视频:IBM如何使用视频人工智能

了解更多关于真实世界的视频人工智能和应用流媒体的下一个事件.

观看这个小组的完整视频， AI101:从内容创作到交付:人工智能如何影响现代媒体，在流媒体会议视频门户.

阅读这段录音的完整文本:

大卫Clevinger: The typical use case that we've been seeing is media entities that have large back catalogs of content, 这是在他们没有复杂的元数据工具集的时候创建的, 不一定有合适的人来应用元数据, 没有考虑输出端的所有用例. 也许是历史内容.

一个非常具体的例子是我们为美网所做的工作. We actually took hundreds of thousands of video clips and photos and news 文章 and vocabulary terms and proper names and fed it to Watson and helped Watson to understand what tennis was about so that it could do things like, 当你听到阿什这个词的时候, 是大写的a -s-h-e, 阿瑟·阿什, 而不是小写字母a-s-h. 所以在这方面有很多培训. The output then became our ability to create clips based on what was happening with an event, 也可以用来描述历史视频.

That's critical for companies with large media back catalogs who then optimize that moving forward. You can apply it to live, of course, but that's a typical use case that we see.

这是一个递归学习系统. 所以我们选取了一组视频资产的横截面, 向华生描述过, 说, “事情就是这样. 这就是这个玩家，这就是他们所说的.“我们能够在其他非结构性资产上放开手脚, 让它说出它以为找到了什么, 然后我们可以修正它.

所以我们基本上能够训练它来理解网球. 然后输出是, we could then turn it loose on a bunch of different kinds of outputs for the client. 这就是我的想法.

Nadine Krefetz: 输出是?

大卫Clevinger: 封闭字幕，视频剪辑，激动人心的评分. I know you've got a video here that talks about the Masters and some work we've done there, 但我们可以做一些事情，比如倾听人群的声音，然后说, “这一定很令人兴奋, 因为人群在这个时候制造了很多噪音.“所以我们能够把它变成一个兴奋的分数. But we wouldn't be able to do that if we didn't help the algorithm understand what it was looking at and how it should be thinking about that body of work.

Nadine Krefetz: So you were training the algorithm to get smarter and smarter, and then you let it go?

大卫Clevinger: 完全. 然后我们就把它放了，让它走了. And that's the idea: to get it to the point where you can just turn it loose and let it run and them move onto the next one.