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
Unveiling the power of deep tracking
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Vise andre og tillknytning
2018 (engelsk)Inngår i: Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part II / [ed] Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu and Yair Weiss, Cham: Springer Publishing Company, 2018, s. 493-509Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

In the field of generic object tracking numerous attempts have been made to exploit deep features. Despite all expectations, deep trackers are yet to reach an outstanding level of performance compared to methods solely based on handcrafted features. In this paper, we investigate this key issue and propose an approach to unlock the true potential of deep features for tracking. We systematically study the characteristics of both deep and shallow features, and their relation to tracking accuracy and robustness. We identify the limited data and low spatial resolution as the main challenges, and propose strategies to counter these issues when integrating deep features for tracking. Furthermore, we propose a novel adaptive fusion approach that leverages the complementary properties of deep and shallow features to improve both robustness and accuracy. Extensive experiments are performed on four challenging datasets. On VOT2017, our approach significantly outperforms the top performing tracker from the challenge with a relative gain of >17% in EAO.

sted, utgiver, år, opplag, sider
Cham: Springer Publishing Company, 2018. s. 493-509
Serie
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 11206
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-161032DOI: 10.1007/978-3-030-01216-8_30ISBN: 9783030012151 (tryckt)ISBN: 9783030012168 (digital)OAI: oai:DiVA.org:liu-161032DiVA, id: diva2:1361991
Konferanse
15th European Conference on Computer Vision (ECCV). Munich, Germany, 8-14 September, 2018
Tilgjengelig fra: 2019-10-17 Laget: 2019-10-17 Sist oppdatert: 2019-10-30bibliografisk kontrollert

Open Access i DiVA

Unveiling the power of deep tracking(627 kB)29 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 627 kBChecksum SHA-512
e1e14dade0f91f39f63ed98033c76b1cfdeb666fb7473406cda76b00e5a4e66f271ddccb72d48b555ea7245c766ba22ddee927f7859c3f92170ab1a0be181f2c
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekst

Personposter BETA

Bhat, GoutamJohnander, JoakimDanelljan, MartinKhan, Fahad ShahbazFelsberg, Michael

Søk i DiVA

Av forfatter/redaktør
Bhat, GoutamJohnander, JoakimDanelljan, MartinKhan, Fahad ShahbazFelsberg, Michael
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 29 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: 66 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