SCENE ANNOTATION USING MACHINE LEARNING

Patent №

US 11,636,673

Granted

2023-04-25

Filed 2018

Owner

SONY INTERACTIVE ENTERTAINMENT INC.

Lab

AI components

3

nlp · vision · speech

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16177214

A system enhances existing audio-visual content with audio describing the setting of the visual content. A scene annotation module classifies scene elements from an image frame received from a host system and generates a caption describing the scene elements. A text to speech synthesis module may then convert the caption to synthesized speech data describing the scene elements within the image frame

Natural languageVisionSpeechG06F 16/65A63F 13/60G06F 16/55G06N 3/0442G06N 3/045G06N 3/0455G06N 3/0464G06N 3/0475+19 more

AI classification

Natural language1.00
Speech1.00
Vision0.96
AI hardware0.12
Knowledge representation0.08
Machine learning0.05
Evolutionary computation0.02
Planning0.00

Ownership

SONY INTERACTIVE ENTERTAINMENT INC.

assignment · 487060784

Assignors

KRISHNAMURTHY, SUDHA, ADAMS, JUSTICE, JATI, ARINDAM, OMOTE, MASANORI, ZHENG, JIAN

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC