We've all struggled to find something WITHIN a specific video. Using our search algorithm, you can now find specific objects and interactions throughout a video, and get to the content that you were looking for much quicker.
How we built it
Using the search terms that you typed in or entered through voice recognition, we grab the most relevant videos using the AOL video API, extract the relevant keyframes, then run a machine-learning image and object classification algorithm to exactly determine the contents of the video. Using this information we construct a database of tags and timestamps, and allow you to jump to any point in the video that matches your search terms.
Built With
- aol
- aol-api
- aol-video
- machine-learning
- node.js
Log in or sign up for Devpost to join the conversation.