English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches

Sattar, H., Krombholz, K., Pons-Moll, G., & Fritz, M. (2019). Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches. Retrieved from http://arxiv.org/abs/1905.11503.

Item is

Files

show Files
hide Files
:
arXiv:1905.11503.pdf (Preprint), 7MB
Name:
arXiv:1905.11503.pdf
Description:
File downloaded from arXiv at 2019-06-03 09:03
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
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: 2019-05-272019
 Publication Status: Published online
 Pages: 10 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1905.11503
URI: http://arxiv.org/abs/1905.11503
BibTex Citekey: Sattar_arXiv1905.11503
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show