• English
    • Türkçe
  • English 
    • English
    • Türkçe
  • Login
View Item 
  •   DSpace Home
  • 3. Mühendislik Fakültesi / Faculty of Engineering
  • Computer Engineering / Bilgisayar Mühendisliği
  • View Item
  •   DSpace Home
  • 3. Mühendislik Fakültesi / Faculty of Engineering
  • Computer Engineering / Bilgisayar Mühendisliği
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.
Realtime Access Map

The visual object tracking VOT2013 challenge results

Thumbnail
View/Open
Conference Paper (395.5Kb)
Date
2013
Author
Kristan, Matej
Pflugfelder, Roman
Leonardis, Ales
Matas, Jiri
Porikli, Fatih
Cehovin, Luka
Nebehay, Georg
Fernandez, Gustavo
Vojir, Tomas
Gatt, Adam
Khajenezhad, Ahmad
Salahledin, Ahmed
Soltani-Farani, Ali
Zarezade, Ali
Petrosino, Alfredo
Milton, Anthony
Bozorgtabar, Behzad
Li, Bo
Chan, Chee Seng
Heng, Cher Keng
Ward, Dale
Kearney, David
Monekosso, Dorothy
Karaimer, Hakkı Can
Rabiee, Hamid R.
Zhu, Jianke
Gao, Jin
Xiao, Jingjing
Zhang, Junge
Xing, Junliang
Huang, Kaiqi
Lebeda, Karel
Cao, Lijun
Maresca, Mario Edoardo
Lim, Mei Kuan
El Helw, Mohamed
Felsberg, Michael
Remagnino, Paolo
Bowden, Richard
Goecke, Roland
Stolkin, Rustam
Lim, Samantha YueYing
Maher, Sara
Poullot, Sebastien
Wong, Sebastien
Satoh, Shin’ichi
Chen, Weihua
Hu, Weiming
Zhang, Xiaoqin
Li, Yang
Zhi Heng, Niu
Metadata
Show full item record
Abstract
Visual tracking has attracted a significant attention in the last few decades. The recent surge in the number of publications on tracking-related problems have made it almost impossible to follow the developments in the field. One of the reasons is that there is a lack of commonly accepted annotated data-sets and standardized evaluation protocols that would allow objective comparison of different tracking methods. To address this issue, the Visual Object Tracking (VOT) workshop was organized in conjunction with ICCV2013. Researchers from academia as well as industry were invited to participate in the first VOT2013 challenge which aimed at single-object visual trackers that do not apply pre-learned models of object appearance (model-free). Presented here is the VOT2013 benchmark dataset for evaluation of single-object visual trackers as well as the results obtained by the trackers competing in the challenge. In contrast to related attempts in tracker benchmarking, the dataset is labeled per-frame by visual attributes that indicate occlusion, illumination change, motion change, size change and camera motion, offering a more systematic comparison of the trackers. Furthermore, we have designed an automated system for performing and evaluating the experiments. We present the evaluation protocol of the VOT2013 challenge and the results of a comparison of 27 trackers on the benchmark dataset. The dataset, the evaluation tools and the tracker rankings are publicly available from the challenge website (http://votchallenge. net).
URI
http://doi.org/10.1109/ICCVW.2013.20
http://hdl.handle.net/11147/6802
Collections
  • Computer Engineering / Bilgisayar Mühendisliği [191]
  • Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection [3276]
  • WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection [2953]


DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
Theme by 
@mire NV
 

 



| IZTECH OS Policy |
DSpace@IYTE Guide |

DSpace@IZTECH

by OpenAIRE
Advanced Search

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsTypeDepartmentPublisherCategoryLanguageAccess TypeIZTECH AuthorThis CollectionBy Issue DateAuthorsTitlesSubjectsTypeDepartmentPublisherCategoryLanguageAccess TypeIZTECH Author

My Account

LoginRegister

Statistics

View Usage Statistics

DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
Theme by 
@mire NV
 

 


|| IZTECH OS Policy || DSpace@IYTE Guide || Library || IYTE || OAI-PMH ||

IZTECH Library, Gülbahçe Kampüsü - 35430 - Urla, İzmir / TURKEY
If you find any errors in content, please contact: openaccess@iyte.edu.tr.

Creative Commons Lisansı
DSpace@IZTECH by IYTE Institutional repository is licensed under a Creative Commons Attribution-Gayriticari-NoDerivs 3.0 Unported License.

DSpace@IZTECH is member of: