Abstract: Various embodiments for sharing multimedia editing projects are described. One embodiment is a method performed at a server for sharing video editing techniques by a user. The method comprises receiving a project description file at the server, wherein the project description file is generated during editing of multimedia content by a first editing system, the project description file comprising information relating to special effect objects applied to the edited multimedia content by the first editing system. The method further comprises providing all or a portion of a timeline-based template according to the project description file, wherein the timeline-based template comprises a timeline and object type designators corresponding to the special effect objects specified by the first editing system, wherein representations of the object type designators are displayed along the timeline. The method further comprises transmitting the timeline-based template from the server to a second editing system.

Abstract: Systems and methods for automatic adjustment of text in a video are described. At least one embodiment includes a system for automatic adjustment of text in a video on a display comprising a ratio detector configured to detect an original aspect ratio of the video, an edge locator configured to identify edges of the video based on the original aspect ratio detected, wherein regions between the edges of the video and edges of the display define unused regions, a size assessment module configured to determine size of the text, wherein the size assessment module determines the size of the text by examining at least one of light portions within the text and a bounding rectangle which surrounds the text. The system further comprises a text adjuster configured to move the text to the unused region above or below the video, wherein the text adjuster further aligns the text to at least one of the edges of the video and the edges of the display device.

Abstract: A method for presenting multi-media contents on a specific communication device is disclosed. The method includes detecting a multi-media content channel currently tuned by the specific communication device; and in addition to a specific multi-media content corresponding to a specific channel number currently tuned by the specific communication device, presenting an information communication user interface.

Abstract: Various embodiments are disclosed for selecting a region of interest within an object. One embodiment is a method for editing a digital image in an image editing device. The method comprises obtaining a first position within a digital image, the first position being specified by a pointer. The method further comprises defining a first selection region based on the first position and obtaining a second position within the digital image, the second position being specified by the pointer. The method further comprises determining movement of the pointer between the first position and the second position and predicting future movement by the pointer based on the determined movement. Based on the determined movement and the predicted future movement, the first selection region is expanded to define a second selection region.

Abstract: Various embodiments are disclosed for facilitating selective rendering during video editing. In accordance with one embodiment, a method of editing video comprises obtaining a video editing project, the video editing project including at least one video clip and timing information corresponding to the at least one video clip. The method further comprises obtaining a reference file generated according to the video editing project and obtaining, from a user, a modification for at least one segment in the video editing project. Based on the modification, each of the at least one segment is identified as a modified segment or an unmodified segment. Based on the identification of at least one modified segment, at least one corresponding segment is extracted from the reference file.

Abstract: A method implemented in a computing system for converting two-dimensional (2D) video to three-dimensional (3D) format comprises sampling the 2D video, wherein the sampling is performed non-linearly in one or more directions. The method further comprises determining depth information of one or more objects within the 2D video based on sampling information and transforming the 2D video to a 3D-compatible format according to the sampling and the depth information.

Abstract: Disclosed are various embodiments for tracking an object shown as moving in a video. One embodiment is a method for tracking an object in a video that comprises tracking in a first temporal direction an object in a plurality of video frames and generating a first tracking result, evaluating the first tracking result corresponding to tracking of the object in the first temporal direction, and stopping tracking in the first temporal direction upon the occurrence of a predefined event, wherein the predefined event is based on an evaluated tracking result. The method further comprises obtaining data identifying an object outline of the object upon stopping the tracking in the first temporal direction, tracking in a second temporal direction the object based on the data identifying the object outline of the object to generate a second tracking result, and generating a refined tracking result based on at least on one of the first tracking result, the second tracking result, or a combination thereof.

Abstract: Systems and methods for performing multimedia conversion are disclosed. In a multimedia conversion system for converting two-dimensional (2D) multimedia data to stereoscopic multimedia data, an absolute difference between pixel pairs is determined for each scan line in a frame of the 2D multimedia data. The absolute difference values are accumulated, and a depth map is derived based on the accumulated difference values. The depth map is applied to the frame in the 2D multimedia data.

Abstract: In one embodiment, a button mapping method comprising comparing an image difference between images before and after a keyboard event, the images including a first and second version of buttons in a menu, respectively; constructing by the processor a button map based on the comparison, the button map comprising button information for at least two buttons in the menu; receiving one or more selection signals corresponding to one or more non-keyboard events; and translating the one or more selection signals into one or more keyboard events based on the button map, wherein the button in the menu is selected based on the translation.

Abstract: Systems and methods are disclosed for adjusting parallax for a 3D object appearing on a display. One such method includes selecting a target 3D object, calculating an adjusted parallax position, calculating a z-axis offset based at least in part on the adjusted parallax position, adjusting a first z-axis position of the target 3D object by the z-axis offset, and rendering the target 3D object on the display at the adjusted first z-axis position. The adjusted parallax position is based at least in part on a maximum user reach, a comfortable viewing distance, and a distance between a user and the display. The z-axis offset is set to a difference between the adjusted parallax position and a parallax for a 3D object which is farthest from the user.

Abstract: Various systems and methods for adaptively modifying a user interface are described. One embodiment is a method performed in a multimedia playback system for adaptively modifying a user interface. The method comprises receiving, by the multimedia playback system, multimedia content and displaying the multimedia content. The method further comprises generating, by a user interface generator, one or more controls displayed in conjunction with the multimedia content, identifying, by an object detector, a target object in a field of view of a video capture device coupled to the multimedia playback system, and predicting, by a selection predictor, a next selection of one of the one or more controls based on a path defined by the target object. The method further comprises displaying, by the user interface generator, a virtual pointer representing the target object in a vicinity of the predicted next selection of the one or more controls.

Abstract: Disclosed are various embodiments for the selection of an object boundary shown in an image. An initial boundary probability map of an image is generated by one or more computing devices. A first input path segment is obtained, and a selection path is generated based on the first input path segment and the initial boundary probability map. A weighted boundary probability map is generated based on the selection path. A second input path segment is obtained, and a replacement selection path is generated based on the weighted boundary probability map and the second input path segment.

Abstract: Systems and methods for performing multimedia conversion are disclosed. In a multimedia conversion system for converting two-dimensional (2D) multimedia data to stereoscopic multimedia data, an absolute difference between pixel pairs is determined for each scan line in a frame of the 2D multimedia data. The absolute difference values are accumulated, and a depth map is derived based on the accumulated difference values. The depth map is applied to the frame in the 2D multimedia data.

Abstract: Various embodiments are disclosed for performing object tracking. One embodiment is a system for tracking an object in a plurality of frames, comprising a probability map generator configured to generate a probability map by estimating probability values of pixels in the frame, wherein the probability of each pixel corresponds to a likelihood of the pixel being located within the object. The system further comprises a contour model generator configured to identify a contour model of the object based on a temporal prediction method, a contour weighting map generator configured to derive a contour weighting map based on thickness characteristics of the contour model, a tracking refinement module configured to refine the probability map according to weight values specified in the contour weighting map, and an object tracker configured to track a location of the object within the plurality of frames based on the refined probability map.

Abstract: A stereoscopic cursor method comprising: calculating a cursor scene depth of a stereoscopic cursor for a stereoscopic user interface comprising plural stereoscopic buttons, wherein the stereoscopic cursor is positioned between a viewer and the plural stereoscopic buttons; constraining movement of the stereoscopic cursor between the viewer and the plural stereoscopic buttons at the cursor scene depth for input device movements by the viewer that navigate across the front of the plural stereoscopic buttons; receiving an input signal corresponding to viewer selection of one of the plural stereoscopic buttons; and responsive to receiving the input signal, causing movement of the stereoscopic cursor from one end of the cursor scene depth to the one of the plural stereoscopic buttons in a direction coincident with the cursor scene depth.

Abstract: Various embodiments are disclosed for performing image inpainting. One embodiment is a method for editing a digital image in an image editing device that comprises obtaining a restoration region in the digital image and generating a structure strength map corresponding to the restoration region based on structure characteristics associated with each pixel in the restoration region. Based on the structure strength map, priority levels are determined for pixels in the restoration region. An inpainting operation is applied to the pixels in the restoration region, beginning with a pixel having a highest relative priority determined based on the structure characteristics.

Abstract: Various embodiments are disclosed for performing object tracking. One embodiment is a method for tracking an object in a plurality of frames, comprising obtaining a reference contour of an object in a reference frame and estimating, for a current frame after the reference frame, a contour of the object. The method further comprises comparing the reference contour with the estimated contour and determining at least one local region of the reference contour in the reference frame based on a difference between the reference contour and the estimated contour. Based on the difference, at least one corresponding region of the current frame is determined.

Abstract: Various embodiments are disclosed for performing image inpainting. One embodiment is a method for editing a digital image in an image editing device that comprises obtaining a restoration region in the digital image and generating a structure strength map corresponding to the restoration region based on structure characteristics associated with each pixel in the restoration region. Based on the structure strength map, priority levels are determined for pixels in the restoration region. An inpainting operation is applied to the pixels in the restoration region, beginning with a pixel having a highest relative priority determined based on the structure characteristics.

Abstract: Various embodiments are disclosed for performing image inpainting. One embodiment is a method for editing a digital image in an image editing device. The method comprises obtaining a restoration region in the digital image and determining texture information corresponding to the restoration region. Based on the texture information, a texture strength map is generated corresponding to the restoration region. Based on the texture strength map, an inpainting operation is applied to pixels in the restoration region.

Abstract: In one embodiment, a method of two-dimensional to stereoscopic image conversion, the method comprising detecting a face in a two-dimensional image; determining a body region based on the detected face; providing a color model from a portion of the determined body region, a portion of the detected face, or a combination of both portions; calculating a similarity value of at least one image pixel of the two-dimensional image based on the provided color model; and assigning a depth value of the image pixel based on the calculated similarity value to generate a stereoscopic image.