The problem is when they start doing in stream ads, that will require something new. That said, people have been doing that with cable for a while, it’ll be real interesting to see what clever stuff comes out to detect them in stream
This is something that would be a surprisingly good use case for machine learning. Fingerprint the ads by watching ahead in the stream, then skip that section.
Actually, I think older algorithmic methods will work. I think that’s how TiVo worked. The annoying part is you’ll have to wait a bit at the start of the video.
I assume something similar to sponsor block, some algorithm to identify ad segments and some user feedback to confirm.
Unless I’m mistaken as to how sponsor block works?
People will watch the videos, report the segments that are sponser slots, and then when people watch the video they can upvote or downvote the accuracy of the report.
In stream ads would be a hard one to tackle because YouTube would likely inject them randomly into the stream to boost engagement (readas, prevent people skipping them easily).
if they were randomly placed, then couldnt you have a sponsor-block type system where instead of the ad segments being marked and skipped, information about the video is externally stored somewhere (like perhaps a really low res screenshot of the video every couple seconds, or some number generated algorithmically by a frame of video), and the results should be the same for all users for the actual video part, but if the ads are placed randomly, the ad section will suddenly not match the data other users had, prompting the video to skip until it matches again (with a buffer included if they remove the ability to move forward)
Take two copies of the same video, diff them and only keep the parts that match.
We can also build up a database of as signatures to automatically identify them without requiring a watermark - we already have the technology to do this for detecting intro sequences for skipping.
The problem is when they start doing in stream ads, that will require something new. That said, people have been doing that with cable for a while, it’ll be real interesting to see what clever stuff comes out to detect them in stream
It’ll require a new mother fucking video platform. We need to just collectively let YouTube die and move on.
There’s Rumble
I fuckin hate Nazis.
Then drown them out with enough non-Nazis, that’s what youtube does
The enemy of my enemy is my friend.
Haven’t heard anything bad about Nebula
Except the price?
This is something that would be a surprisingly good use case for machine learning. Fingerprint the ads by watching ahead in the stream, then skip that section.
Actually, I think older algorithmic methods will work. I think that’s how TiVo worked. The annoying part is you’ll have to wait a bit at the start of the video.
Audio is stupidly easy to fingerprint and identify. It would be glorious if we used the very same dumbass technology to identify ad segments as they use to robo-copyright-claim creators for including a 11 second snippet of a radio ad that’s period authentic to the historical media they’re reviewing. Just take that shit and turn it right against them.
I assume something similar to sponsor block, some algorithm to identify ad segments and some user feedback to confirm. Unless I’m mistaken as to how sponsor block works?
Sponser block works via user input
People will watch the videos, report the segments that are sponser slots, and then when people watch the video they can upvote or downvote the accuracy of the report.
In stream ads would be a hard one to tackle because YouTube would likely inject them randomly into the stream to boost engagement (readas, prevent people skipping them easily).
deleted by creator
if they were randomly placed, then couldnt you have a sponsor-block type system where instead of the ad segments being marked and skipped, information about the video is externally stored somewhere (like perhaps a really low res screenshot of the video every couple seconds, or some number generated algorithmically by a frame of video), and the results should be the same for all users for the actual video part, but if the ads are placed randomly, the ad section will suddenly not match the data other users had, prompting the video to skip until it matches again (with a buffer included if they remove the ability to move forward)
You don’t need anything so complicated.
Take two copies of the same video, diff them and only keep the parts that match.
We can also build up a database of as signatures to automatically identify them without requiring a watermark - we already have the technology to do this for detecting intro sequences for skipping.