2018 7th European Workshop on Visual Information Processing (EUVIP)最新文献_第5页

Automatic 3D Detection and Segmentation of Head and Neck Cancer from MRI Data 基于MRI数据的头颈部肿瘤自动三维检测与分割

2018 7th European Workshop on Visual Information Processing (EUVIP) Pub Date : 2018-09-20 DOI: 10.1109/EUVIP.2018.8611759

Baixiang Zhao, J. Soraghan, D. Grose, T. Doshi, G. D. Caterina

引用次数: 2

Classification of Building Information Model (BIM) Structures with Deep Learning 基于深度学习的建筑信息模型结构分类

2018 7th European Workshop on Visual Information Processing (EUVIP) Pub Date : 2018-08-01 DOI: 10.1109/EUVIP.2018.8611701

Francesco Lomio, Ricardo J. P. C. Farinha, M. Laasonen, H. Huttunen

引用次数: 13

Embedded Implementation of a Deep Learning Smile Detector 深度学习微笑检测器的嵌入式实现

2018 7th European Workshop on Visual Information Processing (EUVIP) Pub Date : 2018-07-10 DOI: 10.1109/EUVIP.2018.8611783

Pedram Ghazi, A. Happonen, J. Boutellier, H. Huttunen

引用次数: 6

Faster Bounding Box Annotation for Object Detection in Indoor Scenes 室内场景中更快的目标检测边界框标注

2018 7th European Workshop on Visual Information Processing (EUVIP) Pub Date : 2018-07-03 DOI: 10.1109/EUVIP.2018.8611732

Bishwo Adhikari, Jukka Peltomäki, Jussi Puura, H. Huttunen

引用次数: 34

Saliency Enhanced Robust Visual Tracking 显著增强鲁棒视觉跟踪

2018 7th European Workshop on Visual Information Processing (EUVIP) Pub Date : 2018-02-08 DOI: 10.1109/EUVIP.2018.8611706

Çağlar Aytekin, Francesco Cricri, Emre B. Aksu

{"title":"Saliency Enhanced Robust Visual Tracking","authors":"Çağlar Aytekin, Francesco Cricri, Emre B. Aksu","doi":"10.1109/EUVIP.2018.8611706","DOIUrl":"https://doi.org/10.1109/EUVIP.2018.8611706","url":null,"abstract":"Discrete correlation filter (DCF) based trackers have shown considerable success in visual object tracking. These trackers often make use of low to mid level features such as histogram of gradients (HoG) and mid-layer activations from convolution neural networks (CNNs). We argue that including semantically higher level information to the tracked features may provide further robustness to challenging cases such as viewpoint changes. Deep salient object detection is one example of such high level features, as it make use of semantic information to highlight the important regions in the given scene. In this work, we propose an improvement over DCF based trackers by combining saliency based and other features based filter responses. This combination is performed with an adaptive weight on the saliency based filter responses, which is automatically selected according to the temporal consistency of visual saliency. We show that our method consistently improves a baseline DCF based tracker especially in challenging cases and performs superior to the state-of-the-art. Our improved tracker operates at 9.3 fps, introducing a small computational burden over the baseline which operates at 11 fps.","PeriodicalId":252212,"journal":{"name":"2018 7th European Workshop on Visual Information Processing (EUVIP)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133698648","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: 8