search

martin-danelljan / ECO

Matlab implementation of the ECO tracker.
GNU General Public License v3.0
614 stars 252 forks source link

About ECO tracking results on VOT2016 #30

Open KevinWalkerFan opened 6 years ago

KevinWalkerFan commented 6 years ago

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 commented 6 years ago

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.

martin-danelljan commented 6 years ago

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.

fybaft2012 commented 6 years ago

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!