AI Video Reviewer – Content Curation Made Easy

The Need to Streamline the Content Curation Process

As the availability and demand for media content continues to explode, companies that deal with large volumes of media assets are faced with the recurring challenge of having to filter out content to meet distribution guidelines and requirements. Oftentimes, this translates into unreasonable amounts of human labor dedicated to manually identifying and editing out instances of questionable content. Too often this labor utilizes relatively scarce and costly resources like video editors along with their associated high-power equipment, stealing time from true value-added creative tasks.

Estimates show that the average medium to large-sized company in the media and entertainment industry dedicates somewhere between 4–10 hours of editing time per hour of content to the curation process. With ever-increasing volumes of content being produced along with the rapidly growing universe of media outlets, the need for a solution that would help companies streamline the rather mundane process of content curation has never been greater.

The AI Video Reviewer Tool

The AI Video Reviewer is an Artificial Intelligence Machine Learning (AI/ML) powered smart review tool that helps companies streamline and automate their content curation processes. It is a web-based solution that can be used by non-editorial staff to search for and mark specific vocabulary and imagery in video assets. The AI Video Reviewer is an ideal solution for companies that handle large volumes of video content that require scrupulous editing to adhere to distribution requirements.

Screenshot 1: Asset Management Page

How The Tool Works

The AI Video Reviewer is a web-based application that can be run from any web browser, at any location, freeing the curation effort from requiring any geographic or on-premise locality.

Upon sign-in, a user is taken to a straightforward asset management interface that provides an upload utility for their videos and a list of content available for review.

Built-in customization for transcribed word identification is supported, and the tool is extensible to recognize other imagery through custom models or more sophisticated AI/ML such as scene detection, sentiment analysis, etc. (contact TrackIt for customization services).

After a user selects a video, the AI Video Reviewer presents an easy-to-use video player interface that allows them to quickly identify and mark items of interest for deletion, retention, or adding comments for editors to then act on. Keyboard shortcuts to jump to marked occurrences on the timeline are available for operator efficiency.

Screenshot 2: Review Page with questionable content detected on the left and a custom video player

Once a video review is complete, users have the choice to export Marker/Edit Decision Lists that can be used by video editors to make final cuts and edits.

Screenshot 3: Download pop-up

AWS Service Used

The following AWS Services were used to build the AI Video Reviewer:

  • Amazon Rekognition: Used to analyze video from the ingested content for segment detection (to detect technical cues and shots) and content moderation (to detect graphic or questionable content).
  • Amazon Transcribe: Used to analyze audio from ingested content. Helps create a transcript file from the audio to identify and filter unwanted words.
  • AWS Amplify Video: Used to provide end-users with a playback video on the web-based UI. An HLS playlist is created using Amplify Video.
  • AWS Elemental MediaConvert: Used for video transcoding.
  • Amazon CloudFront: AWS’s content delivery network (CDN) used to deliver website content and data.
  • Amazon Cognito: Used for user authentication.
  • Amazon Dynamo DB: Used to store results of AI/ML jobs
  • AWS Lambda: Used to host code that processes metadata coming from API requests, Cloudwatch Events, or SNS Topics.
  • Amazon CloudWatch: Used to store logs.
  • Amazon SQS: Message queuing service used to process job results from Rekognition and Transcribe when a job is started, complete, or has failed. (AWS Lambda is used to process messages. Amazon SNS or Amazon CloudWatch events send their messages to the SQS Queue).
  • Amazon SNS: Used to send email notifications to the end-users and send job results from Rekognition/MediaConvert/Transcribe to the SQS Queue.
  • Amazon AppSync: Serves as the GraphQL API to handle user requests and internal requests to save, fetch, and delete metadata and also generate specific assets.
  • Amazon S3: Used to ingest video content and store generated assets (EDL, transcripts, Marker files, HLS playlist).

Conclusion

Companies that handle sizable volumes of content often find themselves dedicating excessive amounts of resources to filter out questionable content from video assets. Leveraging the AI Video Reviewer enables companies of all sizes to realize significant time and cost savings by streamlining and automating their content curation processes.

About TrackIt

TrackIt is an Amazon Web Services Advanced Consulting Partner specializing in cloud management, consulting, and software development solutions based in Marina del Rey, CA.

TrackIt specializes in Modern Software Development, DevOps, Infrastructure-As-Code, Serverless, CI/CD, and Containerization with specialized expertise in Media & Entertainment workflows, High-Performance Computing environments, and data storage.

TrackIt’s forté is cutting-edge software design with deep expertise in containerization, serverless architectures, and innovative pipeline development. The TrackIt team can help you architect, design, build and deploy a customized solution tailored to your exact requirements.