Get the newsletter
Microsoft · AI / ML · Filed Mar 27, 2025 · USPTO published Oct 1, 2026 · Oct 1 release

Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video

Spotting a small, fast-moving object in a blurry video clip is one of the harder problems in computer vision. Microsoft's latest patent applies a relay-race approach, where each piece of an AI model hands off what it learned to the next, building up a richer picture of what's happening across time.

A person reacts to a spider in a video frame, illustrating a scenario for object detection in video. Drawing from patent filing US 2026/0301374 A1.
A person reacts to a spider in a video frame, illustrating a scenario for object detection in video.All 17 drawings ↓
Publication number
US 2026/0301374 A1(US20260301374A1)
Applicant
Microsoft Technology Licensing, LLC
Filed · Published
Mar 27, 2025 · Oct 1, 2026
Inventors
Qi ZHANG, Fuxun YU, Rishi MADHOK, Nikolaos KARIANAKIS
Status when we published
Waiting for an examiner
Document
20 claims
US classification
382/159
Examiner
DUONG, JOHNNYKHOI BAO (Art Unit 2667)

How Microsoft's video AI tracks blurry, tiny, or hidden objects

Imagine you're watching security camera footage of a parking lot at night. A small figure moves quickly across the corner of the frame, blurred by speed and half-hidden by a parked car. A single still-image AI would likely miss it entirely. That's the problem Microsoft is trying to fix here.

The patent describes an AI model that's broken into a series of smaller sub-models, each one responsible for a different video frame. As one sub-model finishes analyzing its frame, it passes a summary of what it found to the next sub-model, which uses that context when examining the following frame. By the end of the chain, the model has a much more complete picture of what's moving, where, and how fast.

The result can be used for tasks like labeling what's in a video, drawing boxes around objects, or segmenting the scene into regions. Think of it as giving the AI a short-term memory so it can connect the dots across time, rather than treating each frame as a brand-new puzzle.

From the filing · CLAIM 1
… 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 …

Translation: The system splits video frames across multiple smaller networks and passes data between them.

How the subnetworks pass context from frame to frame

The system works by distributing individual video frames across a series of subnetworks (smaller, specialized components inside a larger AI model). Each subnetwork handles one frame at a time, but it doesn't work in isolation.

Here's the flow the patent describes:

  • The system pulls a sequence of video frames from a clip.
  • Each frame is assigned to its own subnetwork in a fixed order.
  • The subnetwork extracts initial features from its frame (essentially a compressed mathematical description of what it sees: edges, shapes, colors, motion patterns).
  • Those features, plus intermediate features passed forward from the previous subnetwork, are combined and processed.
  • The final subnetwork in the chain produces final features that represent the whole sequence.
  • Those final features feed into a task-specific output layer for detection, classification, or segmentation.

The key innovation is the propagation of temporal features, meaning information about earlier frames is carried forward through the chain rather than discarded. This is what helps the model handle motion blur (where a fast-moving object appears smeared), occlusion (where an object is partially hidden), and small object size (where a single-frame snapshot may not carry enough pixels to be reliable).

The patent doesn't tie itself to a specific model architecture, which keeps the claims fairly broad.

From the filing · THE ABSTRACT
Objects can be difficult to detect in videos due to motion blur, occlusion, and/or having a relatively small size.

Translation: Video analysis struggles when objects are blurry, hidden, or too small.

What this means for security cameras and video AI tools

Video AI is everywhere: in security systems, sports analytics, autonomous vehicles, and content moderation. The persistent weak point in most deployed systems is exactly what this patent addresses. Small, fast, or partially hidden objects are exactly what cause false negatives in real-world footage, and those misses carry real consequences in safety or surveillance contexts.

For everyday users, this kind of technology could mean a home security camera that actually catches the small detail that matters, or a video conferencing tool that correctly tracks multiple people moving around a room. The patent is filed broadly enough that if granted, it could cover a wide range of implementations where temporal context is passed between AI subnetworks during video analysis, which describes a pattern common to many modern video AI products.

Microsoft's 33rd filing we've tracked since May in AI teams working together builds on ideas like meeting role assistants and a self-managing security trio.

Source: US 2026/0301374 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Microsoft patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 17 sheets

17 drawing sheets from US 2026/0301374 A1 · click any drawing to enlarge

Object detection model architecture, drawing sheet 1 from US 2026/0301374 A1
Sheet 1 Object detection model architecture
Cross-level feature fusion details, drawing sheet 2 from US 2026/0301374 A1
Sheet 2 Cross-level feature fusion details
Video frame with a spider, drawing sheet 3 from US 2026/0301374 A1
Sheet 3 Video frame with a spider
Second video frame with spider, drawing sheet 4 from US 2026/0301374 A1
Sheet 4 Second video frame with spider
Third video frame with spider, drawing sheet 5 from US 2026/0301374 A1
Sheet 5 Third video frame with spider
Fourth video frame with spider, drawing sheet 6 from US 2026/0301374 A1
Sheet 6 Fourth video frame with spider
Fifth video frame with spider, drawing sheet 7 from US 2026/0301374 A1
Sheet 7 Fifth video frame with spider
Processing two video frames, drawing sheet 8 from US 2026/0301374 A1
Sheet 8 Processing two video frames
Show the other 9 sheets
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 9
Sheet 9
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 10
Sheet 10
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 11
Sheet 11
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 12
Sheet 12
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 13
Sheet 13
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 14
Sheet 14
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 15
Sheet 15
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 16
Sheet 16
Microsoft Patents a Chain-of-Networks Approach to Spotting Objects in Video patent drawing, sheet 17
Sheet 17
Patent filing page

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.