Abstract: A computing device captures a live video of a user. For a first frame of the live video, the computing device obtains first target positional coordinates of a first target point located a first predetermined distance from the computing device and obtains first background data. For a second frame, the computing device obtains second target positional coordinates of a second target point located a second predetermined distance from the computing device and obtains second background data. The computing device calculates a target motion vector based on the first target point and the second target point and calculates a background motion vector based on feature points in the first background data and the second background data. The computing device determines a difference value between the target motion vector and the background motion vector and determines whether the user is spoofing the computing device based on the difference value.

Abstract: A computing device generates a user interface that includes a viewing window and a toolbar including a selection tool. The computing device displays a live video depicting one or more individuals in the viewing window of the user interface and generates a segmentation mask for each individual depicted in the live video, where each segmentation mask comprises facial feature vectors of a facial region of each individual. The computing device obtains selection of an individual depicted in the live video and compares facial feature vectors of each of the individuals depicted in the live video with the facial feature vector of the selected individual. The computing device converts the segmentation masks of individuals with corresponding facial feature vectors that do not match the selected facial feature vector to a filter mask and composites the filter mask with a background content of the live video.

Abstract: A computing device having a front-facing camera applies facial landmark detection and identifies eye regions in the digital image responsive to the front-facing camera capturing a digital image of an individual. For at least one of the eye regions, the computing device is further configured to extract attributes of the eye region, determine an eye gaze score based on the extracted attributes, generate a modified eye region based on the eye gaze score, and output a modified digital image with the modified eye region.

Abstract: A server computing device receives user input from a presenter to initiate a live webinar presentation comprising a plurality of slides. Responsive to receiving the user input to initiate the live webinar presentation, the server computing device monitors slide transitions triggered by the presenter and logs time stamp data for each slide transition, generates attendee participation data, and stores the live webinar presentation as a webinar presentation video, the time stamp data, and the attendee participation data. The server computing device obtains a request from a client device to view the stored webinar presentation video and partitions the webinar presentation video into slides based on the time stamp data.

Abstract: A computing device for providing distributed playback of 360-degree video in a plurality of viewing windows receives a 360-degree video bitstream. The computing device receives a field of view angle for a main viewing window from a user. A user interface comprising the main viewing window and the plurality of peripheral viewing windows is generated, where the plurality of peripheral viewing windows each have a corresponding field of view angle. The computing device executes distributed playback of the 360-degree video in the main viewing window and the plurality of peripheral viewing windows based on the field of view angles of the main viewing window and the plurality of peripheral viewing windows.

Abstract: A computing device obtains target multimedia and obtains a style digital image depicting a style pattern to be incorporated into the target multimedia. The computing device extracts an image mask from the style digital image, the image mask depicting the style pattern. The computing device generates a modified image mask from the image mask and blends the modified image mask with the target multimedia to generate a modified target digital multimedia. The computing device generates, by an artificial intelligence processor, a final target digital multimedia based on the modified target digital multimedia and the style digital image.

Abstract: A computing device for reducing horizontal misalignment in a 360-degree video converts the 360-degree video to a rectilinear 360-degree video. At least a pair of views of rectilinear images from the rectilinear 360-degree video are generated and displayed. A user interface for facilitating adjustment of a view angle is generated, the user interface displaying the at least the pair of views of the rectilinear images from the rectilinear 360-degree video. The computing device obtains vertical reference object is obtained in one of the views of rectilinear images; at least one of: a roll angle adjustment, a pitch angle adjustment, and a yaw angle adjustment for aligning the vertical reference object with a vertical axis; and a view angle adjustment corresponding to reduction of the horizontal misalignment. A panoramic 360-degree video is then generated.

Abstract: A method implemented in a computing device for inserting an effect into a 360 video where the computing device receives the effect from a user. The method receives a target region from the user, the target region corresponding to a location within the 360 video for inserting the effect; for each frame in the 360 video. The method then inserts the effect on a surface of a spherical model based on the target region and generates at least two projection frames containing the effect from the spherical model. The method then stitches the projection frames to generate a panoramic representation of the effect, and blends the panoramic representation of the effect with an original source panorama to generate a modified 360 video frame with the effect.

Abstract: A computing device executing an instant messaging application receives a selection from a user specifying at least one instant message conversation record to hide from view. The selected conversation record is hidden from view in response to occurrence of an event of a first type. In response to the occurrence of an event of a second type, a timer hidden from the user is launched. An unlock procedure is received from the user, where the user enters the unlock procedure. In response to the entered unlock procedure matching a predetermined unlock procedure prior to expiration of the timer, the corresponding hidden conversation record is made viewable and is accessible again by the user.

Abstract: A computing device for inserting an effect into a 360 video receives the effect from a user. A target region is also received from the user, where the target region corresponds to a location within the 360 video for inserting the effect. Next, the following steps are performed for each frame in the 360 video. The effect is inserted on a surface of a spherical model based on the target region, and two half-sphere frames containing the effect from the spherical model are generated. The two half-sphere frames are stitched to generate a panoramic representation of the effect, and the panoramic representation of the effect is blended with an original source panorama to generate a modified 360 video frame with the effect.

Abstract: A computing device for re-encoding 360 video based on adjusted bitrate allocation receives and decodes a 360 video. The computing device partitions the 360 video into a plurality of regions and determines a pixel number for each of the plurality of regions. The computing device also determines a distortion level for each of the plurality of regions and performs bitrate allocation for each of the regions based on one or more of: the corresponding pixel number and the corresponding distortion level.

Abstract: In a media editing device for reorganizing media content and editing the reorganized media content, a plurality of tracks is obtained, where each track comprises at least one component, each component comprising at least one segment, each segment comprising one of: image content, video content, audio content, and audio/video content. A first user input selecting a plurality of the tracks is received. A second user input selecting at least one reorganization technique to be applied to the selected tracks is also received. The selected reorganization technique is applied to the selected tracks, and the reorganized tracks are displayed. Editing operations are received for at least one of the reorganized tracks.

Abstract: In a computing device for streaming media content, information relating to a video bitstream is transmitted to a client device for displaying a user interface. An input signal is received from the client device indicating a desired start time in the video bitstream. Based on the start time, a target key frame is identified within the video, the target key frame comprising a nearest key frame in the video bitstream preceding the desired start time. A target frame header comprising a nearest header frame in the video preceding the target key frame is identified within the video bitstream. If necessary, the target key frame is converted to a first frame type. Only the target frame header, the target key frame, and video bitstream that follows the converted target key frame is sent to the client device, where the original frame referencing encoded in the video bitstream is utilized.

Abstract: An image editing device is configured to automatically apply special effects to a digital image. In the image editing device, a digital image is obtained, and a selection is retrieved from a user, where the user selection specifying at least one criterion. At least one attribute of the digital image is analyzed, and a determination is made on whether the at least one attribute coincides with a target attribute associated with the at least one criterion. Responsive to the at least one attribute coinciding with the target attribute, a special effect is obtained from a data store, and the obtained special effect is applied to the digital image.

Abstract: An instant messaging system is configured to facilitate digital photo sharing. An invitation is transmitted to at least one contact at a corresponding instant messaging system, where the invitation includes a selected digital photo presentation template comprising a plurality of panels. Digital photos are uploaded to a media content server, and digital photos shared by the at least one invited contact are accessed, where the digital photos are arranged in each of the panels of the presentation template according to at least one viewing criterion specified by a user of the instant messaging system.

Abstract: A cloud computing device facilitates distribution of digital content by receiving multimedia content and a corresponding effect uploaded from a source device and storing the multimedia content with the corresponding effect, receiving an access request from a requesting device for the multimedia content, and determining whether the requesting device is a registered device. In response to the requesting device not being a registered device, the requesting device is registered and a registered device capabilities list is updated. A determination is made based on the registered device capabilities list on whether the requesting device is compatible with the multimedia content and effect. Based on a compatibility determination, data is transmitted to the requesting device to facilitate playback of the multimedia content and effect.

Abstract: In an instant messaging device, a selection is received from a user, where the selection specifying a plurality of contacts to participate in an instant messaging session. At least one attribute type corresponding to the at least one intended recipient is retrieved in response to detecting a trigger event relating to a message intended for at least one recipient among the plurality of contacts. A verification operation is retrieved for each of the retrieved at least one attribute type. At least one retrieved verification operations is executed. The message is sent to the at least one intended recipient in response to successful execution of the at least one of the retrieved verification operations.