摘要:
In a method for a matching a slideshow with an audio track, a slideshow is received. The slideshow comprises a timebase defining display times for slides of the slideshow. An audio track is received. The audio track is utilized to warp the timebase such that a display time for at least one of the slides is altered to increase a correlation between the display time and an intensity of a portion of the audio track.
摘要:
Systems and methods according to the present invention provide techniques to automatically generate an object layout. Various candidate placement positions are evaluated by computing values associated with placing the object at the placement positions. Cost functions associated with contrast, saliency and/or sharpness can be used to evaluate the desirability of each candidate placement position.
摘要:
A concurrent presentation of video segments of a video file enables rapid comprehension of the video file. A video file is segmented into video segments and a condensed representation of the video file is generated. The condensed representation corresponds to a concurrent presentation of the video segments in respective windows in a display area over repeating cycles of a loop period. The concurrent presentation may be processed to concurrently present video segments corresponding to contiguous sections of the video file in respective windows in a display area over repeating cycles of a loop period.
摘要:
In a method for generating a dimensionally tractable set of image layout constraints, a selected constraint is applied to limit a dimension of a highly dimensional solution space. Through random selection one or more unconstrained dimensions of the highly dimensional solution space are identified which, when constrained, will further limit the highly dimensional solution space to a dimensionally tractable solution space. The tractability of the dimensionally tractable solution space is associated with a capability of a computational resource.
摘要:
A concurrent presentation of video segments of a video file enables rapid comprehension of the video file. A video file is segmented into video segments and a condensed representation of the video file is generated. The condensed representation corresponds to a concurrent presentation of the video segments in respective windows in a display area over repeating cycles of a loop period. The concurrent presentation may be processed to concurrently present video segments corresponding to contiguous sections of the video file in respective windows in a display area over repeating cycles of a loop period.
摘要:
In a method for determining a weighted occlusion cost for presenting an image within a non-uniform viewing region image, saliency data for an image to be displayed in a non-uniform viewing region is received. A layout orientation for presenting the image in the non-uniform viewing region is received. A weighted saliency map of the non-uniform viewing region is received. The image saliency data and said weighted saliency map are utilized to determine a weighted occlusion cost for the layout orientation.
摘要:
An exemplary system for browsing videos comprises a memory for storing a plurality of videos, a processor for accessing the videos, and a video browsing user interface for enabling a user to browse the videos. The user interface is configured to enable video browsing in multiple states on a display screen, including a first state for displaying static representations of the videos, a second state for displaying dynamic representations of the videos, and a third state for playing at least a portion of a selected video.
摘要:
Methods and systems for determining an occlusion cost for concurrently presenting multiple images within a shared viewing region are described. Image saliency data is received for a first image to be displayed concurrently with a second image in the shared viewing region. Image saliency data is received for the second image. A layout orientation is received for concurrently presenting the first image and the second image within the shared viewing region. The image saliency data for the first image and the image saliency data for the second image are utilized to determine the occlusion cost of the layout orientation for concurrently presenting the first image and the second image within the shared viewing region.
摘要:
In a method for determining a temporal occlusion cost for a video crop, video image saliency data for a video is received. A video crop is received for a presenting an edited version of the video within a viewing region. The video image saliency data is used to determine a temporal occlusion cost for the video crop.
摘要:
In a computer implemented method of generating a collage of images, image saliency data is received for a plurality of images that are to be collaged within a templated viewing region. The templated viewing region is generated by scaling a template relative to the plurality of images that are to be collaged. An initial collage layout is generated within the templated viewing region from the plurality of images. The initial collage layout is optimized, where the optimizing comprises iteratively adjusting the initial collage layout by selecting a minimized layout occlusion cost.