17967703. VISUAL AND TEXT SEARCH INTERFACE FOR TEXT-BASED VIDEO EDITING simplified abstract (Adobe Inc.)

VISUAL AND TEXT SEARCH INTERFACE FOR TEXT-BASED VIDEO EDITING

Organization Name

Adobe Inc.

Inventor(s)

Lubomira Assenova Dontcheva of Seattle WA (US)

Dingzeyu Li of Seattle WA (US)

Kim Pascal Pimmel of Seattle WA (US)

Hijung Shin of Arlington MA (US)

Hanieh Deilamsalehy of Seattle WA (US)

Aseem Omprakash Agarwala of Seattle WA (US)

Joy Oakyung Kim of Sunnyvale CA (US)

Joel Richard Brandt of Venice CA (US)

Cristin Ailidh Fraser of Seattle WA (US)

VISUAL AND TEXT SEARCH INTERFACE FOR TEXT-BASED VIDEO EDITING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17967703 titled 'VISUAL AND TEXT SEARCH INTERFACE FOR TEXT-BASED VIDEO EDITING

Simplified Explanation

The patent application describes a system for searching and navigating video transcripts using both visual and text queries.

• Visual search for frames matching a freeform text query
• Text search for matching words in the transcript or video tags
• Display of search results in tiles for easy navigation
• Selection of a search result tile navigates to the corresponding part of the transcript

Key Features and Innovation

• Integration of visual and text search for video transcripts
• Seamless navigation through search results for efficient browsing
• Enhanced user experience with a combination of visual and text cues

Potential Applications

• Video content management systems
• Educational platforms for searching through video lectures
• Legal and forensic analysis of video evidence

Problems Solved

• Efficient searching and navigation of video transcripts
• Integration of visual and text cues for enhanced user experience
• Streamlining the process of finding specific information within video content

Benefits

• Improved search functionality for video transcripts
• Enhanced user experience with a combination of visual and text search
• Efficient navigation through video content for quick access to relevant information

Commercial Applications

The technology can be applied in video content platforms, educational software, and legal analysis tools to enhance search and navigation capabilities, providing a more efficient and user-friendly experience for users.

Prior Art

No specific information on prior art related to this technology is provided in the abstract.

Frequently Updated Research

There is no information on frequently updated research relevant to this technology in the abstract.

Questions about Visual and Text Search Interface for Video Transcripts

Question 1

How does the system differentiate between visual and text search queries in the video transcript interface?

The system uses frame embeddings for visual search and matches them with the corresponding embedding of the freeform text query. It also conducts a text search for matching words in the transcript or video tags.

Question 2

What are the potential applications of this technology beyond video content management systems?

This technology can also be utilized in educational platforms for searching through video lectures and in legal and forensic analysis of video evidence.

Original Abstract Submitted

Embodiments of the present invention provide systems, methods, and computer storage media for a visual and text search interface used to navigate a video transcript. In an example embodiment, a freeform text query triggers a visual search for frames of a loaded video that match the freeform text query (e.g., frame embeddings that match a corresponding embedding of the freeform query), and triggers a text search for matching words from a corresponding transcript or from tags of detected features from the loaded video. Visual search results are displayed (e.g., in a row of tiles that can be scrolled to the left and right), and textual search results are displayed (e.g., in a row of tiles that can be scrolled up and down). Selecting (e.g., clicking or tapping on) a search result tile navigates a transcript interface to a corresponding portion of the transcript.