Abstract: Embodiments are directed to interactive tiles that represent video segments of a segmentation of a video. In some embodiments, each interactive tile represents a different video segment from a particular video segmentation (e.g., a default video segmentation). Each interactive tile includes a thumbnail (e.g., the first frame of the video segment represented by the tile), some transcript from the beginning of the video segment, a visualization of detected faces in the video segment, and one or more faceted timelines that visualize a category of detected features (e.g., a visualization of detected visual scenes, audio classifications, visual artifacts). In some embodiments, interacting with a particular interactive tile navigates to a corresponding portion of the video, adds a corresponding video segment to a selection, and/or scrubs through tile thumbnails.

Abstract: Embodiments are directed to techniques for interacting with a hierarchical video segmentation. In some embodiments, the finest level of the hierarchical segmentation identifies the smallest interaction unit of a video—semantically defined video segments of unequal duration called clip atoms. Each level of the hierarchical segmentation clusters the clip atoms with a corresponding degree of granularity into a corresponding set of video segments. A presented video timeline is segmented based on one of the levels, and one or more segments are selected through interactions with the video timeline (e.g., clicks, drags), by performing a metadata search, or through selection of corresponding metadata segments from a metadata panel. Navigating to a different level of the hierarchy transforms the selection into corresponding coarser or finer video segments defined by the level. Any operation can be performed on selected video segments, including playing back, trimming, or editing.

Abstract: Embodiments are directed to techniques for interacting with a hierarchical video segmentation using a video timeline. In some embodiments, the finest level of a hierarchical segmentation identifies the smallest interaction unit of a video—semantically defined video segments of unequal duration called clip atoms, and higher levels cluster the clip atoms into coarser sets of video segments. A presented video timeline is segmented based on one of the levels, and one or more segments are selected through interactions with the video timeline. For example, a click or tap on a video segment or a drag operation dragging along the timeline snaps selection boundaries to corresponding segment boundaries defined by the level. Navigating to a different level of the hierarchy transforms the selection into coarser or finer video segments defined by the level. Any operation can be performed on selected video segments, including playing back, trimming, or editing.

Abstract: Embodiments are directed to a snap point segmentation that defines the locations of selection snap points for a selection of video segments. Candidate snap points are determined from boundaries of feature ranges of the video indicating when instances of detected features are present in the video. In some embodiments, candidate snap point separations are penalized for being separated by less than a minimum duration corresponding to a minimum pixel separation between consecutive snap points on a video timeline. The snap point segmentation is computed by solving a shortest path problem through a graph that models different snap point locations and separations. When a user clicks or taps on the video timeline and drags, a selection snaps to the snap points defined by the snap point segmentation. In some embodiments, the snap points are displayed during a drag operation and disappear when the drag operation is released.

Abstract: Embodiments are directed to video segmentation based on a query. Initially, a first segmentation such as a default segmentation is displayed (e.g., as interactive tiles in a finder interface, as a video timeline in an editor interface), and the default segmentation is re-segmented in response to a user query. The query can take the form of a keyword and one or more selected facets in a category of detected features. Keywords are searched for detected transcript words, detected object or action tags, or detected audio event tags that match the keywords. Selected facets are searched for detected instances of the selected facets. Each video segment that matches the query is re-segmented by solving a shortest path problem through a graph that models different segmentation options.

Abstract: Embodiments are directed to a thumbnail segmentation that defines the locations on a video timeline where thumbnails are displayed. Candidate thumbnail locations are determined from boundaries of feature ranges of the video indicating when instances of detected features are present in the video. In some embodiments, candidate thumbnail separations are penalized for being separated by less than a minimum duration corresponding to a minimum pixel separation (e.g., the width of a thumbnail) between consecutive thumbnail locations on a video timeline. The thumbnail segmentation is computed by solving a shortest path problem through a graph that models different thumbnail locations and separations. As such, a video timeline is displayed with thumbnails at locations on the timeline defined by the thumbnail segmentation, with each thumbnail depicting a portion of the video associated with the thumbnail location.

Abstract: Embodiments are directed to techniques for interacting with a hierarchical video segmentation by performing a metadata search. Generally, various types of metadata can be extracted from a video, such as a transcript of audio, keywords from the transcript, content or action tags visually extracted from video frames, and log event tags extracted from an associated temporal log. The extracted metadata is segmented into metadata segments and associated with corresponding video segments defined by a hierarchical video segmentation. As such, a metadata search can be performed to identify matching metadata segments and corresponding matching video segments defined by a particular level of the hierarchical segmentation. Matching metadata segments are emphasized in a composite list of the extracted metadata, and matching video segments are emphasized on the video timeline. Navigating to a different level of the hierarchy transforms the search results into corresponding coarser or finer segments defined by the level.

Abstract: Embodiments are directed to techniques for interacting with a hierarchical video segmentation using a metadata panel with a composite list of video metadata. The composite list is segmented into selectable metadata segments at locations corresponding to boundaries of video segments defined by a hierarchical segmentation. In some embodiments, the finest level of a hierarchical segmentation identifies the smallest interaction unit of a video—semantically defined video segments of unequal duration called clip atoms, and higher levels cluster the clip atoms into coarser sets of video segments. One or more metadata segments can be selected in various ways, such as by clicking or tapping on a metadata segment or by performing a metadata search. When a metadata segment is selected, a corresponding video segment is emphasized on the video timeline, a playback cursor is moved to the first video frame of the video segment, and the first video frame is presented.

Abstract: Disclosed systems and methods predict visemes from an audio sequence. In an example, a viseme-generation application accesses a first audio sequence that is mapped to a sequence of visemes. The first audio sequence has a first length and represents phonemes. The application adjusts a second length of a second audio sequence such that the second length equals the first length and represents the phonemes. The application adjusts the sequence of visemes to the second audio sequence such that phonemes in the second audio sequence correspond to the phonemes in the first audio sequence. The application trains a machine-learning model with the second audio sequence and the sequence of visemes. The machine-learning model predicts an additional sequence of visemes based on an additional sequence of audio.