Adobe Inc.
Contextualized Video Segment Selection For Video-Filled Text

Abstract:

A video editing application generates video-filled text based on context-sensitive video segments. For example, the video editing application receives a text selection including multiple characters. A text selection context that identifies a characteristic of the text selection is determined, the context including a category of the text selection and a tag identifying an entity associated with the text selection. Scores are computed for multiple video segments, each score indicating a match between an attribute of the respective video segment and the text selection context. Video segments with attributes that match the context are selected, based on a comparison of each score to a threshold. The video editing application generates a composite video that includes a combination of a selected video segment and a character from the text selection, the combination including an outline of the character and the selected video segment.