/Patent Tracker
MicrosoftPatent applicationAI & softwareInterest 4/10

Microsoft patents video object detection using split neural networks

Patent drawing
Patent drawing from the official filing.

Microsoft has filed a patent application for a method that detects objects in videos by splitting the footage into frames and processing them through different parts of a machine learning model. The system shares information between these parts to help identify objects that might be blurry, hidden, or small. The final output can be used for tasks like classifying the video or locating specific items within it.

Why it mattersThis technique could make video analysis more accurate in real-world applications where objects are hard to see, such as in security footage or autonomous driving systems.

In the filing’s own words

This document relates to detecting objects in videos. Objects can be difficult to detect in videos due to motion blur, occlusion, and/or having a relatively small size. The disclosed techniques can assign frames of a video to respective subnetworks of a machine learning model. Visual features of the frames can be processed by the subnetworks together with temporal features propagated from preceding subnetworks. The final features produced by the machine learning model can be employed for tasks such as video classification, object detection, and/or semantic segmentation.

What exactly they claim (claim 1)

1. A computer-implemented method comprising: obtaining video frames of a video; assigning individual video frames of the video to respective subnetworks of a machine learning model; extracting initial features from respective video frames of the video; inputting the initial features to respective assigned subnetworks of the machine learning model; propagating intermediate features among the subnetworks; obtaining final features produced by a final subnetwork of the machine learning model; processing the final features using the machine learning model to produce a result; and outputting the result.

Facts

Company
Microsoft (Microsoft Technology Licensing, LLC)
Official title
OBJECT DETECTION FOR VIDEO APPLICATIONS
Publication number
US20260301374A1
Application number
19092595
Filed
Mar 27, 2025
Published
Oct 1, 2026
Inventors
4
Claims
20

Classified under

G06V 10/7715 Physics & computingG06V 10/82 Physics & computingG06V 20/46 Physics & computing

More from Microsoft in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.