This package includes raw results files for the DeepSRDCF tracker [1], which employs deep convolutional features in the SRDCF method [2]. Results on four datasets are included:

- OTB-2015 [3] (which also includes OTB-2013 [4])
- ALOV300 [5]
- TempleColor [6]
- VOT2015 [7]

The result files for OTB-2015, ALOV300 and TempleColor are saved in the same format used in the OTB-2013 evaluation toolkit [4]. But the naming convention of the files might differ from the original verison of the OTB-2013 toolkit. This can be easily solved using some file renaming utility or script. The VOT2015 results were generated by a pre-challenge 2015 version of the toolkit [8].

[1] Martin Danelljan, Gustav Hger, Fahad Shahbaz Khan and Michael Felsberg.
	Convolutional Features for Correlation Filter Based Visual Tracking.
	ICCV workshop on the Visual Object Tracking (VOT) Challenge, 2015. 

[2] Martin Danelljan, Gustav Hger, Fahad Shahbaz Khan and Michael Felsberg.
	Learning Spatially Regularized Correlation Filters for Visual Tracking.
	In Proceedings of the International Conference in Computer Vision (ICCV), 2015.
	
[3] https://sites.google.com/site/benchmarkpami/

[4] https://sites.google.com/site/trackerbenchmark/benchmarks/v10

[5] http://www.alov300.org/

[6] http://www.dabi.temple.edu/~hbling/data/TColor-128/TColor-128.html

[7] http://www.votchallenge.net/vot2015/

[8] https://github.com/votchallenge/vot-toolkit
