Yes. There are 2 ways we do video search.

(1) Using a mobile device camera to recognize a video
IQ Engines can index a video, and make it visually interactive. So a user can use a mobile phone or tablet camera, point at a TV show or commercial, and the 2nd screen mobile phone or tablet can then take the user to a webpage or video. In other words, IQ Engines API can be used to make video interactive. To do this, we use the Training API to learn a video (typically a few frames per second), and then the video will be interactive via visual search with your API key.

You can view a demonstration of this in this video http://vimeo.com/31107943.  In the middle you will see a Chevy car commercial, and the mobile phone is visually recognizing the frames as they appear.  

(2) Using the API to index a video
Another application is to index a video with text. This will also work using IQ Engines API, and typically you would send a frame every few seconds, and you can quickly index with keywords an entire video. Because this often involves both computer vision and human crowdsourcing, it is important to specify a “custom question” with your API to the crowdsourcing node. For example, you may want to identify all the characters and objects in a video frame, so it is important for the crowd to understand that is the task you want done.