The Visual Object Tracking VOT2015 challenge results

被引：541

作者：

Kristan, Matej ^{[1
]}

Matas, Jiri ^{[2
]}

Leonardis, Ales ^{[3
]}

Felsberg, Michael ^{[4
]}

Cehovin, Luka ^{[1
]}

Fernandez, Gustavo ^{[5
]}

Vojir, Tomas ^{[2
]}

Hager, Gustav ^{[4
]}

Nebehay, Georg ^{[5
]}

Pflugfelder, Roman ^{[5
]}

Gupta, Abhinav ^{[6
]}

Bibi, Adel ^{[7
]}

Lukezic, Alan ^{[1
]}

Garcia-Martins, Alvaro ^{[8
]}

Saffari, Amir ^{[10
]}

Petrosino, Alfredo ^{[12
]}

Montero, Andres Solis ^{[13
]}

Varfolomieiev, Anton ^{[14
]}

Baskurt, Atilla ^{[15
]}

Zhao, Baojun ^{[16
]}

Ghanem, Bernard ^{[7
]}

Martinez, Brais ^{[17
]}

Lee, ByeongJu ^{[18
]}

Han, Bohyung ^{[19
]}

Wang, Chaohui ^{[20
]}

Garcia, Christophe ^{[21
]}

Zhang, Chunyuan ^{[22
,23
]}

Schmid, Cordelia ^{[24
]}

Tao, Dacheng ^{[25
]}

Kim, Daijin ^{[19
]}

Huang, Dafei ^{[22
,23
]}

Prokhorov, Danil ^{[26
]}

Du, Dawei ^{[27
,28
]}

Yeung, Dit-Yan ^{[29
]}

Ribeiro, Eraldo ^{[30
]}

Khan, Fahad Shahbaz ^{[4
]}

Porikli, Fatih ^{[31
,32
]}

Bunyak, Filiz ^{[33
]}

Zhu, Gao ^{[31
]}

Seetharaman, Guna ^{[34
]}

Kieritz, Hilke ^{[36
]}

Yau, Hing Tuen ^{[37
]}

Li, Hongdong ^{[31
,38
]}

Qi, Honggang ^{[27
,28
]}

Bischof, Horst ^{[39
]}

Possegger, Horst ^{[39
]}

Lee, Hyemin ^{[19
]}

Nam, Hyeonseob ^{[19
]}

Bogun, Ivan ^{[30
]}

Jeong, Jae-chan ^{[40
]}

机构：

[1] Univ Ljubljana, Ljubljana, Slovenia

[2] Czech Tech Univ, Prague, Czech Republic

[3] Univ Birmingham, Birmingham, W Midlands, England

[4] Linkoping Univ, Linkoping, Sweden

[5] Austrian Inst Technol, Seibersdorf, Austria

[6] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA

[7] King Abdullah Univ Sci & Technol, Thuwal, Saudi Arabia

[8] Univ Autonoma Madrid, E-28049 Madrid, Spain

[9] Baidu Corp, Beijing, Peoples R China

[10] Affectv, London, England

[11] TuSimple LLC, San Diego, CA USA

[12] Parthenope Univ Naples, Naples, Italy

[13] Univ Ottawa, Ottawa, ON K1N 6N5, Canada

[14] Natl Tech Univ Ukraine, Kiev, Ukraine

[15] Univ Lyon, Lyon, France

[16] Beijing Inst Technol, Beijing, Peoples R China

[17] Univ Nottingham, Nottingham, England

[18] Seoul Natl Univ, Seoul, South Korea

[19] POSTECH, Pohang, South Korea

[20] Univ Paris Est, Paris, France

[21] LIRIS, Lyon, France

[22] Natl Univ Def Technol, Changsha, Hunan, Peoples R China

[23] Natl Key Lab Parallel & Distributed Proc, Changsha, Hunan, Peoples R China

[24] INRIA Grenoble Rhone Alpes, Grenoble, France

[25] Univ Technol Sydney, Sydney, NSW, Australia

[26] Toyota Res Inst, Toyota, Japan

[27] SUNY Albany, Albany, NY USA

[28] Chinese Acad Sci, SCCE, Beijing, Peoples R China

[29] Hong Kong Univ Sci & Technol, Hong Kong, Hong Kong, Peoples R China

[30] Florida Inst Technol, Melbourne, FL USA

[31] Australian Natl Univ, Canberra, ACT 0200, Australia

[32] NICTA, Sydney, NSW, Australia

[33] Univ Missouri, Columbia, MO 65211 USA

[34] Naval Res Lab, Washington, DC 20375 USA

[35] Harbin Engn Univ, Harbin, Peoples R China

[36] Fraunhofer IOSB, Karlsruhe, Germany

[37] Chinese Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China

[38] ARC Ctr Excellence Robot Vis, Brisbane, Qld, Australia

[39] Graz Univ Technol, Graz, Austria

[40] Elect & Telecommun Res Inst, Daejeon, South Korea

[41] Zhejiang Univ, Hangzhou, Zhejiang, Peoples R China

[42] CUHK, Hong Kong, Hong Kong, Peoples R China

[43] Chinese Acad Sci, Inst Automat, Beijing, Peoples R China

[44] Univ Surrey, Guildford GU2 5XH, Surrey, England

[45] Univ Oxford, Oxford OX1 2JD, England

[46] Obvious Engn, London, England

[47] Harbin Inst Technol, Harbin, Peoples R China

来源：

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW) | 2015年

关键词：

ADAPTIVE MEAN-SHIFT; MOTION; FACE;

D O I：

10.1109/ICCVW.2015.79

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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(1).

引用

页码：564 / 586

页数：23

共 85 条

[1]

[Anonymous], 2014, BRIT MACH VIS C

[2]

[Anonymous], P ACCV DTCE

[3]

[Anonymous], 2006, BMVC06

[4]

[Anonymous], TPAMI

[5]

[Anonymous], 2011, 16 COMP VIS WINT WOR

[6]

[Anonymous], WACV 2014 IEEE WINT

[7]

Asthana A., 2014, COMPUTER VISION PATT

[8]

Atkinson R. C., 1968, PSYCHOL LEARN MOTIV, V2, P89

[9] Robust Object Tracking with Online Multiple Instance Learning [J].

Babenko, Boris ;

Yang, Ming-Hsuan ;

Belongie, Serge .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (08) :1619-1632

[10]

Bao CL, 2012, PROC CVPR IEEE, P1830, DOI 10.1109/CVPR.2012.6247881

← 1 2 3 4 5 6 7 8 9 →