Initial Observations:

Preliminary Data Exploration

Visually exploring a random sampling of roughly 200 or so Bad Guy videos and trying to intuit the results. Video © their respective owners, courtesy YouTube.
“duck, duck … piano?” Video © their respective owners, courtesy YouTube.

Edits, Structure, Pattern.

Example time series for a single channel value
Example time series for a 3 channel value. Our real data was hundreds of channels per sample.
Example dimensionality reduction of our sample 3 channel data above. Being able to go from multi channel to single channel allowed us to use off the shelf DTW frameworks meant for audio. Its lossy, but it works.
Exploring similarity via Dynamic Time Warping in Synopsis Inspector. Video © their respective owners, courtesy YouTube.

Ontology and Labelling

Screenshot of video labeling interface with videos blurred out. Image courtesy IYOIYO Studios.

Prototype to Production

Wrapping it up

Special Circumstances is a Computational Cinematography R&D company. We build next generation tools for film makers.

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Special Circumstances

Special Circumstances

Special Circumstances is a Computational Cinematography R&D company. We build next generation tools for film makers.

More from Medium

Corruption and Collusion: How Airbnb is selling out timeshare owners.

Airbnb selling data to wyndham

Similar Lifestyles, Different Dynamic

Abandoning Niceness in Volunteer Engagement

Demand Generation vs Lead Generation