Puissant, N. Vincent

{"title":"Classification of spatially enriched pixel time series with convolutional neural networks","authors":"Mohamed Chelali, Camille Kurtz, A. Puissant, N. Vincent","doi":"10.1109/ICPR48806.2021.9412892","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412892","url":null,"abstract":"Satellite Image Time Series (SITS), MRI sequences, and more generally image time series, constitute $2D+t$ data providing spatial and temporal information about an observed scene. Given a pattern recognition task such as image classification, considering jointly such rich information is crucial during the decision process. Nevertheless, due to the complex representation of the data-cube, spatio-temporal features extraction from $2D+t$ data remains difficult to handle. We present in this article an approach to learn such features from this data, and then to proceed to their classification. Our strategy consists in enriching pixel time series with spatial information. It is based on Random Walk to build a novel segment-based representation of the data, passing from a $2D+t$ dimension to a $2D$ one, without loosing too much spatial information. Such new representation is then involved in an end-to-end learning process with a classical 2D Convolutional Neural Network (CNN) in order to learn spatiotemporal features for the classification of image time series. Our approach is evaluated on a remote sensing application for the mapping of agricultural crops. Thanks to a visual attention mechanism, the proposed $2D$ spatio-temporal representation makes also easier the interpretation of a SITS to understand spatiotemporal phenomenons related to soil management practices.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"4 1","pages":"5310-5317"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87487170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1