Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Representation learning from video with spatial audio

Representation learning from video with spatial audio

US Patent 11308329 · Granted Apr 19, 2022

Estimated economic value: $123,565,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Spoken language recognition2025
Self-supervised audio-visual learning for correlating music and video2025
Self-supervised audio-visual learning for correlating music and video2025
Music-aware speaker diarization for transcripts and text-based video editing2025
System and method for utilizing perturbation in a multimodal environment2024
Automatic recognition of visual and audio-visual cues2024
Localization of narrations in image data2024
Video segment selection and editing using transcript interactions2024
Snap point video segmentation identifying selection snap points for a video2024
Generating action tags for digital videos2024
Defending multimodal fusion models against single-source adversaries2024
Thumbnail video segmentation identifying thumbnail locations for a video2024