Download PDF

Fuse Logo

Fuse Media is a Latino-owned, multicultural focused, multiplatform entertainment company. It unites cultures through colorful storytelling that celebrates our blended America. The minority-owned and managed company serves its millennial and Gen Z audience through a portfolio of streaming and television brands including Fuse, Fuse+, Fuse Backstage, Fuse Beat, FM (Fuse Music), Fuse Sweat and fuse.tv. Fuse Media also operates the Fuse Content Studio, its in-house production and distribution arm, as well as a growing branded content and live events business. For more information, readers can visit www.fusepress.tv


The Need For A Solution That Would Help Save Time In the Post-Production Editing Process 

The Fuse Media team was looking for a solution that would help the company realize significant time savings in its editing process. Being a media & entertainment company, Fuse Media handles huge volumes of content on a daily basis and one of the primary challenges it faces is the need to consistently detect and filter out questionable content (swear words, graphic imagery, nudity, etc.) during post-production. The company realized that it was dedicating too many human resources to accomplish this relatively mundane task in the editing process and started looking for a better solution.

“Like most organizations, we’re constantly battling resourcing and trying to find ways to work more efficiently. We found that the specific workflow we had was consuming a lot of human labor to accomplish. We figured there had to be a better way and started to search for solutions. We knew AWS had some ML/AI libraries that would be beneficial here so we reached out to AWS and started talking about this design concept. That’s when they brought TrackIt into the fold and we started to really flesh out the idea of how we could work more efficiently with machine learning and AI.”Bejon Parsinia, Senior Vice President, Technology, Fuse Media

The Fuse Media team decided to partner with TrackIt, on AWS’s recommendation, to implement a pipeline that would allow them to leverage machine learning and AI to streamline and accelerate their post-production editing process. 

Implementation

Architecture
Solution Architecture

The TrackIt team helped Fuse Media build a solution that leverages Amazon Rekognition and Amazon Transcribe, AWS’s machine learning and AI services, to detect questionable content in media files. The TrackIt team also assisted Fuse Media in building a custom, web-based video player application specifically designed for content curation and review. With the implemented solution, instances of questionable content detected are displayed on an easy-to-use web interface where editing staff can easily review clips, accept/reject identified markers, and add further notes if necessary.

“We knew we wanted to leverage the Amazon Rekognition ML library in particular. TrackIt came on board to help us realize what other components would be needed to make the overall workflow a reality. We had the conceptual idea of what we wanted to accomplish and how to go about it. TrackIt helped us define a meaningful workflow that we could actually implement.” – Bejon Parsinia, Senior Vice President, Technology, Fuse Media

Screenshot 1
Screenshot 1: Dashboard with list of ingested files
Screenshot 2
Screenshot 2: Review page with potential unwanted items detected on the left and a custom video player on the right
Screenshot 3
Screenshot 3: Download pop-up – Markers file in XML/CSV format & Edit Decision List file

TrackIt’s Expertise & Results

The Fuse Media team was very pleased with TrackIt’s expertise in helping them implement a workflow that would help them significantly accelerate their post-production editing process. Bejon Parsinia, Senior Vice President of Technology at Fuse Media highlighted the time savings the company was going to realize through this solution:

“Depending on the type of content that we’re taking in for editing, we’ll be saving, on average, anywhere from 6-10 human hours of time in the edit space.” – Bejon Parsinia, Senior Vice President, Technology, Fuse Media

“Our team is absolutely excited about the workflow that’s been implemented. This not only saves time from an editing standpoint but there are other teams that are going to realize time savings from this solution as well. Before it was a back-and-forth exchange between multiple teams. Now we have a nice web UI that people can just click through to get their job done rather than having to go back and forth over email, which was not efficient.” – Bejon Parsinia, Senior Vice President, Technology, Fuse Media


A Solution for the M&E Community in General

“It was interesting because after hearing our use case, the AWS team was surprised that this had not come up before. They were pretty excited about this solution’s applicability to other partners in the media space. I think that this solution we’ve put together with TrackIt can certainly benefit the media and entertainment community in general. It obviously is serving a need and I’m pretty sure other people in the media space would want to benefit from a workflow similar to this.” – Bejon Parsinia, Senior Vice President, Technology, Fuse Media

Q. Would you Recommend TrackIt to other companies looking to implement similar solutions? Why?

“I’d absolutely recommend TrackIt to other companies. They’re professional, they understand the inner workings of AWS and a lot of the components that need to come together to build cohesive workflows. They’re not afraid to roll up their sleeves, get their hands dirty, and figure things out when they don’t necessarily have the required depth on a particular component. They are willing to stretch into areas that they haven’t worked in before. They’ve been wonderful to work with and whenever we’ve had an idea, they’ve had an answer.” – Bejon Parsinia, Senior Vice President, Technology, Fuse Media


Challenges:

  • The need for a solution to help save time In the post-production editing process

Solution:

  • ML/AI pipeline leveraging Amazon Rekognition and Amazon Transcribe

Outcomes:

  • Significant time savings in the post-production editing process thanks to the implemented ML/AI pipeline
  • A solution with the potential to benefit the M&E community in general

Download PDF