VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People

被引：63

作者：

Gurari, Danna ^{[1
]}

Li, Qing ^{[2
]}

Lin, Chi ^{[1
]}

Zhao, Yinan ^{[1
]}

Guo, Anhong ^{[3
]}

Stangl, Abigale ^{[4
]}

Bigham, Jeffrey P. ^{[3
]}

机构：

[1] Univ Texas Austin, Austin, TX 78712 USA

[2] Univ Calif Los Angeles, Los Angeles, CA 90024 USA

[3] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA

[4] Univ Colorado, Boulder, CO 80309 USA

来源：

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) | 2019年

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/CVPR.2019.00103

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We introduce the first visual privacy dataset originating from people who are blind in order to better understand their privacy disclosures and to encourage the development of algorithms that can assist in preventing their unintended disclosures. It includes 8,862 regions showing private content across 5,537 images taken by blind people. Of these, 1,403 are paired with questions and 62% of those directly ask about the private content. Experiments demonstrate the utility of this data for predicting whether an image shows private information and whether a question asks about the private content in an image. The dataset is publicly-shared at http://vizwiz.org/data/.

引用

页码：939 / 948

页数：10

共 49 条

[41]

World Health Organization, 2012, GLOB DAT VIS IMP 201

[42] Automatic Alt-text: Computer-generated Image Descriptions for Blind Users on a Social Network Service [J].

Wu, Shaomei ;

Wieland, Jeffrey ;

Farivar, Omid ;

Schiller, Julie .

CSCW'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK AND SOCIAL COMPUTING, 2017, :1180-1192

[43]

Xiao JX, 2010, PROC CVPR IEEE, P3485, DOI 10.1109/CVPR.2010.5539970

[44] Leveraging Content Sensitiveness and User Trustworthiness to Recommend Fine-Grained Privacy Settings for Social Image Sharing [J].

Yu, Jun ;

Kuang, Zhenzhong ;

Zhang, Baopeng ;

Zhang, Wei ;

Lin, Dan ;

Fan, Jianping .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2018, 13 (05) :1317-1332

[45] Visual Madlibs: Fill in the blank Description Generation and Question Answering [J].

Yu, Licheng ;

Park, Eunbyung ;

Berg, Alexander C. ;

Berg, Tamara L. .

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :2461-2469

[46]

Zerr S, 2012, SIGIR 2012: PROCEEDINGS OF THE 35TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, P35, DOI 10.1145/2348283.2348292

[47] Guided Image Inpainting: Replacing an Image Region by Pulling Content from Another Image [J].

Zhao, Yinan ;

Price, Brian ;

Cohen, Scott ;

Gurari, Danna .

2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, :1514-1523

[48]

Zhong Y., 2013, P 15 INT ACM SIGACCE, DOI [DOI 10.1145/2513383.2513443, 10.1145/2513383.2513443]

[49] RegionSpeak: Quick Comprehensive Spatial Descriptions of Complex Images for Blind Users [J].

Zhong, Yu ;

Lasecki, Walter S. ;

Brady, Erin ;

Bigham, Jeffrey P. .

CHI 2015: PROCEEDINGS OF THE 33RD ANNUAL CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, 2015, :2353-2362

← 1 2 3 4 5 →