Abstract: Techniques related to eye contact correction to provide a virtual user gaze aligned with a camera while the user views a display are discussed. Such techniques may include determining and reducing histogram of oriented gradient features for an eye region of a source image to provide a feature set, applying a pretrained classifier to the feature set to determine a motion vector field for the eye region, and warping and inserting the eye region into the source image to generate an eye contact corrected image.

Abstract: Techniques related to eye contact correction to provide a virtual user gaze aligned with a camera while the user views a display are discussed. Such techniques may include encoding an eye region of a source image using a pretrained neural network to generate compressed features, applying a pretrained classifier to the features to determine a motion vector field for the eye region, and warping and inserting the eye region into the source image to generate an eye contact corrected image.

Abstract: Techniques related to generating dictionaries for example based image processing algorithms are discussed. Such techniques may include iteratively performing example based image processing for candidate look up entries of candidate pairs from a training set database using a current dictionary to determine a test result for each of the look up entries of the candidate pairs and selecting one or more of the candidate pairs for entry in a resultant dictionary based on an error between the test result and a predetermined result entry for the candidate pairs.

Abstract: Methods, apparatuses and systems may provide for operating a machine learning device by obtaining training image data, conducting an offline prediction analysis of the training image data with respect to one or more real-time parameters of an image capture device, and generating one or more parameter detection models based on the offline prediction analysis. Additionally, methods, apparatuses and systems may provide for operating the image capture device by obtaining a candidate image associated with the image capture device, determining that the candidate image corresponds to a particular type of scene represented in a parameter prediction model, and adjusting one or more real-time parameters of the image capture device based at least in part on one or more parameter values associated with the particular type of scene.

Abstract: Techniques related to eye contact correction to provide a virtual user gaze aligned with a camera while the user views a display are discussed. Such techniques may include determining and reducing histogram of oriented gradient features for an eye region of a source image to provide a feature set, applying a pretrained classifier to the feature set to determine a motion vector field for the eye region, and warping and inserting the eye region into the source image to generate an eye contact corrected image.

Abstract: Techniques related to eye contact correction to provide a virtual user gaze aligned with a camera while the user views a display are discussed. Such techniques may include encoding an eye region of a source image using a pretrained neural network to generate compressed features, applying a pretrained classifier to the features to determine a motion vector field for the eye region, and warping and inserting the eye region into the source image to generate an eye contact corrected image.

Abstract: Techniques related to generating dictionaries for example based image processing algorithms are discussed. Such techniques may include iteratively performing example based image processing for candidate look up entries of candidate pairs from a training set database using a current dictionary to determine a test result for each of the look up entries of the candidate pairs and selecting one or more of the candidate pairs for entry in a resultant dictionary based on an error between the test result and a predetermined result entry for the candidate pairs.

Abstract: Methods, apparatuses and systems may provide for operating a machine learning device by obtaining training image data, conducting an offline prediction analysis of the training image data with respect to one or more real-time parameters of an image capture device, and generating one or more parameter detection models based on the offline prediction analysis. Additionally, methods, apparatuses and systems may provide for operating the image capture device by obtaining a candidate image associated with the image capture device, determining that the candidate image corresponds to a particular type of scene represented in a parameter prediction model, and adjusting one or more real-time parameters of the image capture device based at least in part on one or more parameter values associated with the particular type of scene.

Abstract: A method and apparatus for producing a variable bit rate audio signal is disclosed. An audio signal is encoded into a plurality of encoded audio signals at different bit rates. A variable bit rate audio signal is produced by selecting between the plurality of encoded audio frames of different bit rates in accordance with a selection criterion.

Abstract: A method and apparatus for producing a variable bit rate audio signal is disclosed. An audio signal is encoded into a plurality of encoded audio signals at different bit rates. A variable bit rate audio signal is produced by selecting between the plurality of encoded audio frames of different bit rates in accordance with a selection criterion.

Abstract: A method and apparatus for producing a variable bit rate audio signal is disclosed. An audio signal is encoded into a plurality of encoded audio signals at different bit rates. A variable bit rate audio signal is produced by selecting between the plurality of encoded audio frames of different bit rates in accordance with a selection criterion.

Abstract: A method and apparatus are disclosed for detecting scene cuts in a video bitstream. The number of coded macroblocks for each of a plurality of potential scene cuts is determined. The number of predicted macroblocks for each of the plurality of potential scene cuts is determined. A ratio of the number of coded macroblocks to the number of predicted macroblocks for each of a plurality frames corresponding to the potential scene cuts is then calculated. A frame having the desired ratio is selected. The ratio of the selected frame is compared to a threshold value. A scene cut is reported as detected responsive to a determination that the ratio of the selected frame satisfies the threshold value.

Abstract: A method and apparatus for producing a variable bit rate audio signal is disclosed. An audio signal is encoded into a plurality of encoded audio signals at different bit rates. A variable bit rate audio signal is produced by selecting between the plurality of encoded audio frames of different bit rates in accordance with a selection criterion.

Abstract: An apparatus and method for implementing object motion segmentation and object trajectory segmentation for an image sequence. Specifically, block-based motion vectors for a pair of adjacent frames are used to derive optical flow, e.g., affine, motion parameters. Such optical flow motion parameters are employed to determine key objects where their motion and trajectory within a sequence of frames are calculated and stored. Such object motion information is used to improve or offer image processing functions such as context-based indexing of the input image sequence by using motion-based information.

Abstract: The process of identifying and associating information with objects in a hyperlinked video sequence is automated by creating an accessible list of object information, including semantic representations, which updates with the identification of new objects. Because objects appear in more than one shot in many video sequences, the invention makes guesses about the identification of objects in a newly segmented sequence. If it guesses the object correctly, the author is relieved of the need to manually search a database of object information to make the association.

Abstract: A method and apparatus are disclosed for detecting scene cuts in a video bitstream. The number of coded macroblocks for each of a plurality of potential scene cuts is determined. The number of predicted macroblocks for each of the plurality of potential scene cuts is determined. A ratio of the number of coded macroblocks to the number of predicted macroblocks for each of a plurality frames corresponding to the potential scene cuts is then calculated. A frame having the desired ratio is selected. The ratio of the selected frame is compared to a threshold value. A scene cut is reported as detected responsive to a determination that the ratio of the selected frame satisfies the threshold value.

Abstract: An apparatus and method for implementing object trajectory segmentation for an image sequence. Specifically, block-based motion vectors for a pair of adjacent frames are used to derive optical flow, e.g., affine, motion parameters. The object trajectory segmenter applies the optical flow motion parameters to form a new prediction or method for predicting the positions of all the points on an object over time within an interval. The new prediction is then applied and the result is compared with an error metric. The results from such comparison with the error metric will dictate the proper intervals (temporal boundaries) of the image sequence at which the motion parameters are valid for various key objects.