/Patent Tracker
GooglePatent applicationAI & softwareInterest 6/10

Google patents video analysis that focuses on objects, not just pixels

Google describes a method for analyzing video by breaking it into small blocks called tokens that represent either objects or background. The system reduces the amount of background data processed and uses a specific attention mechanism to focus on the objects, helping the computer understand what is happening in the video more efficiently.

Why it mattersThis approach could make video understanding tools faster and more accurate by allowing computers to ignore unimportant background details and focus on the main subjects.

In the filing’s own words

The technology provides approaches for use in classifying video data. This includes obtaining input object detections for a video segment having a plurality of video frames ( 2102). The system identifies, based on the object detections, a set of foreground tokens and a set of background tokens according to object locations in one of the plurality of video frames ( 2104). Each foreground token and each background token is a nonoverlapping space-time token ( 2104). The system downsamples the set of background tokens to obtain a reduced set of background tokens ( 2106). The system applies the set of foreground tokens and the reduced set of background tokens to an object-aware attention module to obtain updated features of patch tokens associated with the frame of the plurality of video frames ( 2108). The updated features of the patch tokens can then be used to perform a video processing task ( 2110).

What exactly they claim (claim 1)

1. A computer-implemented method for use in classifying video data, the method comprising: obtaining, by one or more processors, input object detections for a video segment having a plurality of video frames; identifying, by the one or more processors based on the object detections, a set of foreground tokens and a set of background tokens according to object locations in a frame of the plurality of video frames, wherein each foreground token and each background token is a nonoverlapping space-time token; downsampling, by the one or more processors, the set of background tokens to obtain a reduced set of background tokens; applying, by the one or more processors, the set of foreground tokens and the reduced set of background tokens to an object-aware attention module to obtain updated features of patch tokens associated with the frame of the plurality of video frames; and using, by the one or more processors, the updated features of the patch tokens to perform a video processing task.

Facts

Company
Google (Google LLC)
Official title
USING EXTERNAL OBJECT DETECTIONS IN TRANSFORMER-BASED ACTION RECOGNITION
Publication number
US20260279047A1
Application number
19165690
Filed
Feb 1, 2024
Published
Sep 17, 2026
Inventors
4
Claims
22

Classified under

G06V 20/41 Physics & computingG06V 10/82 Physics & computingG06N 3/045 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google 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.