Abstract: The importance of video sections of a video file may be determined from features of the video file. The video file may be decoded to obtain video frames and audio data associated with the video frames. Feature scores for each video frame may be obtained by analyzing features of the video frame or the audio data associated with the video frame based on a local rule, a global rule, or both. The feature scores are further combined to derive a frame importance score for the video frame. Based on the feature scores of the video frames in the video file, the video file may be segmented into video sections of different section importance values.

Abstract: Techniques for identifying prominent subjects in video content based on feature point extraction are described herein. Video files may be processed to detect faces on video frames and extract feature points from the video frames. Some video frames may include detected faces and extracted feature points and other video frames may not include detected faces. Based on the extracted feature points, faces may be inferred on video frames where no face was detected. The inferring may be based on feature points. Additionally, video frames may be arranged into groups and two or more groups may be merged. The merging may be based on some groups including video frames having overlapping feature points. The resulting groups each may identify a subject. A frequency representing a number of video frames where the subject appears may be determined for calculating a prominence score for each of the identified subjects in the video file.

Abstract: Technologies for a single-pass process for enhancing video quality with temporal smoothing. The process may include providing for user overrides of automatically enhanced video/frame characteristics and providing substantially immediate previews of enhanced video frames to a user. The process may also include detecting a degree of shakiness in a portion of the video, and performing or recommending stabilization based on the detected shakiness.

Abstract: An encoded bitstream is processed without re-encoding so as to recombine multiple packets of each image into contiguous data of one packet for the image. Each packet is assigned a presentation time stamp, corresponding to the display order of its image in the sequence of images. In one embodiment, each intra-frame compressed image also is marked as a recovery point indicating that a decompression processor empties its buffers of data for prior groups of pictures before processing the image. A video editing or other playback application uses the converted bitstream for scrubbing and similar playback operations.

Abstract: Enhanced, efficient source frame decoding for user previewing is implemented by decoding and caching source frames of an input file that a user is interested in. Source frames for a user preview session are identified and decoded first to enhance user satisfaction with more timely preview segments for review. Additional source frames continue to be decoded on the fly to opportunistically enhance the current preview segment and to be prepared for additional preview segments and/or output file generation.

Abstract: This disclosure describes techniques for training models from video data and applying the learned models to identify desirable video data. Video data may be labeled to indicate a semantic category and/or a score indicative of desirability. The video data may be processed to extract low and high level features. A classifier and a scoring model may be trained based on the extracted features. The classifier may estimate a probability that the video data belongs to at least one of the categories in a set of semantic categories. The scoring model may determine a desirability score for the video data. New video data may be processed to extract low and high level features, and feature values may be determined based on the extracted features. The learned classifier and scoring model may be applied to the feature values to determine a desirability score associated with the new video data.

Abstract: Technologies for a single-pass process for enhancing video quality with temporal smoothing. The process may include providing for user overrides of automatically enhanced video/frame characteristics and providing substantially immediate previews of enhanced video frames to a user. The process may also include detecting a degree of shakiness in a portion of the video, and performing or recommending stabilization based on the detected shakiness.

Abstract: Technologies for a single-pass process for enhancing video quality with temporal smoothing. The process may include providing for user overrides of automatically enhanced video/frame characteristics and providing substantially immediate previews of enhanced video frames to a user. The process may also include detecting a degree of shakiness in a portion of the video, and performing or recommending stabilization based on the detected shakiness.

Abstract: Techniques for identifying prominent subjects in video content based on feature point extraction are described herein. Video files may be processed to detect faces on video frames and extract feature points from the video frames. Some video frames may include detected faces and extracted feature points and other video frames may not include detected faces. Based on the extracted feature points, faces may be inferred on video frames where no face was detected. The inferring may be based on feature points. Additionally, video frames may be arranged into groups and two or more groups may be merged. The merging may be based on some groups including video frames having overlapping feature points. The resulting groups each may identify a subject. A frequency representing a number of video frames where the subject appears may be determined for calculating a prominence score for each of the identified subjects in the video file.

Abstract: This disclosure describes techniques for training models from video data and applying the learned models to identify desirable video data. Video data may be labeled to indicate a semantic category and/or a score indicative of desirability. The video data may be processed to extract low and high level features. A classifier and a scoring model may be trained based on the extracted features. The classifier may estimate a probability that the video data belongs to at least one of the categories in a set of semantic categories. The scoring model may determine a desirability score for the video data. New video data may be processed to extract low and high level features, and feature values may be determined based on the extracted features. The learned classifier and scoring model may be applied to the feature values to determine a desirability score associated with the new video data.

Abstract: Technologies for a single-pass process for enhancing video quality with temporal smoothing. The process may include providing for user overrides of automatically enhanced video/frame characteristics and providing substantially immediate previews of enhanced video frames to a user. The process may also include detecting a degree of shakiness in a portion of the video, and performing or recommending stabilization based on the detected shakiness.

Abstract: The importance of video sections of a video file may be determined from features of the video file. The video file may be decoded to obtain video frames and audio data associated with the video frames. Feature scores for each video frame may be obtained by analyzing features of the video frame or the audio data associated with the video frame based on a local rule, a global rule, or both. The feature scores are further combined to derive a frame importance score for the video frame. Based on the feature scores of the video frames in the video file, the video file may be segmented into video sections of different section importance values.

Abstract: An encoded bitstream is processed without re-encoding so as to recombine multiple packets of each image into contiguous data of one packet for the image. Each packet is assigned a presentation time stamp, corresponding to the display order of its image in the sequence of images. In one embodiment, each intra-frame compressed image also is marked as a recovery point indicating that a decompression processor empties its buffers of data for prior groups of pictures before processing the image. A video editing or other playback application uses the converted bitstream for scrubbing and similar playback operations.

Abstract: Enhanced, efficient source frame decoding for user previewing is implemented by decoding and caching source frames of an input file that a user is interested in. Source frames for a user preview session are identified and decoded first to enhance user satisfaction with more timely preview segments for review. Additional source frames continue to be decoded on the fly to opportunistically enhance the current preview segment and to be prepared for additional preview segments and/or output file generation.

Abstract: A system and method for generating a 2D transition between a first media object and a second media object. A 3D model is defined corresponding to a desired 2D transition pattern. A graphics processing unit (GPU) or a set of instructions generates a transition between the first media object and the second media object as a function of the defined 3D model. A transition generator maps a plurality of vertices of the first media object to a first mesh creating a first mapped media object where the first mesh relates to the 3D model. The transition generator maps a plurality of vertices of the second media object to a transition pattern mesh creating a second mapped media object where the transition pattern mesh relates to the 3D model. The GPU or the set of instructions renders the transition from the first mapped media object and the second mapped media object.

Abstract: A system and method for generating a 2D transition between a first media object and a second media object. A 3D model is defined corresponding to a desired 2D transition pattern. A graphics processing unit (GPU) or a set of instructions generates a transition between the first media object and the second media object as a function of the defined 3D model. A transition generator maps a plurality of vertices of the first media object to a first mesh creating a first mapped media object where the first mesh relates to the 3D model. The transition generator maps a plurality of vertices of the second media object to a transition pattern mesh creating a second mapped media object where the transition pattern mesh relates to the 3D model. The GPU or the set of instructions renders the transition from the first mapped media object and the second mapped media object.