The Visual Object Tracking VOT2015 Challenge Results

Matej Kristan, Jiri Matas, Ale Leonardis, Michael Felsberg, Luka Cehovin, Gustavo Fernandez, Toma Vojir, Gustav Hager, Georg Nebehay, Roman Pflugfelder, Abhinav Gupta, Adel Bibi, Alan Lukezic, Alvaro Garcia-Martin, Amir Saffari, Alfredo Petrosino, Andres Solıs Montero, Anton Varfolomieiev, Atilla Baskurt, Baojun ZhaoBernard Ghanem, Brais Martinez, ByeongJu Lee, Bohyung Han, Chaohui Wang, Christophe Garcia, Chunyuan Zhang, Cordelia Schmid, Dacheng Tao, Daijin Kim, Dafei Huang, Danil Prokhorov, Dawei Du, Dit-Yan Yeung, Eraldo Ribeiro, Fahad Shahbaz Khan, Fatih Porikli, Filiz Bunyak, Gao Zhu, Guna Seetharaman, Hilke Kieritz, Hing Tuen Yau, Hongdong Li, Honggang Qi, Horst Bischof, Horst Possegger, Hyemin Lee, Hyeonseob Nam, Ivan Bogun, Jae-chan Jeong, Jae-il Cho, Jae-Yeong Lee, Jianke Zhu, Jianping Shi, Jiatong Li, Jiaya Jia, Jiayi Feng, Jin Gao, Jin Young Choi, Ji-Wan Kim, Jochen Lang, Jose M. Martinez, Jongwon Choi, Junliang Xing, Kai Xue, Kannappan Palaniappan, Karel Lebeda, Karteek Alahari, Ke Gao, Kimin Yun, Kin Hong Wong, Lei Luo, Liang Ma, Lipeng Ke, Longyin Wen, Luca Bertinetto, Mahdieh Pootschi, Mario Maresca, Martin Danelljan, Mei Wen, Mengdan Zhang, Michael Arens, Michel Valstar, Ming Tang, Ming-Ching Chang, Muhammad Haris Khan, Nana Fan, Naiyan Wang, Ondrej Miksik, Philip H S Torr, Qiang Wang, Rafael Martin-Nieto, Rengarajan Pelapur, Richard Bowden, Robert Laganiere, Salma Moujtahid, Sam Hare, Simon Hadfield, Siwei Lyu, Siyi Li, Song-Chun Zhu, Stefan Becker, Stefan Duffner, Stephen L Hicks, Stuart Golodetz, Sunglok Choi, Tianfu Wu, Thomas Mauthner, Tony Pridmore, Weiming Hu, Wolfgang Hubner, Xiaomeng Wang, Xin Li, Xinchu Shi, Xu Zhao, Xue Mei, Yao Shizeng, Yang Hua, Yang Li, Yang Lu, Yuezun Li, Zhaoyun Chen, Zehua Huang, Zhe Chen, Zhe Zhang, Zhenyu He, Zhibin Hong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

475 Scopus citations

Abstract

The Visual Object Tracking challenge 2015, VOT2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 62 trackers are presented. The number of tested trackers makes VOT 2015 the largest benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the appendix. Features of the VOT2015 challenge that go beyond its VOT2014 predecessor are: (i) a new VOT2015 dataset twice as large as in VOT2014 with full annotation of targets by rotated bounding boxes and per-frame attribute, (ii) extensions of the VOT2014 evaluation methodology by introduction of a new performance measure. The dataset, the evaluation kit as well as the results are publicly available at the challenge website.
Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Computer Vision Workshop (ICCVW)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages564-586
Number of pages23
ISBN (Print)9781467397117
DOIs
StatePublished - Feb 16 2016

Fingerprint

Dive into the research topics of 'The Visual Object Tracking VOT2015 Challenge Results'. Together they form a unique fingerprint.

Cite this