Spot Ai, Inc.

Nathaniel Paul Lee

Kevin Tajeran

Jordan Hart

Cameron Akhavan

Dunchadhn Hanley Broer Lyons

Julie Anne Noble

Amrish Sushil Kapoor

Methods, systems, and computer programs are presented to perform semantic analysis of video data for event detection and validation. One method includes an operation for training a machine-learning model with text-image pairs to create a semantic model. The semantic model generates text embeddings based on text describing events and image embeddings from video frames. The system calculates similarity values between text and image embeddings to determine event occurrences when the similarity exceeds a predetermined threshold. The system enables precise event detection by analyzing object relationships and attributes within video frames, reducing false alarms and enhancing monitoring efficiency. Further, these techniques can be used to detect any event describable by human text or by some image examples.

Growing community of inventors

San Francisco, CA, United States of America

Nathaniel Paul Lee