Abstract: A system is described for reducing artifacts produced by a rolling shutter capture technique in the presence of high-frequency motion, e.g., produced by large accelerations or jitter. The system operates by computing low-frequency information based on the motion of points from one frame to the next. The system then uses the low-frequency information to infer the high-frequency motion, e.g., by treating the low-frequency information as known integrals of the unknown underlying high-frequency information. The system then uses the high-frequency information to reduce the presence of artifacts. In effect, the correction aims to re-render video information as though all the pixels in each frame were imaged at the same time using a global shutter technique. An auto-calibration module can estimate the value of a capture parameter, which relates to a time interval between the capture of two subsequent rows of video information.

Abstract: The described implementations relate to assisted face recognition tagging of digital images, and specifically to context-driven assisted face recognition tagging. In one case, context-driven assisted face recognition tagging (CDAFRT) tools can access face images associated with a photo gallery. The CDAFRT tools can perform context-driven face recognition to identify individual face images at a specified probability. In such a configuration, the probability that the individual face images are correctly identified can be higher than attempting to identify individual face images in isolation.

Abstract: Described is a technology in which video shots are clustered based upon the location at which the shots were captured. A global energy function is optimized, including a first term that computes clusters so as to be reasonably dense and well connected, to match the possible shots that are captured at a location, e.g., based on similarity scores between pairs of shots. A second term is a temporal prior that encourages subsequent shots to be placed in the same cluster. The shots may be represented as nodes of a minimum spanning tree having edges with weights that are based on the similarity score between the shots represented by their respective nodes. Agglomerative clustering is performed by selecting pairs of available clusters, merging the pairs and keeping the pair with the lowest cost. Clusters are iteratively merged until a stopping criterion or criteria is met (e.g., only a single cluster remains).

Abstract: Captured images are analyzed to identify portrayed individuals and/or scene elements therein. Upon user confirmation of one or more identified individuals and/or scene elements entity information is accessed to determine whether there are any available communication addresses, e.g., email addresses, SMS-based addresses, websites, etc., that correspond with or are otherwise linked to an identified individual or scene element in the current captured image. A current captured image can then be automatically transmitted, with no need for any other user effort, to those addresses located for an identified individual or scene element.

Abstract: A system is described for reducing artifacts produced by a rolling shutter capture technique in the presence of high-frequency motion, e.g., produced by large accelerations or jitter. The system operates by computing low-frequency information based on the motion of points from one frame to the next. The system then uses the low-frequency information to infer the high-frequency motion, e.g., by treating the low-frequency information as known integrals of the unknown underlying high-frequency information. The system then uses the high-frequency information to reduce the presence of artifacts. In effect, the correction aims to re-render video information as though all the pixels in each frame were imaged at the same time using a global shutter technique. An auto-calibration module can estimate the value of a capture parameter, which relates to a time interval between the capture of two subsequent rows of video information.

Abstract: The described implementations relate to assisted face recognition tagging of digital images, and specifically to context-driven assisted face recognition tagging. In one case, context-driven assisted face recognition tagging (CDAFRT) tools can access face images associated with a photo gallery. The CDAFRT tools can perform context-driven face recognition to identify individual face images at a specified probability. In such a configuration, the probability that the individual face images are correctly identified can be higher than attempting to identify individual face images in isolation.

Abstract: Described is a technology in which video shots are clustered based upon the location at which the shots were captured. A global energy function is optimized, including a first term that computes clusters so as to be reasonably dense and well connected, to match the possible shots that are captured at a location, e.g., based on similarity scores between pairs of shots. A second term is a temporal prior that encourages subsequent shots to be placed in the same cluster. The shots may be represented as nodes of a minimum spanning tree having edges with weights that are based on the similarity score between the shots represented by their respective nodes. Agglomerative clustering is performed by selecting pairs of available clusters, merging the pairs and keeping the pair with the lowest cost. Clusters are iteratively merged until a stopping criterion or criteria is met (e.g., only a single cluster remains).