The Visual Object Tracking VOT2015 Challenge Results

@article{Kristan2015TheVO,
  title={The Visual Object Tracking VOT2015 Challenge Results},
  author={Matej Kristan and Jiri Matas and Ale{\vs} Leonardis and Michael Felsberg and Luka Cehovin and Gustavo Javier Fernandez and Tom{\'a}s Voj{\'i}r and Gustav H{\"a}ger and Georg Nebehay and Roman P. Pflugfelder and Zhe Chen},
  journal={2015 IEEE International Conference on Computer Vision Workshop (ICCVW)},
  year={2015},
  pages={564-586}
}
  • M. KristanJiri Matas Zhe Chen
  • Published 7 December 2015
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision Workshop (ICCVW)
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… 
View on IEEE
repository.kaust.edu.sa
403 Citations
Highly Influential Citations
91
Background Citations
172
Methods Citations
175
Results Citations
14

Figures and Tables from this paper

403 Citations

The Visual Object Tracking VOT 2016 Challenge Results

The VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.

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 VOT2013 Challenge Results

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 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 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 VOT 2015 and VOT-TIR 2015 Challenges Submission Report

The goal of these challenges is to compare short-term model-free single-object trackers, and serve as the de factor state-of-the-art evaluation platform for visual object tracking.

Long-Term Visual Object Tracking Benchmark

Existing short sequence benchmarks fail to bring out the inherent differences in tracking algorithms which widen up while tracking on long sequences and the accuracy of trackers abruptly drops on challenging long sequences, suggesting the potential need of research efforts in the direction of long-term tracking.

Challenges Driven Network for Visual Tracking

The challenges driven network (CDNet) for motion and occlusion handling is proposed, and a motion-aware proposal method utilizing cues of optical flow and previous target states is provided and a challenges driven feature learning approach is constructed by combining dual multi-domain learning and category prior learning.

One-Shot Scale and Angle Estimation for Fast Visual Object Tracking

A one-shot Siamese network, named Siam-OS, for fast and efficient visual object tracking that significantly reduces the number of computations required for the deep convolutional feature extraction, and thus increases the tracking speed.

Visual Tracking With Long-Short Term Based Correlation Filter

A novel real-time long-short-term multi-model based tracking method designed to solve the inaccurate prediction of object position due to the cosine window in the correlation filter and the bounding-box regression strategy is introduced.
...

References

SHOWING 1-10 OF 83 REFERENCES

The Visual Object Tracking VOT2013 Challenge Results

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…

Online Object Tracking with Proposal Selection

This paper formulating it as a proposal selection task and making two contributions, introducing novel proposals estimated from the geometric transformations undergone by the object, and building a rich candidate set for predicting the object location.

NUS-PRO: A New Visual Tracking Challenge

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.

Long-Term Tracking through Failure Cases

A visual tracking algorithm, robust to many of the difficulties which often occur in real-world scenes, and addressing long-term stability, enabling the tracker to recover from drift and to provide redetection following object disappearance or occlusion is proposed.

A Novel Performance Evaluation Methodology for Single-Target Trackers

The requirements are the basis of a new evaluation methodology that aims at a simple and easily interpretable tracker comparison and a fully-annotated dataset with per-frame annotations with several visual attributes, which is the largest benchmark to date.

Object Tracking Benchmark

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.

Using Discriminative Motion Context for Online Visual Object Tracking

An algorithm for online, real-time tracking of arbitrary objects in videos from unconstrained environments based on a particle filter framework using different visual features and motion prediction models is proposed, effectively integrating a discriminative online learning classifier into the model and proposed new method to collect negative training examples for updating the classifier at each video frame.

The Importance of Estimating Object Extent when Tracking with Correlation Filters

This paper demonstrates that it is possible to partially correct this behaviour using a simple refinement of the estimated position based on a pixel-wise object likelihood, which makes these trackers significantly more robust to shape change, because the model update uses a non-drifted version of the target.

A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration

This paper presents a very appealing tracker based on the correlation filter framework and suggests an effective scale adaptive scheme to tackle the problem of the fixed template size in kernel correlation filter tracker.
...