liu.seSök publikationer i DiVA
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Two-Stream Part-based Deep Representation for Human Attribute Recognition
Aalto Univ, Finland.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Aalto Univ, Finland.
2018 (Engelska)Ingår i: 2018 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB), IEEE , 2018, s. 90-97Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Recognizing human attributes in unconstrained environments is a challenging computer vision problem. State-of-the-art approaches to human attribute recognition are based on convolutional neural networks (CNNs). The de facto practice when training these CNNs on a large labeled image dataset is to take RGB pixel values of an image as input to the network. In this work, we propose a two-stream part-based deep representation for human attribute classification. Besides the standard RGB stream, we train a deep network by using mapped coded images with explicit texture information, that complements the standard RGB deep model. To integrate human body parts knowledge, we employ the deformable part-based models together with our two-stream deep model. Experiments are performed on the challenging Human Attributes (HAT-27) Dataset consisting of 27 different human attributes. Our results clearly show that (a) the two-stream deep network provides consistent gain in performance over the standard RGB model and (b) that the attribute classification results are further improved with our two-stream part-based deep representations, leading to state-of-the-art results.

Ort, förlag, år, upplaga, sidor
IEEE , 2018. s. 90-97
Serie
International Conference on Biometrics, ISSN 2376-4201
Nyckelord [en]
Deep learning; Human attribute recognition; Part-based representation
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Identifikatorer
URN: urn:nbn:se:liu:diva-152842DOI: 10.1109/ICB2018.2018.00024ISI: 000449428100013ISBN: 978-1-5386-4285-6 (tryckt)OAI: oai:DiVA.org:liu-152842DiVA, id: diva2:1265191
Konferens
11th IAPR International Conference on Biometrics (ICB)
Anmärkning

Funding Agencies|Academy of Finland [251170]; H2020-ICT project MeMAD [780069]; VR starting grant [2016-05543]; Nvidia; SSF

Tillgänglig från: 2018-11-22 Skapad: 2018-11-22 Senast uppdaterad: 2018-11-22

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Sök vidare i DiVA

Av författaren/redaktören
Khan, Fahad
Av organisationen
DatorseendeTekniska fakulteten
Datorseende och robotik (autonoma system)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 150 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf