This looks like the inverse of the usual "tell we what's in this video" design - Dextro seems to want you to ask it if something their system already knows about is in a video.
I think I'd rather just submit a video and have all the matches and their confidence / salience (not sure that these are the same thing).
Yes! General tagging of videos with all possible tags is great for media discovery, but we've built our system with data analysis in mind. We want to be useful for those who want to analyze photo and video datasets when they already know what their query is.
We've found that most of the value is in the latter. For example, our system helps answer:
1) on a publisher video server, which videos were about automotive?
Can we package those ads off to car brands?
2) how many people took photos of my brand's product on instagram
after our marketing campaign?
3) what were pedestrian traffic patterns like outside
our store based on the CCTV system?
It seems like if you're going to support querying you should also support "just give me all the content tags", even if that's implemented as running all the individual queries. Especially for example number 1 you're going to find that publishers aren't thinking "Do I have automotive videos to package up for a car brand?", they're thinking "I have no idea what content I have in my network, what broad categories does it fall into?".
My employer, SET Media [1], has built out our own ML / CV system that applies a taxonomy of a bit over 1000 tags to several million videos. We add new videos and re-compute existing results multiple times a day. It's been invaluable for us to be able to query for both a specific tag as well as to see all the tags (and their confidences) that are applied to a video.
I think I remember talking to David about this in SF a few years ago, or at a YEI event or something. I interned at Numenta and he was aking me some ML questions. Looks like y'all have come a long way. Nice job!
You might find some partners for a tool like this in music video publishers, or advertisers looking to build competitive intel. e.g. a database of all commercials with "X" in them, or all music videos with "Y" in them (for product placement). Just a thought.
6 comments
[ 2.6 ms ] story [ 21.1 ms ] threadI think I'd rather just submit a video and have all the matches and their confidence / salience (not sure that these are the same thing).
We've found that most of the value is in the latter. For example, our system helps answer:
Our full API accepts the major video formats.
My employer, SET Media [1], has built out our own ML / CV system that applies a taxonomy of a bit over 1000 tags to several million videos. We add new videos and re-compute existing results multiple times a day. It's been invaluable for us to be able to query for both a specific tag as well as to see all the tags (and their confidences) that are applied to a video.
[1] www.set.tv
I think I remember talking to David about this in SF a few years ago, or at a YEI event or something. I interned at Numenta and he was aking me some ML questions. Looks like y'all have come a long way. Nice job!
You might find some partners for a tool like this in music video publishers, or advertisers looking to build competitive intel. e.g. a database of all commercials with "X" in them, or all music videos with "Y" in them (for product placement). Just a thought.