Abstract: A method of enhancing the accuracy to predict the gender of a network user comprises: obtaining campaign gender distribution ratios for each advertising campaign by counting the gender information of groundtruth devices which clicked in the respective advertising campaigns; assigning the gender information for each unknown device by finding out the advertising campaigns that are clicked by the unknown device, multiplying the campaign gender distribution ratios of the clicked advertising campaigns, and comparing the multiplied result with a first certain value; obtaining update campaign gender distribution ratios for each advertising campaign by counting the gender information of groundtruth devices and unknown devices which clicked in the respective advertising campaigns; and comparing a quadratic sum of the difference of the old and update campaign gender distribution ratios with a second certain value for each advertising campaign, and back to the assigning step if the quadratic sum is greater than a second

Abstract: Various embodiments are disclosed for image editing. A frame is obtained from a frame sequence depicting at least one individual, and facial characteristics in the frame are analyzed. A utilization score is assigned to the frame based on the detected facial characteristics, and a determination of whether to utilize the frame is made based on the utilization score. A completeness value is assigned, and a determination is made based on the completeness value of whether to repeat the steps above for an additional frame in the frame sequence based on the completeness value. Regions from the frames are combined to generate a composite image.

Abstract: Various embodiments are disclosed for image editing. A frame is obtained from a frame sequence depicting at least one individual, and facial characteristics in the frame are analyzed. A utilization score is assigned to the frame based on the detected facial characteristics, and a determination of whether to utilize the frame is made based on the utilization score. A completeness value is assigned, and a determination is made based on the completeness value of whether to repeat the steps above for an additional frame in the frame sequence based on the completeness value. Regions from the frames are combined to generate a composite image.

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: 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: Various embodiments described herein provide users with a fast and efficient way for identifying scenes for editing purposes. At least one embodiment is a method for editing video. The method comprises receiving a video with scenes to be edited, receiving a scene selection for editing, and partitioning the selected scene into subscenes based on the presence of subtitles, audio analysis, or a combination of both. The method further comprises identifying subscenes of interest, receiving editing commands for the subscenes of interest, and associating the editing commands with the video for future playback, wherein the video is left unmodified.

Abstract: Various embodiments described herein provide users with a fast and efficient way for identifying scenes for editing purposes. At least one embodiment is a method for editing video. The method comprises receiving a video with scenes to be edited, receiving a scene selection for editing, and partitioning the selected scene into subscenes based on the presence of subtitles, audio analysis, or a combination of both. The method further comprises identifying subscenes of interest, receiving editing commands for the subscenes of interest, and associating the editing commands with the video for future playback, wherein the video is left unmodified.