Optical flow in deep visual tracking

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

9 Sitaatiot (Scopus)

Abstrakti

Single-target tracking of generic objects is a difficult task since a trained tracker is given information present only in the first frame of a video. In recent years, increasingly many trackers have been based on deep neural networks that learn generic features relevant for tracking. This paper argues that deep architectures are often fit to learn implicit representations of optical flow. Optical flow is intuitively useful for tracking, but most deep trackers must learn it implicitly. This paper is among the first to study the role of optical flow in deep visual tracking. The architecture of a typical tracker is modified to reveal the presence of implicit representations of optical flow and to assess the effect of using the flow information more explicitly. The results show that the considered network learns implicitly an effective representation of optical flow. The implicit representation can be replaced by an explicit flow input without a notable effect on performance. Using the implicit and explicit representations at the same time does not improve tracking accuracy. The explicit flow input could allow constructing lighter networks for tracking.

AlkuperäiskieliEnglanti
OtsikkoProceedings of the AAAI Conference on Artificial Intelligence
JulkaisupaikkaPalo Alto, CA, USA
KustantajaAAAI Press
Sivut12112-12119
Sivumäärä8
ISBN (painettu)978-1-57735-835-0
DOI - pysyväislinkit
TilaJulkaistu - 3 huhtik. 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaAAAI Conference on Artificial Intelligence - New York, Yhdysvallat
Kesto: 7 helmik. 202012 helmik. 2020
Konferenssinumero: 34
https://aaai.org/Conferences/AAAI-20/

Julkaisusarja

NimiProceedings of the AAAI Conference on Artificial Intelligence
KustantajaAAAI Press, Palo Alto, CA, USA
Numero7
Vuosikerta34
ISSN (painettu)2159-5399
ISSN (elektroninen)2374-3468

Conference

ConferenceAAAI Conference on Artificial Intelligence
LyhennettäAAAI
Maa/AlueYhdysvallat
KaupunkiNew York
Ajanjakso07/02/202012/02/2020
www-osoite

Sormenjälki

Sukella tutkimusaiheisiin 'Optical flow in deep visual tracking'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä