2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)最新文献_第10页

Unsupervised Long-Term Routine Modelling Using Dynamic Bayesian Networks 基于动态贝叶斯网络的无监督长期例程建模

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227502

Yangdi Xu, David Bull, D. Damen

{"title":"Unsupervised Long-Term Routine Modelling Using Dynamic Bayesian Networks","authors":"Yangdi Xu, David Bull, D. Damen","doi":"10.1109/DICTA.2017.8227502","DOIUrl":"https://doi.org/10.1109/DICTA.2017.8227502","url":null,"abstract":"Routine can be defined as the frequent and regular activity patterns over a specified timescale (e.g. daily/weekly routine). In this work, we capture routine patterns for a single person from long- term visual data using a Dynamic Bayesian Network (DBN). Assuming a person always performs purposeful activities at corresponding locations; spatial, pose and time-of-day information are used as sources of input for routine modelling. We assess variations of the independence assumptions within the DBN model among selected features. Unlike traditional models that are supervisedly trained, we automatically select the number of hidden states for fully unsupervised discovery of a single person's indoor routine. We emphasize unsupervised learning as it is practically unrealistic to obtain ground-truth labels for long term behaviours. The datasets used in this work are long term recordings of non-scripted activities in their native environments, each lasting for six days. The first captures the routine of three individuals in an office kitchen; the second is recorded in a residential kitchen. We evaluate the routine by comparing to ground-truth when present, using exhaustive search to relate discovered patterns to ground-truth ones. We also propose a graphical visualisation to represent and qualitatively evaluate the discovered routine.","PeriodicalId":194175,"journal":{"name":"2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","volume":"72 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131137391","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

Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking 基于学习方差核相关滤波器的鲁棒视觉目标跟踪

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227458

Chenghuan Liu, D. Huynh, Mark Reynolds

引用次数: 0

Judging Aesthetic Quality in Paintings Based on Artistic Inspired Color Features 从艺术灵感色彩特征判断绘画的审美品质

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227452

S. A. Amirshahi, Joachim Denzler

引用次数: 5

Multi-Feature Kernel Discriminant Dictionary Learning for Classification in Alzheimer's Disease 多特征核判别字典学习在阿尔茨海默病分类中的应用

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227467

Qing Li, Xia Wu, Lele Xu, L. Yao, Kewei Chen

引用次数: 1

HOSO: Histogram of Surface Orientation for RGB-D Salient Object Detection 面向RGB-D显著目标检测的表面方向直方图

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227440

David Feng, N. Barnes, Shaodi You

引用次数: 6

Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics 快速鲁棒的三维膝关节运动学多模态图像配准

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227434

Shabnam Saadat, M. Pickering, D. Perriman, J. Scarvell, Paul N. Smith

引用次数: 10

Deformable and Occluded Object Tracking via Graph Learning 基于图学习的可变形和遮挡对象跟踪

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227424

Wei Han, G. Huang, Dongshun Cui

引用次数: 0

Ubiquitous Document Capturing with Deep Learning 泛在文档捕获与深度学习

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227501

T. Naz, A. A. Khan, F. Shafait

引用次数: 0

Hyper-Feature Based Tracking with the Fully-Convolutional Siamese Network 基于超特征的全卷积Siamese网络跟踪

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227442

Yangliu Kuai, G. Wen, Dongdong Li

{"title":"Hyper-Feature Based Tracking with the Fully-Convolutional Siamese Network","authors":"Yangliu Kuai, G. Wen, Dongdong Li","doi":"10.1109/DICTA.2017.8227442","DOIUrl":"https://doi.org/10.1109/DICTA.2017.8227442","url":null,"abstract":"Convolutional neural network (CNN) has drawn increasing interest in visual tracking, among which fully-convolutional Siamese network based method (SiamFC) is quite popular due to its competitive performance in both precision and efficiency. Generally, SiamFC captures robust semantics from high-level features in the last layer but ignores detailed spatial features in earlier layers, thus tending to drift towards similar target regions in the search area. In this paper, we design a skip-layer connection network on the basis of SiamFC to aggregate hierarchical feature maps and constitute the hyper- feature representations of target, considering that convolutional layers in different levels characterize target from different perspectives and the lower-level feature maps of SiamFC is computed beforehand. The Hyper-features well incorporate deep but highly semantic, intermediate but really complementary, and shallow but naturally high-resolution representations. The designed network is trained end-to-end offline similar to SiamFC on the ILSVRC2015 dataset and later used for online tracking. Experimental results on OTB benchmark show that the proposed algorithm performs favourably against many state-of-the-art trackers in terms of accuracy while maintaining real-time tracking speed.","PeriodicalId":194175,"journal":{"name":"2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115262866","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

Double-Guided Filtering: Image Smoothing with Structure and Texture Guidance 双导滤波:图像平滑与结构和纹理指导

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2017-11-01 DOI: 10.1109/DICTA.2017.8227425

Kaiyue Lu, Shaodi You, N. Barnes

{"title":"Double-Guided Filtering: Image Smoothing with Structure and Texture Guidance","authors":"Kaiyue Lu, Shaodi You, N. Barnes","doi":"10.1109/DICTA.2017.8227425","DOIUrl":"https://doi.org/10.1109/DICTA.2017.8227425","url":null,"abstract":"Image smoothing is a fundamental technology which aims to preserve image structure and remove insignificant texture. Balancing the trade-off between preserving structure and suppressing texture, however, is not a trivial task. This is because existing methods rely on only one guidance to infer structure or texture and assume the other is dependent. However, in many cases, textures are composed of repetitive structures and difficult to be distinguished by only one guidance. In this paper, we aim to better solve the trade-off by applying two independent guidance for structure and texture. Specifically, we adopt semantic edge detection as structure guidance, and texture decomposition as texture guidance. Based on this, we propose a kernel-based image smoothing method called the double-guided filter (DGF). In the paper, for the first time, we introduce the concept of texture guidance, and DGF, the first kernel- based method that leverages structure and texture guidance at the same time to be both 'structure- aware' and 'texture-aware'. We present a number of experiments to show the effectiveness of the proposed filter.","PeriodicalId":194175,"journal":{"name":"2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","volume":"51 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114129019","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: 4