liu.seSearch for publications in DiVA
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Deep motion features for visual tracking
Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för systemteknik, Datorseende.
Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för systemteknik, Datorseende.
Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för systemteknik, Datorseende.
Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för systemteknik, Datorseende.ORCID-id: 0000-0002-6096-3648
2016 (engelsk)Inngår i: Proceedings of the 23rd International Conference on, Pattern Recognition (ICPR), 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, s. 1243-1248Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Robust visual tracking is a challenging computer vision problem, with many real-world applications. Most existing approaches employ hand-crafted appearance features, such as HOG or Color Names. Recently, deep RGB features extracted from convolutional neural networks have been successfully applied for tracking. Despite their success, these features only capture appearance information. On the other hand, motion cues provide discriminative and complementary information that can improve tracking performance. Contrary to visual tracking, deep motion features have been successfully applied for action recognition and video classification tasks. Typically, the motion features are learned by training a CNN on optical flow images extracted from large amounts of labeled videos. This paper presents an investigation of the impact of deep motion features in a tracking-by-detection framework. We further show that hand-crafted, deep RGB, and deep motion features contain complementary information. To the best of our knowledge, we are the first to propose fusing appearance information with deep motion features for visual tracking. Comprehensive experiments clearly suggest that our fusion approach with deep motion features outperforms standard methods relying on appearance information alone.

sted, utgiver, år, opplag, sider
Institute of Electrical and Electronics Engineers (IEEE), 2016. s. 1243-1248
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-137896DOI: 10.1109/ICPR.2016.7899807ISI: 000406771301042Scopus ID: 2-s2.0-85019098606ISBN: 9781509048472 (digital)ISBN: 9781509048489 (tryckt)OAI: oai:DiVA.org:liu-137896DiVA, id: diva2:1104308
Konferanse
The 23rd International Conference on, Pattern Recognition (ICPR), Cancun, Mexico, 4-8 Dec. 2016
Tilgjengelig fra: 2017-05-31 Laget: 2017-05-31 Sist oppdatert: 2018-10-16bibliografisk kontrollert

Open Access i DiVA

fulltext(1805 kB)69 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 1805 kBChecksum SHA-512
9bb1a5b1bc3b7239cb858fa19b4ee9e7abcacd157cf2815bb2a83bea9048894a5b05e4187d62d5013b64526568974592c2b4d88c72f663444d25ed9077baf833
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Danelljan, MartinKhan, Fahad ShahbazFelsberg, Michael

Søk i DiVA

Av forfatter/redaktør
Danelljan, MartinKhan, Fahad ShahbazFelsberg, Michael
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 69 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 422 treff
RefereraExporteraLink to record
Permanent link

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