ECO icon indicating copy to clipboard operation
ECO copied to clipboard

Published 20 hours ago • verified publisher icon martin-danelljan

About ECO tracking results on VOT2016

Open KevinWalkerFan opened this issue 6 years ago • 3 comments

Hi! I just tested the ECO tracker on the VOT2016 dataset but the result curve below is different from the ECO paper. Is there something wrong with my testing results? 839543dabbe2c87ad842231002d60923_expected_overlap_curves_baseline

KevinWalkerFan avatar Apr 10 '18 07:04 KevinWalkerFan

I met a 'tag does not exist' problem when I run the run_analysis.m. I just tried to replace 'tag' with 'indentifier' in the report_ranking_spotlight.m file to fix the problem. I don't know if this solution is correct.

KevinWalkerFan avatar Apr 10 '18 07:04 KevinWalkerFan

How do you mean? In the paper, I plotted the sequence length in log-scale, as done in the VOT results paper. That's why the plots look different.

martin-danelljan avatar May 11 '18 13:05 martin-danelljan

Hi Kevin andd MD @martin-danelljan @goutamgmb I met the problem when I integrate ECO tracker with VOT2016 toolkit. I just follow the instruction of VOT document, and copy VOT_integration file and change the tracker path to my local path. When I run "run_test.m", matlab got struck forever. would you please help me what's wrong with it and How to solve this problem? Thank you very much and hope you can reply me!

fybaft2012 avatar Jul 03 '18 06:07 fybaft2012