Recognizing salient video events through learning-based multimodal analysis of visual features and audio-based analytics

US10679063B2 · kind B2 · utility

Assignee

• SRI International · US

Inventors

• Hui Cheng · Bound Brook, US
• Ajay Divakaran · Woburn, US
• Elizabeth Shriberg · Berkeley, US
• Harpreet Singh Sawhney · Plainsboro, US
• Jingen Liu · Plainsboro, US
• Ishani Chakraborty · Seattle, US
• Omar Javed · Willingboro, US
• David Chisolm · Dallas, US
• Behjat Siddiquie · College Park, US
• Steven S. Weiner · Yeadon, US

Key dates

• Filing date: Sep 4, 2015
• Grant date: Jun 9, 2020
• Expiry date: Jan 31, 2038

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04N21/8549
• WIPO field: Audio-visual technology
• WIPO sector: Electrical engineering

Abstract

A computing system for recognizing salient events depicted in a video utilizes learning algorithms to detect audio and visual features of the video. The computing system identifies one or more salient events depicted in the video based on the audio and visual features.