Abstract: Systems and methods are directed to auto-adjusting play time of slides based on content intelligence. The system accesses media comprising a plurality of media items, wherein a media item of the plurality of media items comprises a first content type. The system performs machine analysis associated with the first content type. Based on the machine analysis, the system determines a first display time for the first content type and derives a total display time for the media item based on the first display time. If the media item includes a second content type, then the system performs machine analysis associated with the second content type and determines a second display time for the second content type. The total display time now comprises an aggregation of the first and second display times. The system can cause a machine action based on the total display time.

Abstract: Systems and methods are directed to auto-adjusting play time of slides based on content intelligence. The system accesses media comprising a plurality of media items, wherein a media item of the plurality of media items comprises a first content type. The system performs machine analysis associated with the first content type. Based on the machine analysis, the system determines a first display time for the first content type and derives a total display time for the media item based on the first display time. If the media item includes a second content type, then the system performs machine analysis associated with the second content type and determines a second display time for the second content type. The total display time now comprises an aggregation of the first and second display times. The system can cause a machine action based on the total display time.

Abstract: Systems and methods are directed to auto-adjusting play time of slides based on content intelligence. The system accesses media comprising a plurality of media items, wherein a media item of the plurality of media items comprises a first content type. The system performs machine analysis associated with the first content type. Based on the machine analysis, the system determines a first display time for the first content type and derives a total display time for the media item based on the first display time. If the media item includes a second content type, then the system performs machine analysis associated with the second content type and determines a second display time for the second content type. The total display time now comprises an aggregation of the first and second display times. The system can cause a machine action based on the total display time.

Abstract: An automated motion-blur detection process can detect frames in digital videos where only a part of the frame exhibits motion blur. Certain embodiments programmatically identify a plurality of feature points within a video clip, and calculate a speed of each feature point within the video clip. A collective speed of the plurality of feature points is determined based on the speed of each feature point. A selection factor is compared to a selection threshold for each video frame. The selection factor is based at least in part on the collective speed of the plurality of feature points. Based on this comparison, at least one video frame from within the video clip is selected. In some aspects, the selected video frame is relatively free of motion blur, even motion blur that occurs in only a part of the image.

Abstract: Systems and methods for segmenting video. A segmentation application executing on a computing device receives a video including video frames. The segmentation application calculates, using a predictive model trained to evaluate quality of video frames, a first aesthetic score for a first video frame and a second aesthetic score for a second video frame. The segmentation application determines that the first aesthetic score and the second aesthetic score differ by a quality threshold and that a number of frames between the first video frame and the second video frame exceeds a duration threshold. The segmentation application creates a video segment by merging a subset of video frames ranging from the first video frame to an segment-end frame preceding the second video frame.

Abstract: Automatic frame selection and action shot generation techniques in a digital medium environment are described. A computing device identifies an object in a foreground of video data. A determination is then made by the computing device as to motion of the object exhibited between frames of the video data. A subset of frames is then selected by the computing device based on a determined motion of the identified object depicting an action sequence. An action shot is generated by the computing device by overlaying the identified objects in the selected frames on a background.

Abstract: Systems and methods for segmenting video. A segmentation application executing on a computing device receives a video including video frames. The segmentation application calculates, using a predictive model trained to evaluate quality of video frames, a first aesthetic score for a first video frame and a second aesthetic score for a second video frame. The segmentation application determines that the first aesthetic score and the second aesthetic score differ by a quality threshold and that a number of frames between the first video frame and the second video frame exceeds a duration threshold. The segmentation application creates a video segment by merging a subset of video frames ranging from the first video frame to an segment-end frame preceding the second video frame.

Abstract: An automated motion-blur detection process can detect frames in digital videos where only a part of the frame exhibits motion blur. Certain embodiments programmatically identify a plurality of feature points within a video clip, and calculate a speed of each feature point within the video clip. A collective speed of the plurality of feature points is determined based on the speed of each feature point. A selection factor is compared to a selection threshold for each video frame. The selection factor is based at least in part on the collective speed of the plurality of feature points. Based on this comparison, at least one video frame from within the video clip is selected. In some aspects, the selected video frame is relatively free of motion blur, even motion blur that occurs in only a part of the image.

Abstract: Systems and methods disclosed herein provide automatic and intelligent video sorting in the context of creating video compositions. A computing device sorts a media bin of videos in the user's work area based on similarity to the videos included in the video composition being created. When a user selects or includes a particular video on the composition's timeline, the video is compared against the entire video collection to change the display of videos in the media bin. In one example, videos that have similar tags to a selected video are prioritized at the top. Only a subset of frames of each of the videos are used to use to identify video tags. Intelligently selecting tags using a subset of frames from each video rather than using all frames enables more efficient and accurate tagging of videos, which facilitates quicker and more accurate comparison of video similarities.

Abstract: Systems and methods disclosed herein provide automatic and intelligent video sorting in the context of creating video compositions. A computing device sorts a media bin of videos in the user's work area based on similarity to the videos included in the video composition being created. When a user selects or includes a particular video on the composition's timeline, the video is compared against the entire video collection to change the display of videos in the media bin. In one example, videos that have similar tags to a selected video are prioritized at the top. Only a subset of frames of each of the videos are used to use to identify video tags. Intelligently selecting tags using a subset of frames from each video rather than using all frames enables more efficient and accurate tagging of videos, which facilitates quicker and more accurate comparison of video similarities.

Abstract: Automatic frame selection and action shot generation techniques in a digital medium environment are described. A computing device identifies an object in a foreground of video data. A determination is then made by the computing device as to motion of the object exhibited between frames of the video data. A subset of frames is then selected by the computing device based on a determined motion of the identified object depicting an action sequence.

Abstract: Various embodiments calculate a score for each frame of a video segment based on various subject-related factors associated with a subject (e.g., face or other object) captured in a frame relative to corresponding factors of the subject in other frames of the video segment. A highest-scoring frame from the video segment can then be extracted based on a comparison of the score of each frame of the video segment with the score of each other frame of the video segment, and the extracted frame can be transcoded as an image for display via a display device. The score calculation, extraction, and transcoding actions are performed automatically and without user intervention, which improves previous approaches that use a primarily manual, tedious, and time consuming approach.

Abstract: Various embodiments calculate a score for each frame of a video segment based on various subject-related factors associated with a subject (e.g., face or other object) captured in a frame relative to corresponding factors of the subject in other frames of the video segment. A highest-scoring frame from the video segment can then be extracted based on a comparison of the score of each frame of the video segment with the score of each other frame of the video segment, and the extracted frame can be transcoded as an image for display via a display device. The score calculation, extraction, and transcoding actions are performed automatically and without user intervention, which improves previous approaches that use a primarily manual, tedious, and time consuming approach.

Abstract: Fitting content to a resized frame is described. In one or more embodiments, input is received to resize a frame that defines a boundary for a content item in a layout of content. For example, a user grabs a handle of the frame and drags the handle horizontally or vertically to resize the frame. In so doing, the aspect ratio of the frame is changed. A content fitting module fits the content item to the frame so that when the content item is displayed, the content item does not appear distorted and is contained within the frame. To do so, the content fitting module proportionally scales the content item based on an amount the frame is resized, repositions the content item to align a center of the content item with a center of the resized frame, and crops the scaled and repositioned content item according to the resized frame.