United StatesTechnology and telecom2021 – ongoingTripleLift
Computer vision for reviewing product-placement opportunities
TripleLift reduced video analysis time by about 50% with computer vision
Problem
Finding suitable product-placement scenes required staff to watch videos. This review competed with creative work for the team's time.
Approach
TripleLift built a video-analysis pipeline using custom models, Amazon SageMaker, and Amazon Rekognition. Computer vision identified potential placement opportunities. Creative staff selected placements and composited brand artwork into the footage.
Results
Takeaway
Automating the initial review left TripleLift's creative team more time for creative work. Staff still selected placements and edited scenes.
Categories
- Industry
- Technology and telecom
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Company's own claim
Sources
Source summaries
AWS described TripleLift's automated search for product-placement opportunities. A company engineer said the initial review took about half the time of manual work. The page carries no date; the Internet Archive first saved it on June 22, 2021.
Full details are in the original sources.