Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Video Saliency Detection using Deep Learning
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Hitta fokuspunkter i video med neurala nätverk (English)
Abstract [en]

A deep learning model for video saliency detection is proposed and trained. The neural network architecture combines recent innovations in the field: A twostream approach merges two separate input streams for appearance and motion aspects of saliency. Pre-trained convolutional features detect objectness. Attention modules are employed to efficiently reweight features. A ConvLSTM module ensures temporal consistency. Training data comprises both videos and images with corresponding gaze fixation locations from eye trackers. The model is evaluated and shown to perform on par with the state of the art.

Abstract [sv]

En deep learning-modell designas för att detektera fokuspunkter i video, dvs. förutspå vart människor kommer att rikta sin blick. Det neurala nätverkets arkitektur kombinerar flera innovationer inom fältet: två inputströmmar modellerar utseende och rörelse separat. Förtränad feature extraction detekterar objekt. Residual attention-moduler viktar om features. En ConvLSTM-modul säkerställer tidsmässig stabilitet i detektionen. Träningsdata består av både videoklipp och bilder, båda med motsvarande ögonfixeringsdata från eye trackers. Modellen utvärderas och visas prestera i klass med senaste forskningen.

Place, publisher, year, edition, pages
2019. , p. 50
Series
TRITA-EECS-EX ; 2019:87
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-251657OAI: oai:DiVA.org:kth-251657DiVA, id: diva2:1316346
Supervisors
Examiners
Available from: 2019-05-24 Created: 2019-05-17 Last updated: 2019-05-24Bibliographically approved

Open Access in DiVA

fulltext(2661 kB)48 downloads
File information
File name FULLTEXT01.pdfFile size 2661 kBChecksum SHA-512
34f267b4f16637720b4cb33be75797ba33b63ec77487b8b415a46510be8f7e2ed12dd816fc9f287440a99cc05b6edf9dd87075d7e34afcff1504beb02209dfcc
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 48 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 143 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf