Optical flow in deep visual tracking

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the AAAI Conference on Artificial Intelligence
Place of PublicationPalo Alto, CA, USA
PublisherAAAI PRESS
Pages12112-12119
Number of pages8
ISBN (Print)978-1-57735-835-0
DOIs
Publication statusPublished - 3 Apr 2020
MoE publication typeA4 Article in a conference publication
EventAAAI Conference on Artificial Intelligence - New York, United States
Duration: 7 Feb 202012 Feb 2020
Conference number: 34
https://aaai.org/Conferences/AAAI-20/

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
PublisherAAAI Press, Palo Alto, CA, USA
Number7
Volume34
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

ConferenceAAAI Conference on Artificial Intelligence
Abbreviated titleAAAI
Country/TerritoryUnited States
CityNew York
Period07/02/202012/02/2020
Internet address

Fingerprint

Dive into the research topics of 'Optical flow in deep visual tracking'. Together they form a unique fingerprint.

Cite this