Football is infinite in the sense that when a player has possession there are an infinite number of things they could do with it; dribble in any direction for any distance; pass any distance, any length, with any type of height on the ball; shoot at any area of the goal with any power and curl etc. On any given move in chess you have a finite number of pieces you could move in a finite number of ways.
xG is only capturing shots that actually happened - doesn't capture anything else. That's its limitation.
If only I’d known that years ago when I did the poolsFootball is absolutely not infinite, there’s a limited number of players in a limited space. The barrier to modelling isn’t resolution, we can accurately model the weather after all.
We can absolutely build a predictive model using some kind of tokenisation and traditional feature extraction from current video segmentation and labelling techniques. Even a relatively low resolution 3D grid would capture most of the relevant features of players and balls maybe you could get sophisticated with pose estimation and kinematic modelling of player body positions, but a simple CNN classifier to put them into a few minimal pose buckets would work too for player state: standing, jumping, falling, etc. time series gives you velocity and movement.
Once you’ve done that you can model goals and produce some kind of similarity metric which allows you to assign difficulty scores.
But I fully expect that’s what closed source xG models are doing.
TBH I wouldn’t be surprised if you could skip all of that these days and feed the video into a video transformer model similar to ChatGPT and get a direct prediction out. Next token prediction is what video generation models do, run a bunch of next frames predictions after training on all the football footage you can find and assess how many have the ball in the goal.
Was watching something or reading something and the figures of variables after about 6 moves was in the billions unless I was mishearing
Actually their front three work hard to try & press high.Wednesday will park the bus and play deep so wouldn't be surprised too see BTA out wide as no space for him to run into through the middle. Other than that I'd go pretty much with the same team with Simms replacing Tats.
Wow , I never saw a calculator until I was 14 !!Football is absolutely not infinite, there’s a limited number of players in a limited space. The barrier to modelling isn’t resolution, we can accurately model the weather after all.
We can absolutely build a predictive model using some kind of tokenisation and traditional feature extraction from current video segmentation and labelling techniques. Even a relatively low resolution 3D grid would capture most of the relevant features of players and balls maybe you could get sophisticated with pose estimation and kinematic modelling of player body positions, but a simple CNN classifier to put them into a few minimal pose buckets would work too for player state: standing, jumping, falling, etc. time series gives you velocity and movement.
Once you’ve done that you can model goals and produce some kind of similarity metric which allows you to assign difficulty scores.
But I fully expect that’s what closed source xG models are doing.
TBH I wouldn’t be surprised if you could skip all of that these days and feed the video into a video transformer model similar to ChatGPT and get a direct prediction out. Next token prediction is what video generation models do, run a bunch of next frames predictions after training on all the football footage you can find and assess how many have the ball in the goal.
We had about 3 different players there who all seemed to be doing the same thing - moving inside and not tracking back.My only concern is that at the moment whoever plays on the right doesn't track back enough, leaving MVE to decide which of two players to cover
Actually their front three work hard to try & press high.
Wow , I never saw a calculator until I was 14 !!
What's that the value of, just asking?🫣55378008
Logarithmic?What's that the value of, just asking?🫣
70755378008
IMO the same happens on the left not only do they not track back they stand in no mans land when marking up for goalkicks .My only concern is that at the moment whoever plays on the right doesn't track back enough, leaving MVE to decide which of two players to cover
Is that oppo GK or in our favour that would be genius?IMO the same happens on the
IMO the same happens on the left not only do they not track back they stand in no mans land when marking up for goalkicks .
with our recordWatched Wednesday against Brizzle the other night and I wasn’t impressed, should be a comfortable home win. Same team but EMC for Saka. I’m gonna go 2-0 win EMC and Wright with the goals.
Nor were 10 other playersSheaf not in the recent video uploaded of the players running around in training...
Wasn't it against this lot that kitching got sent off for defending himself?Hope we tonk these racist bellends 8-0
And I hope whoever was with us last season hasn’t forgot their centre halves cowardly elbow on Jamie Allen which ruled him out for months
That was the League game on Boxing Day where Kitch was sent off for being headbutted, Allen was clotheslined in the cup replay at homeWasn't it against this lot that kitching got sent off for defending himself?
Scabby players, scabby club and scabby fan base
BTA starts. Surely. Dropping him after the win would be nuts and send out totally the wrong message. I love his energy and personality and I don't really get why West Brom fans don't rate him...If we want to play the same as Tuesday assante has to play up front, started the press from the front, simms doesn’t do that, feel a bit sorry for him, don’t think he’s gonna fit in to how we should be playing at home, away games maybe
Football is infinite in the sense that when a player has possession there are an infinite number of things they could do with it; dribble in any direction for any distance; pass any distance, any length, with any type of height on the ball; shoot at any area of the goal with any power and curl etc. On any given move in chess you have a finite number of pieces you could move in a finite number of ways.
xG is only capturing shots that actually happened - doesn't capture anything else. That's it's limitation.
BTA has longish braids/breads so they may get confused as they aren't too smartAt least their racist fanbase can’t boo Kasey Palmer
You’re just a bunch of Clive EakinsBTA has longish braids/breads so they may get confused as they aren't too smart
Yeah, I just hope we, you know, kick it up the other end, and just stick one right in their fucking goal hole!I like the bit where we score the ball in the goal
Yeah, I just hope we, you know, kick it up the other end, and just stick one right in their fucking goal hole!
Was right in front of me that. One of the most baffling reds I’ve ever seen. Their lad nutted kitching about 3x and kitching just stood thereThat was the League game on Boxing Day where Kitch was sent off for being headbutted, Allen was clotheslined in the cup replay at home
Scabby stadium as well, awful place
Only a small number have this problem. The same may be said of our fan base. The good thing is that it was dealt with.Hope we tonk these racist bellends 8-0
And I hope whoever was with us last season hasn’t forgot their centre halves cowardly elbow on Jamie Allen which ruled him out for months
Agreed.Only a small number have this problem. The same may be said of our fan base. The good thing is that it was dealt with.
We use cookies and similar technologies for the following purposes:
Do you accept cookies and these technologies?
We use cookies and similar technologies for the following purposes:
Do you accept cookies and these technologies?