Improving YouTube video thumbnails with deep neural nets
youtube-eng.blogspot.com
Improving YouTube video thumbnails with deep neural nets
1–10 of 26 posts
Re: Improving YouTube video thumbnails with deep neural nets
#2I wonder if they included sexy images in their negative training sets -- many videos accrue millions of views (and ad dollars) by having a few frames of cleavage interspersed with other (often derivative) footage.
It would be great if their algorithm picked a thumbnail that reflected the entire video, not just a few frames specifically chosen to game people's compulsive clicking.
Re: Improving YouTube video thumbnails with deep neural nets
#3There's an outside company that was working on this: Neon Labs (https://www.neon-lab.com/).
Their insight is that not only are there images that are "high-quality", but also images that are positive. Positive images get more clicks, over just a decent image. I wonder if that information is encoded in the RNN in some way.
(This is where I'd normally rant about RNNs and other ML techniques hiding this information from their creators by locking it up inside the black box, but I'll save that for another day.)
Re: Improving YouTube video thumbnails with deep neural nets
#4I wonder if they included sexy images in their negative training sets -- many videos accrue millions of views (and ad dollars) by having a few frames of cleavage interspersed with other (often derivative) footage. It would be great if their algorithm picked a thumbnail that reflected the entire video, not just a few frames specifically chosen to game people's compulsive clicking.
They stated that the negative training set was constructed by randomly sampling frames from the video.
If someone wants to game the thumbnails, then they will just manually select the thumbnail to use; and there are to many legitimate use cases for this ability for Youtube to remove it.
Re: Improving YouTube video thumbnails with deep neural nets
#5Seeing this run through an equivalent of the deep dream visualizer could be really interesting -- what _are_ people looking for in thumbnails? I'm having difficulty imagining what features would even be relevant in such a situation.
Re: Improving YouTube video thumbnails with deep neural nets
#6I wonder if they included sexy images in their negative training sets -- many videos accrue millions of views (and ad dollars) by having a few frames of cleavage interspersed with other (often derivative) footage. It would be great if their algorithm picked a thumbnail that reflected the entire video, not just a few frames specifically chosen to game people's compulsive clicking.
Is there a way YouTube could alter the "view count" to only include views where 100% of the video has been watched? May help cut down on videos with misleading thumbnails and/or titles.
Re: Improving YouTube video thumbnails with deep neural nets
#7I wonder if they included sexy images in their negative training sets -- many videos accrue millions of views (and ad dollars) by having a few frames of cleavage interspersed with other (often derivative) footage. It would be great if their algorithm picked a thumbnail that reflected the entire video, not just a few frames specifically chosen to game people's compulsive clicking.
Most of those are just manually selected thumbnails by the uploader. After uploading, YT gives you 3-5 thumbnails you can choose from.
Also, partnered accounts are allowed to upload custom thumbnails (which can be any image, not necessarily even a screenshot from the video).
Re: Improving YouTube video thumbnails with deep neural nets
#8I wonder if they included sexy images in their negative training sets -- many videos accrue millions of views (and ad dollars) by having a few frames of cleavage interspersed with other (often derivative) footage. It would be great if their algorithm picked a thumbnail that reflected the entire video, not just a few frames specifically chosen to game people's compulsive clicking.
Is there a way YouTube could alter the "view count" to only include views where 100% of the video has been watched? May help cut down on videos with misleading thumbnails and/or titles.
A better way to filter those out algorithmically would be to simply look at the thumbs-up vs thumbs-down ratio.
The ones with misleading titles/thumbnails often have far more down-votes than up-votes yet YouTube continues to show those as the highest recommended/relevant (I guess Google prefers click-throughs over user-satisfaction).
Re: Improving YouTube video thumbnails with deep neural nets
#9Seeing this run through an equivalent of the deep dream visualizer could be really interesting -- what _are_ people looking for in thumbnails? I'm having difficulty imagining what features would even be relevant in such a situation.
I'm guessing: "sharpness" of image, good saturation, presence of (smiling?) human faces, non-human mammals facing the camera, bare human skin (?)
(I agree that'd be cool.)
Re: Improving YouTube video thumbnails with deep neural nets
#10I wonder if they included sexy images in their negative training sets -- many videos accrue millions of views (and ad dollars) by having a few frames of cleavage interspersed with other (often derivative) footage. It would be great if their algorithm picked a thumbnail that reflected the entire video, not just a few frames specifically chosen to game people's compulsive clicking.
Is there a way YouTube could alter the "view count" to only include views where 100% of the video has been watched? May help cut down on videos with misleading thumbnails and/or titles.
> Is there a way YouTube could alter the "view count" to only include views where 100% of the video has been watched?
You wouldn't want to require 100%, as many people stop when a video starts rolling credits, or when it switches to a screen using annotations to link to other videos. But 50-75% would work well as a threshold to count "views".