Workshop program

13:00 - 13:05 Opening and welcome
Matej Kristan (University of Ljubljana, Slovenia)

13:05 - 13:15 Session 1 (Chair: Aleš Leonardis):

13:05 The Visual Object Tracking VOT2015 challenge results
Matej Kristan (University of Ljubljana, Slovenia), Jiři Matas (Czech Technical University, Czech Republic), Aleš Leonardis (University of Birmingham, UK), Michael Felsberg (Linköping University, Sweden), Luka Čehovin (University of Ljubljana, Slovenia), Gustavo Fernández (Austrian Institute of Technology, Austria), Tomáš Vojiř (Czech Technical University, Czech Republic), Gustav Häger (Linköping University, Sweden), Georg Nebehay (Austrian Institute of Technology, Austria), Roman Pflugfelder (Austrian Institute of Technology, Austria), et al.

Presentation
Paper

13:50 Winners of the VOT challenge: Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
Hyeonseob Nam and Bohyung Han (POSTECH, Korea)

14:10 Scalable Kernel Correlation Filter with Sparse Feature Integration
Andrés Solís Montero, Jochen Lang, Robert Laganière (University of Ottawa, Canada)

14:30 Keynote Talk I: Fast correlation filter tracking - tricks of the trade
João F. Henriques (University of Coimbra, Portugal)

15:15 Coffe break with posters and demos (Chair: Gustavo Fernandez)

    **Posters**
- **[Joint Scale-Spatial Correlation Tracking with Adaptive Rotation Estimation](https://data.votchallenge.net/vot2015/presentations/poster_Mengdan_Zhang.pdf)**
Mengdan Zhang, Junliang Xing, Jin Gao, Xinchu Shi, Qiang Wang, Weiming Hu (Institute of Automation, Chinese Academy of Sciences, China)
- **[Robust visual tracking by exploiting the historical tracker snapshots](https://data.votchallenge.net/vot2015/presentations/poster_Jiatong_Li.pdf)**
Jiatong Li (Beijing Institute of Technology, China and University of Technology, Australia), Zhibin Hong (University of Technology, Australia), Baojun Zhao (Beijing Institute of Technology, China)
- **[Multi-Template Scale-Adaptive Kernelized Correlation Filters](https://data.votchallenge.net/vot2015/presentations/poster_Adel_Bibi.pdf)**
Adel Bibi, Bernard Ghanem (King Abdullah University of Science and Technology, Saudi Arabia)
- **Convolutional Features for Correlation Filter Based Visual Tracking**
Gustav Häger, Martin Danelljan, Fahad Khan, Michael Felsberg (Linköping University, Sweden)
- **Tracker Fusion on VOT challenge: How does it perform and what can we learn about single trackers?**
Christian Bailer, Didier Stricker (German Research Center for Artificial Intelligence, Germany)
- **Ask not what the VOT challenge can do for you ...**
Luka Čehovin (University of Ljubljana, Slovenia)

**Demos**
- **[Scalable Kernel Correlation Filter with Sparse Feature Integration (sKCF)](https://data.votchallenge.net/vot2015/presentations/demo_Solis_Montero.mp4)**
Andres Solis Montero (University of Ottawa, Canada)
- **[Scale Ratio Adaptive Tracker (SRAT)](https://data.votchallenge.net/vot2015/presentations/demo_Hyemin_Lee.pdf)**
HyeminLee, Daijin Kim (Postech, Korea)
- **Likelihood of Features Tracker (LOFT-Lite)**
K. Palaniappan (University of Missouri, USA)
- **Tracking by Regression with Incrementally Learned Cascades (TRIC-track)**
Xiaomeng Wang (University of Nottingham, UK)
- **Multi-Channel Multiple-Instance-Learning Tracker (CMIL)**
Hilke Kieritz (Fraunhofer Institute, Germany)
- **[SumShift tracker and Concurrent tracker](https://data.votchallenge.net/vot2015/presentations/demo_Jae_Yeong_Lee.mp4)**
JaeYeong Lee (ETRI, Korea)
- **[Staple: Complementary Learners for Real-Time Tracking](https://data.votchallenge.net/vot2015/presentations/poster_Luca_Bertinetto.pdf)** [Project page](http://www.robots.ox.ac.uk/~luca/staple.html)
Luca Bertinetto (University of Oxford, UK)
- **Ask not what the VOT challenge can do for you ...**
Luka Čehovin (University of Ljubljana, Slovenia)

16:30 - 19:00 Session 2 (Chair: Jiři Matas):

16:30 Keynote Talk II: Semantic and geometric models in visual object tracking
Richard Bowden (University of Surrey, UK)

17:15 The Visual Object Tracking VOT-TIR2015 challenge results
Michael Felsberg (Linköping University, Sweden), Amanda Berg (Linköping University and Termisk Systemteknik, Sweden), Jörgen Ahlberg (Linköping University and Termisk Systemteknik, Sweden), Gustav Häger (Linköping University, Sweden), Matej Kristan (University of Ljubljana, Slovenia), Jiři Matas (Czech Technical University, Czech Republic), Aleš Leonardis (University of Birmingham, UK), Luka Čehovin (University of Ljubljana, Slovenia), Gustavo Fernández (Austrian Institute of Technology, Austria), Tomáš Vojiř (Czech Technical University, Czech Republic), Georg Nebehay (Austrian Institute of Technology, Austria), Roman Pflugfelder (Austrian Institute of Technology, Austria), et al.

Presentation
Paper

17:35 Winners of the VOT-TIR challenge: Simplified Proposal Selection Tracker (sPST)
Yang Hua, Karteek Alahari, Cordelia Schmid (INRIA, France)

17:55 Learning Spatially Regularized Correlation Filters for Visual Tracking
Martin Danelljan, Gustav Häger, Fahad Khan, Michael Felsberg (Linköping University, Sweden)

18:15 Panel discussion (Moderator: Aleš Leonardis)

  • Richard Bowden (University of Surrey, UK)
  • Gerard Guy Medioni (University of Southern California, USA)
  • James Ferryman (University of Reading, UK)
  • Ming-Hsuan Yang (University of California at Merced, USA)
  • Jiři Matas (Czech Technical University in Prague, Czech Republic)

18:50 Closing, concluding remarks


Notes

et al. (VOT results)

Abhinav Gupta (Carnegie Mellon University), Adel Bibi (King Abdullah University of Science and Technology), Alan Lukežič (Ljubljana University), Alvaro Garcia-Martin (Universidad Autónoma de Madrid), Alfredo Petrosino (Parthenope University of Naples), Amir Saffari (Affectv Limited), Andrés Solís Montero (University of Ottawa), Anton Varfolomieiev (National Technical University of Ukraine), Atilla Baskurt (Universitè de Lyon), Baojun Zhao (Beijing Institute of Technology), Bernard Ghanem (King Abdullah University of Science and Technology), Brais Martinez (University of Nottingham), ByeongJu Lee (Seoul National University), Bohyung Han (POSTECH), Chaohui Wang (Universitè Paris-Est), Christophe Garcia (LIRIS), Chunyuan Zhang (National University of Defense Technology and National Key Laboratory of Parallel and Distributed Processing Changsha), Cordelia Schmid (INRIA Grenoble Rhône-Alpes), Dacheng Tao (University of Technology), Daijin Kim (POSTECH), Dafei Huang (National University of Defense Technology and National Key Laboratory of Parallel and Distributed Processing Changsha), Danil Prokhorov (Toyota Research Institute), Dawei Du (University at Albany and SCCE Chinese Academy of Sciences), Dit-Yan Yeung (Hong Kong University of Science and Technology), Eraldo Ribeiro (Florida Institute of Technology), Fahad Shahbaz Khan (Linköping University), Fatih Porikli (Australian National University and NICTA), Filiz Bunyak (University of Missouri), Gao Zhu (Australian National University), Guna Seetharaman (Naval Research Lab), Hilke Kieritz (Fraunhofer IOSB), Hing Tuen Yau (Chinese University of Hong Kong), Hongdong Li (Chinese University of Hong Kong and ARC Centre of Excellence for Robotic Vision), Honggang Qi (University at Albany and SCCE Chinese Academy of Sciences), Horst Bischof (Graz University of Technology), Horst Possegger (Graz University of Technology), Hyemin Lee (POSTECH), Hyeonseob Nam (POSTECH), Ivan Bogun (Florida Institute of Technology), Jae-chan Jeong (Electronics and Telecommunications Research Institute), Jae-il Cho (Electronics and Telecommunications Research Institute), Jae-Yeong Lee (Electronics and Telecommunications Research Institute), Jianke Zhu (Zhejiang University), Jianping Shi (CUHK), Jiatong Li (Beijing Institute of Technology and University of Technology), Jiaya Jia (CUHK), Jiayi Feng (Institute of Automation Chinese Academy of Sciences), Jin Gao (Institute of Automation Chinese Academy of Sciences), Jin Young Choi (Seoul National University), Ji-Wan Kim (Electronics and Telecommunications Research Institute), Jochen Lang (University of Ottawa), Jose M. Martinez (Universidad Autónoma de Madrid), Jongwon Choi (Seoul National University), Junliang Xing (Institute of Automation Chinese Academy of Sciences), Kai Xue (Harbin Engineering University), Kannappan Palaniappan (University of Missouri), Karel Lebeda (University of Surrey), Karteek Alahari (INRIA Grenoble Rhône-Alpes), Ke Gao (University of Missouri), Kimin Yun (Seoul National University), Kin Hong Wong (Chinese University of Hong Kong), Lei Luo (National University of Defense Technology), Liang Ma (Harbin Engineering University), Lipeng Ke (University at Albany and SCCE Chinese Academy of Sciences), Longyin Wen (University at Albany), Luca Bertinetto (Oxford University), Mahdieh Pootschi (University of Missouri), Mario Maresca (Parthenope University of Naples), Martin Danelljan (Linköping University), Mei Wen (National University of Defense Technology and National Key Laboratory of Parallel and Distributed Processing Changsha), Mengdan Zhang (Institute of Automation Chinese Academy of Sciences), Michael Arens (Fraunhofer IOSB), Michel Valstar (University of Nottingham), Ming Tang (Institute of Automation Chinese Academy of Sciences), Ming-Ching Chang (University at Albany), Muhammad Haris Khan (University of Nottingham), Nana Fan (Harbin Institute of Technology), Naiyan Wang (Hong Kong University of Science and Technology and TuSimple LLC), Ondrej Miksik (Oxford University), Philip Torr (Oxford University), Qiang Wang (Institute of Automation Chinese Academy of Sciences), Rafael Martin-Nieto (Universidad Autónoma de Madrid), Rengarajan Pelapur (University of Missouri), Richard Bowden (University of Surrey), Robert Laganière (University of Ottawa), Salma Moujtahid (Universitè de Lyon), Sam Hare (Obvious Engineering Limited), Simon Hadfield (University of Surrey), Siwei Lyu (University at Albany), Siyi Li (Hong Kong University of Science and Technology), Song-Chun Zhu (University of California), Stefan Becker (Fraunhofer IOSB), Stefan Duffner (Universitè de Lyon and LIRIS), Stephen L Hicks (Oxford University), Stuart Golodetz (Oxford University), Sunglok Choi (Electronics and Telecommunications Research Institute), Tianfu Wu (University of California), Thomas Mauthner (Graz University of Technology), Tony Pridmore (University of Nottingham), Weiming Hu (Institute of Automation Chinese Academy of Sciences), Wolfgang Hübner (Fraunhofer IOSB), Xiaomeng Wang (University of Nottingham), Xin Li (Harbin Institute of Technology), Xinchu Shi (Institute of Automation Chinese Academy of Sciences), Xu Zhao (Institute of Automation Chinese Academy of Sciences), Xue Mei (Toyota Research Institute), Yao Shizeng (University of Missouri), Yang Hua (INRIA Grenoble Rhône-Alpes), Yang Li (Zhejiang University), Yang Lu (University of California), Yuezun Li (University at Albany), Zhaoyun Chen (National University of Defense Technology and National Key Laboratory of Parallel and Distributed Processing Changsha), Zehua Huang (Carnegie Mellon University), Zhe Chen (University of Technology), Zhe Zhang (Baidu Corporation), Zhenyu He (Harbin Institute of Technology), and Zhibin Hong (University of Technology).

et al. (VOT-TIR results)

Alan Lukežič (Ljubljana University), Alvaro Garcia-Martin (Universidad Autónoma de Madrid), Amir Saffari (Affectv Limited), Ang Li (Xi’an Jiaotong University), Andrés Solís Montero (University of Ottawa), Baojun Zhao (Beijing Institute of Technology), Cordelia Schmid (INRIA Grenoble Rhône-Alpes), Dapeng Chen (Xi’an Jiaotong University), Dawei Du (University at Albany and SCCE Chinese Academy of Sciences), Fahad Shahbaz Khan (Linköping University), Fatih Porikli (Australian National University and NICTA), Gao Zhu (Australian National University), Guibo Zhu (NLPR Chinese Academy of Sciences), Hanqing Lu (NLPR Chinese Academy of Sciences), Hilke Kieritz (Fraunhofer IOSB), Hongdong Li (Chinese University of Hong Kong and ARC Centre of Excellence for Robotic Vision), Honggang Qi (University at Albany and SCCE Chinese Academy of Sciences), Jae-chan Jeong (Electronics and Telecommunications Research Institute), Jae-il Cho (Electronics and Telecommunications Research Institute), Jae-Yeong Lee (Electronics and Telecommunications Research Institute), Jianke Zhu (Zhejiang University), Jiatong Li (Beijing Institute of Technology and University of Technology), Jiayi Feng (Institute of Automation Chinese Academy of Sciences), Jinqiao Wang (NLPR Chinese Academy of Sciences), Ji-Wan Kim (Electronics and Telecommunications Research Institute), Jochen Lang (University of Ottawa), Jose M. Martinez (Universidad Autónoma de Madrid), Kai Xue (Harbin Engineering University), Karteek Alahari (INRIA Grenoble Rhône-Alpes), Liang Ma (Harbin Engineering University), Lipeng Ke (University at Albany and SCCE Chinese Academy of Sciences), Longyin Wen (University at Albany), Luca Bertinetto (Oxford University), Martin Danelljan (Linköping University), Michael Arens (Fraunhofer IOSB), Ming Tang (Institute of Automation Chinese Academy of Sciences), Ming-Ching Chang (University at Albany), Ondrej Miksik (Oxford University), Philip Torr (Oxford University), Rafael Martin-Nieto (Universidad Autónoma de Madrid), Robert Laganière (University of Ottawa), Sam Hare (Obvious Engineering Limited), Siwei Lyu (University at Albany), Song-Chun Zhu (University of California), Stefan Becker (Fraunhofer IOSB), Stephen L Hicks (Oxford University), Stuart Golodetz (Oxford University), Sunglok Choi (Electronics and Telecommunications Research Institute), Tianfu Wu (University of California), Wolfgang Hübner (Fraunhofer IOSB), Xu Zhao (Institute of Automation Chinese Academy of Sciences), Yang Hua (INRIA Grenoble Rhône-Alpes), Yang Li (Zhejiang University), Yang Lu (University of California), Yuezun Li (University at Albany), Zejian Yuan (Xi’an Jiaotong University), and Zhibin Hong (University of Technology).