The Visual Object Tracking VOT2016 Challenge Results

@inproceedings{Kristan2016TheVO,
  title={The Visual Object Tracking VOT2016 Challenge Results},
  author={Matej Kristan and Ale{\vs} Leonardis and Jiri Matas and Michael Felsberg and Roman P. Pflugfelder and Luka Cehovin and Tom{\'a}s Voj{\'i}r and Gustav H{\"a}ger and Alan Luke{\vz}i{\vc} and Gustavo Javier Fernandez and Abhinav Kumar Gupta and Alfredo Petrosino and Alireza Memarmoghadam and {\'A}lvaro Garc{\'i}a-Mart{\'i}n and Andr{\'e}s Sol{\'i}s Montero and Andrea Vedaldi and Andreas Robinson and Andy Jinhua Ma and Anton Yuriiovych Varfolomieiev and A. Aydin Alatan and Aykut Erdem and Bernard Ghanem and Bin Liu and Bohyung Han and Brais Mart{\'i}nez and Chang-Ming Chang and Changsheng Xu and Chong Sun and Daijin Kim and Dapeng Chen and Dawei Du and Deepak Mishra and Dit-Yan Yeung and Erhan Gundogdu and Erkut Erdem and Fahad Shahbaz Khan and Fatih Murat Porikli and Fei Zhao and Filiz Bunyak and Francesco Battistone and Gao Zhu and Giorgio Roffo and Gorthi Rama Krishna Sai Subrahmanyam and Guilherme Sousa Bastos and Guna Seetharaman and Henry Ponti Medeiros and Hongdong Li and Honggang Qi and Horst Bischof and Horst Possegger and Huchuan Lu and Hyemin Lee and Hyeonseob Nam and Hyung Jin Chang and Isabela Drummond and Jack Valmadre and Jae-chan Jeong and Jae Il Cho and Jae-Y. Lee and Jianke Zhu and Jiayi Feng and Jin Gao and Jin Young Choi and Jingjing Xiao and Ji-Wan Kim and Jiyeoup Jeong and Jo{\~a}o F. Henriques and Jochen Lang and Jongwon Choi and Jos{\'e} M. Mart{\'i}nez and Junliang Xing and Junyu Gao and Kannappan Palaniappan and Karel Lebeda and Ke Gao and Krystian Mikolajczyk and Lei Qin and Lijun Wang and Longyin Wen and Luca Bertinetto and Madan Kumar Rapuru and Mahdieh Poostchi and Mario Edoardo Maresca and Martin Danelljan and Matthias Mueller and Mengdan Zhang and Michael Arens and Michel F. Valstar and Ming Tang and Mooyeol Baek and Muhammad Haris Khan and Naiyan Wang and Nana Fan and Noor M. Al-Shakarji and Ondřej Mik{\vs}{\'i}k and Osman Akin and Payman Moallem and Pedro Senna and Philip H. S. Torr and Pong Chi Yuen and Qingming Huang and Rafael Martin-Nieto and Rengarajan Pelapur and Richard Bowden and Robert Lagani{\`e}re and R. Stolkin and Ryan Walsh and Sebastian Bernd Krah and Shengkun Li and Shengping Zhang and Shizeng Yao and Simon Hadfield and Simone Melzi and Siwei Lyu and Siyi Li and Stefan Becker and Stuart Golodetz and Sumithra Kakanuru and Sunglok Choi and Tao Hu and Thomas Mauthner and Tianzhu Zhang and Tony P. Pridmore and Vincenzo Santopietro and Weiming Hu and Wenbo Li and Wolfgang H{\"u}bner and Xiangyuan Lan and Xiaomeng Wang and Xin Li and Yang Li and Y. Demiris and Yifan Wang and Yuankai Qi and Zejian Yuan and Zexiong Cai and Zhan Xu and Zhenyu He and Zhizhen Chi},
  booktitle={ECCV Workshops},
  year={2016}
}
The Visual Object Tracking challenge VOT2016 aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 70 trackers are presented, with a large number of trackers being published at major computer vision conferences and journals in the recent years. The number of tested state-of-the-art trackers makes the VOT 2016 the largest and most challenging benchmark on short-term tracking to date. For each participating tracker, a… 

The Visual Object Tracking VOT2017 Challenge Results

The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art

The Visual Object Tracking VOT 2017 challenge results

The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art

The Sixth Visual Object Tracking VOT2018 Challenge Results

The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are

The Ninth Visual Object Tracking VOT2021 Challenge Results

The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art

The Seventh Visual Object Tracking VOT2019 Challenge Results

The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art

The Thermal Infrared Visual Object Tracking VOT-TIR2015 Challenge Results

The Thermal Infrared Visual Object Tracking challenge 2015, VOT-TIR2015, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply

The Eighth Visual Object Tracking VOT2020 Challenge Results

TLDR
A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.

Visual object tracking challenges revisited: VOT vs. OTB

TLDR
The proposed mirror tracking metrics can identify the over-fitting scenarios of a tracker, the ranks produced by OTB are more robust than those produced by VOT, and the joint ranks producedBy OTB and VOT can be used to measure failure recovery.

Motion Prediction in Visual Object Tracking

  • Jianren WangYihui He
  • Computer Science
    2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2020
TLDR
This work addresses the importance of motion prediction in VOT with a straightforward combination of standard methods using an off-the-shelf object detector to obtain instance bounding boxes and a combination of camera motion decouple and Kalman filter for state estimation.

Two Stages for Visual Object Tracking

  • Fei ChenXiaodong Wang
  • Computer Science
    2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)
  • 2021
TLDR
This paper proposes a novel tracker with two-stages: detection and segmentation, capable of locating the target by Siamese networks and can obtain competitive performance on GOT-10k dataset.
...

References

SHOWING 1-10 OF 111 REFERENCES

The Visual Object Tracking VOT2015 Challenge Results

TLDR
The Visual Object Tracking challenge 2015, VOT 2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and presents a new VOT2015 dataset twice as large as in VOT2014 with full annotation of targets by rotated bounding boxes and per-frame attribute.

The Visual Object Tracking VOT2013 Challenge Results

TLDR
The evaluation protocol of the VOT2013 challenge and the results of a comparison of 27 trackers on the benchmark dataset are presented, offering a more systematic comparison of the trackers.

The Thermal Infrared Visual Object Tracking VOT-TIR2015 Challenge Results

The Thermal Infrared Visual Object Tracking challenge 2015, VOT-TIR2015, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply

NUS-PRO: A New Visual Tracking Challenge

TLDR
A thorough experimental evaluation of 20 state-of-the-art tracking algorithms is presented with detailed analysis using different metrics and a large-scale database which contains 365 challenging image sequences of pedestrians and rigid objects is proposed.

Object Tracking Benchmark

TLDR
An extensive evaluation of the state-of-the-art online object-tracking algorithms with various evaluation criteria is carried out to identify effective approaches for robust tracking and provide potential future research directions in this field.

MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking

TLDR
With MOTChallenge, the work toward a novel multiple object tracking benchmark aimed to address issues of standardization, and the way toward a unified evaluation framework for a more meaningful quantification of multi-target tracking is described.

Robust visual tracking using template anchors

TLDR
This work proposes decomposing the visual model into several sub-models, each describing the target at a different level of detail, and introduces controlled graduation in estimation of the free parameters to address the problem of self-supervised estimation of a large number of parameters.

Single Object Long-term Tracker for Smart Control of a PTZ camera

TLDR
A single-object long-term tracker that supports high appearance changes in the tracked target, occlusions, and is also capable of recovering a target lost during the tracking process is presented.

Texture-Independent Long-Term Tracking Using Virtual Corners

TLDR
This work proposes a visual tracking algorithm, robust to many of the difficulties that often occur in real-world scenes, and addresses long-term stability, enabling the tracker to recover from drift and to provide redetection following object disappearance or occlusion.

Long-term correlation tracking

TLDR
This paper decomposes the task of tracking into translation and scale estimation of objects and shows that the correlation between temporal context considerably improves the accuracy and reliability for translation estimation, and it is effective to learn discriminative correlation filters from the most confident frames to estimate the scale change.
...