摘要:
Described are various technologies that pertain to automatically generating looped videos or cinemagraphs by selecting objects to animate from an input video. In one implementation a group of semantically labeled objects from an input video is received. Candidate objects from the input video that can appear as a moving object in an output cinemagraph or looped video are identified. Candidate video loops are generated using the selected candidate objects. One or more of these candidate video loops are then selected to create a final cinemagraph. The selection of candidate video loops used to create the final cinemagraph can be made by a user or by a predictive model trained to evaluate the subjective attractiveness of the candidate video loops.
摘要:
A system and method of preparing images captured by a lifelog camera for efficient transfer from the camera to another device. The lifelog camera generates a corresponding thumbnail for each image that it captures, and an automated analysis engine analyzes the thumbnails for interestingness and, in some cases, for similarity.
摘要:
A processing device receives at least a first set of images from a capture device. The first set of images can be a video clip captured using a first frame rate over a first duration of time. The processing device analyzes the first set of images to determine one or more properties associated with the images. Based upon the determined properties, the first set of images is modified and played back at a second frame rate over a second duration of time.
摘要:
A user interface for visually presenting media content items available for time-shifted playback. The user interface includes a first plurality of preview images having an aspect ratio and a first size. The user interface also includes a second plurality of preview images having the same aspect ratio and a second size, smaller than the first size. Each preview image visually represents a different media content item available for time-shifted playback. Each preview image is spatially-sorted in an array according to a temporal order with which that media content item is added to the array. Preview images having the first size alternate between being aligned above and being aligned below two side-by-side preview images having the second size.
摘要:
A method for processing image information has accessing position information associated with images, identifying a position sequence that provides a series of locations along a pathway corresponding to a subject, and displaying the images in an order of the position sequence. The position sequence is adjusted based on movement of the subject.
摘要:
The present embodiments relate a method comprising recording media by an electronic device; determining a primary track of the recording, which primary track indicates the main content; determining one or more secondary tracks, wherein each of the secondary tracks will contain a selected content of the recording; creating a multitrack media of said primary track and said one or more secondary tracks in said electronic device; and transmitting said multitrack media to a remixing server in order to receive a multitrack presentation.
摘要:
A receiving apparatus includes a first receiving unit that receives signaling information and a first signal comprising reference data through a radio frequency broadcast network; a control unit that detects a plurality of additional data source information from the signaling information; a second receiving unit that accesses an internet protocol communication network, and receives a second signal comprising additional data from a source apparatus corresponding to each of the plurality of additional data source information; a storage unit that stores the reference data contained in the first signal and the additional data contained in the second signal; and an output unit that processes, synchronizes and outputs each of the reference data and additional data.