2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)最新文献

Incorporating Touch Biometrics to Mobile One-Time Passwords: Exploration of Digits 将触摸生物识别技术应用于移动一次性密码:数字探索

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00088

Rubén Tolosana, R. Vera-Rodríguez, Julian Fierrez, J. Ortega-Garcia

引用次数: 7

Geometry-Aware Traffic Flow Analysis by Detection and Tracking 基于检测与跟踪的几何感知交通流分析

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00023

Humphrey Shi

引用次数: 19

Recognizing American Sign Language Gestures from Within Continuous Videos 从连续视频中识别美国手语手势

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00280

Yuancheng Ye, Yingli Tian, Matt Huenerfauth, Jingya Liu

{"title":"Recognizing American Sign Language Gestures from Within Continuous Videos","authors":"Yuancheng Ye, Yingli Tian, Matt Huenerfauth, Jingya Liu","doi":"10.1109/CVPRW.2018.00280","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00280","url":null,"abstract":"In this paper, we propose a novel hybrid model, 3D recurrent convolutional neural networks (3DRCNN), to recognize American Sign Language (ASL) gestures and localize their temporal boundaries within continuous videos, by fusing multi-modality features. Our proposed 3DRCNN model integrates 3D convolutional neural network (3DCNN) and enhanced fully connected recurrent neural network (FC-RNN), where 3DCNN learns multi-modality features from RGB, motion, and depth channels, and FC-RNN captures the temporal information among short video clips divided from the original video. Consecutive clips with the same semantic meaning are singled out by applying the sliding window approach to segment the clips on the entire video sequence. To evaluate our method, we collected a new ASL dataset which contains two types of videos: Sequence videos (in which a human performs a list of specific ASL words) and Sentence videos (in which a human performs ASL sentences, containing multiple ASL words). The dataset is fully annotated for each semantic region (i.e. the time duration of each word that the human signer performs) and contains multiple input channels. Our proposed method achieves 69.2% accuracy on the Sequence videos for 27 ASL words, which demonstrates its effectiveness of detecting ASL gestures from continuous videos.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123435005","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: 58

Hierarchical Dictionary Learning and Sparse Coding for Static Signature Verification 用于静态签名验证的分层字典学习和稀疏编码

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00084

E. Zois, Marianna Papagiannopoulou, Dimitrios Tsourounis, G. Economou

{"title":"Hierarchical Dictionary Learning and Sparse Coding for Static Signature Verification","authors":"E. Zois, Marianna Papagiannopoulou, Dimitrios Tsourounis, G. Economou","doi":"10.1109/CVPRW.2018.00084","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00084","url":null,"abstract":"An assortment of review papers as well as newly quoted literature indicates that usually, the most important link in the chain of designing signature verification systems (SV's) is the feature extraction one. These methods are divided in two main categories. The first one, includes handcrafted features which are methods smanually engineered by scientists to be optimal for certain type of information extraction-summarization from signature images. Examples of this kind include global-local and/or grid-texture oriented features. The second feature category addresses signature modeling and verification with the use of dedicated features, usually learned directly from raw signature image data. Typical representatives include Deep Learning (DL) as well as Bag of Visual Words (BoW) or Histogram of Templates (HOT). Recently, sparse representation (SR) methods (dictionary learning and coding) have been introduced for signature modeling and verification with promising results. In this paper, we propose an extension of the SR framework by introducing the idea of embedding the atoms of a dictionary in a directed tree. This is demonstrated with an l0 tree-structured sparse regularization norm. The efficiency of the proposed method is shown by conducting experiments with two popular datasets namely the CEDAR and MCYT-75.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125315597","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: 16

Efficient Module Based Single Image Super Resolution for Multiple Problems 基于高效模块的多问题单图像超分辨率

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00133

Dongwon Park, Kwanyoung Kim, S. Chun

{"title":"Efficient Module Based Single Image Super Resolution for Multiple Problems","authors":"Dongwon Park, Kwanyoung Kim, S. Chun","doi":"10.1109/CVPRW.2018.00133","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00133","url":null,"abstract":"Example based single image super resolution (SR) is a fundamental task in computer vision. It is challenging, but recently, there have been significant performance improvements using deep learning approaches. In this article, we propose efficient module based single image SR networks (EMBSR) and tackle multiple SR problems in NTIRE 2018 SR challenge by recycling trained networks. Our proposed EMBSR allowed us to reduce training time with effectively deeper networks, to use modular ensemble for improved performance, and to separate subproblems for better performance. We also proposed EDSR-PP, an improved version of previous ESDR by incorporating pyramid pooling so that global as well as local context information can be utilized. Lastly, we proposed a novel denoising / deblurring residual convolutional network (DnResNet) using residual block and batch normalization. Our proposed EMBSR with DnResNet and EDSR-PP demonstrated that multiple SR problems can be tackled efficiently and effectively by winning the 2nd place for Track 2 (× 4 SR with mild adverse condition) and the 3rd place for Track 3 (×4 SR with difficult adverse condition). Our proposed method with EDSR-PP also achieved the ninth place for Track 1 (×8 SR) with the fastest run time among top nine teams.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125408495","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: 15

Detecting Presentation Attacks from 3D Face Masks Under Multispectral Imaging 基于多光谱成像的3D面具呈现攻击检测

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00014

Jun Liu, Ajay Kumar

引用次数: 17

An Online and Flexible Multi-object Tracking Framework Using Long Short-Term Memory 一种基于长短期记忆的在线灵活多目标跟踪框架

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00169

Xingyu Wan, Jinjun Wang, Sanping Zhou

引用次数: 22

Hybrid User-Independent and User-Dependent Offline Signature Verification with a Two-Channel CNN 基于双通道CNN的用户独立和用户依赖混合离线签名验证

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00094

M. Yilmaz, Kagan Ozturk

{"title":"Hybrid User-Independent and User-Dependent Offline Signature Verification with a Two-Channel CNN","authors":"M. Yilmaz, Kagan Ozturk","doi":"10.1109/CVPRW.2018.00094","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00094","url":null,"abstract":"Signature verification task needs relevant signature representations to achieve low error rates. Many signature representations have been proposed so far. In this work we propose a hybrid user-independent/dependent offline signature verification technique with a two-channel convolutional neural network (CNN) both for verification and feature extraction. Signature pairs are input to the CNN as two channels of one image, where the first channel always represents a reference signature and the second channel represents a query signature. We decrease the image size through the network by keeping the convolution stride parameter large enough. Global average pooling is applied to decrease the dimensionality to 200 at the end of locally connected layers. We utilize the CNN as a feature extractor and report 4.13% equal error rate (EER) considering 12 reference signatures with the proposed 200-dimensional representation, compared to 3.66% of a recently proposed technique with 2048-dimensional representation using the same experimental protocol. When the two methods are combined at score level, more than 50% improvement (1.76% EER) is achieved demonstrating the complementarity of them. Sensitivity of the model to gray-level and binary images is investigated in detail. One model is trained using gray-level images and the other is trained using binary images. It is shown that the availability of gray-level information in train and test data decreases the EER e.g. from 11.86% to 4.13%.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122867523","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: 36

Embodied Question Answering 具身问答

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00279

Abhishek Das, Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh, Dhruv Batra

引用次数: 0

Efficient and Safe Vehicle Navigation Based on Driver Behavior Classification 基于驾驶员行为分类的高效安全车辆导航

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00149

E. Cheung, Aniket Bera, Dinesh Manocha

引用次数: 23