Thanks for the tip!
Any theories on how they choose the "key moment" segments? The Feynman video has 2.7M views, which would be plenty to evaluate the frequency of watch/rewind/pause/deeplink events.
Any theories on how they choose the "key moment" segments? The Feynman video has 2.7M views, which would be plenty to evaluate the frequency of watch/rewind/pause/deeplink events.
- https://twitter.com/jugurthahadjar/status/127667009860295475...
- https://twitter.com/jugurthahadjar/status/127667126411615846...
Reproduced here:
>If a talk doesn't provide a link to slides but shows them on the screen, I watch it muted at 16x with "Video Speed Controller". 50 minutes become ~3 minutes and it's easier to decide if the talk is worth the time and/or has high information density in the topic of interest.
>If there are no slides linked nor shown, I use "Youtube Captions Search" to search for expressions of interest in the video, and go straight to where they're mentioned. If I like the treatment of the subject, I make a note to invest in that video and watch it.
There are many articles when you search for "google key moments algorithm" which relay a "recent Google announcement" without a source, or a link.
However, here's a link to a thread: https://support.google.com/youtube/thread/18138167/youtube-t...
>[November 23 2020] Testing automatic video chapters: We want to make it easier for people to navigate videos with video chapters, so we are experimenting with automatically adding video chapters (so creators don't have to manually add timestamps). We’ll use machine learning to recognize text in order to auto generate video chapters. We’re testing this out with a small group of videos. If your videos are impacted, you can opt out of this experiment and/or share feedback here. More on video chapters here.
So, searching for their own lingo "automatic video chapters" would yield more interesting results. Actually searching for "site:https://research.google/ automatic video chapters" returns interesting papers
"Automatic Generation of Two-Level Hierarchical Tutorials from Instructional Makeup Videos", https://storage.googleapis.com/pub-tools-public-publication-...
Or this one:
"Speech2Action: Cross-modal Supervision for Action Recognition": https://storage.googleapis.com/pub-tools-public-publication-...
https://youglish.com is a website where you enter a word, and it returns YouTube videos at the precise time that word is pronounced. Its goal is for people to "improve" their English.
I use it as a "Google for YouTube" returning videos that YouTube search functionality would probably never return.
For example, here's a search on Kubernetes on Youglish:
https://youglish.com/pronounce/kubernetes/english?
Here's the search on YouTube: https://www.youtube.com/results?search_query=kubernetes
Want to get fresh videos that mentioned Theranos? https://youglish.com/pronounce/Theranos/english?
I get access to extremely good content that would never have been recommended to me where the matter is actually discussed, escaping filter bubbles, and tacky/popular content pushed atop because the channel has a large audience, and quickly change language. https://youglish.com/pronounce/Uber/french?