English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Body Shape Privacy in Images: Understanding Privacy and Preventing Automatic Shape Extraction

Sattar, H., Krombholz, K., Pons-Moll, G., & Fritz, M. (2021). Body Shape Privacy in Images: Understanding Privacy and Preventing Automatic Shape Extraction. In A. Bartoli, & A. Fusiello (Eds.), Computer Vision -- ECCV Workshops 2020 (pp. 411-428). Berlin: Springer. doi:10.1007/978-3-030-68238-5_31.

Item is

Basic

show hide
Genre: Conference Paper
Latex : Body Shape Privacy in Images: {U}nderstanding Privacy and Preventing Automatic Shape Extraction

Files

show Files
hide Files
:
arXiv:1905.11503.pdf (Preprint), 13MB
 
File Permalink:
-
Name:
arXiv:1905.11503.pdf
Description:
File downloaded from arXiv at 2021-01-27 13:35 Proc. of the IEEE European Conference on Computer Vision Workshops (ECCVW), CV-COPS@ECCV2020
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Sattar, Hosnieh1, Author           
Krombholz, Katharina2, Author
Pons-Moll, Gerard1, Author           
Fritz, Mario2, Author           
Affiliations:
1Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Artificial Intelligence, cs.AI,Computer Science, Cryptography and Security, cs.CR,Computer Science, Learning, cs.LG
 Abstract: Modern approaches to pose and body shape estimation have recently achieved
strong performance even under challenging real-world conditions. Even from a
single image of a clothed person, a realistic looking body shape can be
inferred that captures a users' weight group and body shape type well. This
opens up a whole spectrum of applications -- in particular in fashion -- where
virtual try-on and recommendation systems can make use of these new and
automatized cues. However, a realistic depiction of the undressed body is
regarded highly private and therefore might not be consented by most people.
Hence, we ask if the automatic extraction of such information can be
effectively evaded. While adversarial perturbations have been shown to be
effective for manipulating the output of machine learning models -- in
particular, end-to-end deep learning approaches -- state of the art shape
estimation methods are composed of multiple stages. We perform the first
investigation of different strategies that can be used to effectively
manipulate the automatic shape estimation while preserving the overall
appearance of the original image.

Details

show
hide
Language(s): eng - English
 Dates: 2019-05-272020-10-222021
 Publication Status: Published online
 Pages: 33 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Sattar_ECCV20
DOI: 10.1007/978-3-030-68238-5_31
 Degree: -

Event

show
hide
Title: 16th European Conference on Compute Vision
Place of Event: Glasgow, UK
Start-/End Date: 2020-08-23 - 2020-08-28

Legal Case

show

Project information

show

Source 1

show
hide
Title: Computer Vision -- ECCV Workshops 2020
  Abbreviation : ECCV 2020
  Subtitle : Glasgow, UK, August 23–28, 2020 ; Proceedings, Part V
Source Genre: Proceedings
 Creator(s):
Bartoli, Adrien1, Editor
Fusiello, Andrea1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Berlin : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 411 - 428 Identifier: ISBN: 978-3-030-68237-8

Source 2

show
hide
Title: Lecture Notes in Computer Science
  Abbreviation : LNCS
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 12539 Sequence Number: - Start / End Page: - Identifier: -