Ask Your Question

Vision Challenge is unnoticed

asked 2014-09-21 02:52:56 -0500

PhilLab gravatar image

updated 2014-09-22 02:40:39 -0500

berak gravatar image

Hi, why is the ongoing OpenCV Vision Challenge not advertised? I only found it by coincidence in the development area. Why not announcing it on, Twitter, ... ?

This seems like a waste of the $50.000 prize money.

edit retag flag offensive close merge delete


Probably because when the idea was launched they seemed to be able to get the deadline for firing it up. Last thing I saw is that the challenge extras were still in the PR bots :)

So probably it is postponed!

StevenPuttemans gravatar imageStevenPuttemans ( 2014-09-22 04:33:58 -0500 )edit

Guys, wiki page is a bit outdated. Whole team is working, probably update will be at the EOW (contest hasn't started yet).

Daniil Osokin gravatar imageDaniil Osokin ( 2014-09-22 08:40:33 -0500 )edit

No problem Daniil. It is just very confusing for users, this should be kept in mind.

StevenPuttemans gravatar imageStevenPuttemans ( 2014-09-23 03:45:05 -0500 )edit

Yeah, I already spread the word in my research group :-P Ok, looking forward to it!

PhilLab gravatar imagePhilLab ( 2014-09-23 11:59:00 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2014-09-29 03:11:43 -0500

Dmitriy Anisimov gravatar image

updated 2014-11-20 03:17:25 -0500

Briefly: yes, challenge was postponed.

The main reason, I think, is that there is no clear vision, what algorithms should win: with best performance from all challenge participants, close to the state of the art or newly developed with performance above current SOTA, fastest and close to SOTA, etc.

Finally, OpenCV Vision Challenge was announced!

edit flag offensive delete link more


Thanks for the information!

StevenPuttemans gravatar imageStevenPuttemans ( 2014-09-29 03:57:20 -0500 )edit

Grand challenges are actually quite common in research. It looks like even the evaluation, or even the planning, of such challenges will need to involve members of the research community, and then these organizing helpers will need to abstain from participating from the challenge in order to maintain neutrality. A reminder for other people: just keep in mind that scientifically evaluating an algorithm is not as simple as running a program, printing out some numbers and then compare them side-by-side.

rwong gravatar imagerwong ( 2014-09-30 16:59:20 -0500 )edit

hooray ! ;)

berak gravatar imageberak ( 2014-11-20 05:16:56 -0500 )edit

@berak, you participating? :)

StevenPuttemans gravatar imageStevenPuttemans ( 2014-11-20 05:41:45 -0500 )edit

^^ maybe, for sports ;)

i was already wondering, what all the contrib/datasets stuff was for...

if you look at the samples there closely, eg. the fr_lfw_benchmark.cpp already contains the test results for the builtin competitors ..

berak gravatar imageberak ( 2014-11-20 06:02:52 -0500 )edit

Good luck then! my algorithms are far from state of the art, so probably won't join in :)

StevenPuttemans gravatar imageStevenPuttemans ( 2014-11-20 06:45:42 -0500 )edit

Wow! I'll just be a spectator but this is interesting!

Doombot gravatar imageDoombot ( 2014-11-20 09:00:01 -0500 )edit

Question Tools


Asked: 2014-09-21 02:52:56 -0500

Seen: 529 times

Last updated: Nov 20 '14