Abstract: Disclosed are systems, techniques, and non-transitory storage media for predicting social media postings as being trusted news or a type of suspicious news. The systems, techniques, and non-transitory storage media are based on unique neural network architectures that learn from a combined representation including at least representations of social media posting content and a vector representation of communications among connected users.

Abstract: Disclosed are systems, techniques, and non-transitory storage media for predicting social media postings as being trusted news or a type of suspicious news. The systems, techniques, and non-transitory storage media are based on unique neural network architectures that learn from a combined representation including at least representations of social media posting content and a vector representation of communications among connected users.

Abstract: A method for determining the likelihood of a modification of a social media account based upon the algorithmic review of preselected features including, but not limited to, a combination of profile, behavior, language, affect, and network features form the basis for highly accurate (0.82 accuracy) prediction of the deletion of an account.

Abstract: Different advantageous embodiments provide a crowdsourcing method for modeling user intent in conversational interfaces. One or more stimuli are presented to a plurality of describers. One or more sets of describer data are captured from the plurality of describers using a data collection mechanism. The one or more sets of describer data are processed to generate one or more models. Each of the one or more models is associated with a specific stimulus from the one or more stimuli.

Abstract: A method of embedding image-related information in an image, the method including: receiving an image including a plurality of frames; receiving information related to the image; generating a codeword by encoding the image-related information; and embedding the image-related information in the image by substituting macroblocks included in at least one of the plurality of frames of the image based on the generated codeword.

Abstract: A method of embedding a watermark in video data includes generating a watermark to be embedded in the video data, generating a bit string based on a generated watermark, and embedding a watermark in the video data by changing a quantization parameter of the video data by a predetermined value based on the bit string.

Abstract: A method of compressing video signal data via three-dimensional (3D) transformation, and decoding the compressed video signal data. The method includes: receiving transformation coefficients included in video signal data compressed via 3D transformation; selecting at least one transformation coefficient from among the received transformation coefficients based on a reproducing capability of a device for reproducing the video signal data; and decoding the compressed video signal data to video signal data in a spatial domain by 3D inverse transforming the compressed video signal data using the selected at least one transformation coefficient.

Abstract: A method of embedding image-related information in an image, the method including: receiving an image including a plurality of frames; receiving information related to the image; generating a codeword by encoding the image-related information; and embedding the image-related information in the image by substituting macroblocks included in at least one of the plurality of frames of the image based on the generated codeword.

Abstract: Different advantageous embodiments provide a crowdsourcing method for modeling user intent in conversational interfaces. One or more stimuli are presented to a plurality of describers. One or more sets of describer data are captured from the plurality of describers using a data collection mechanism. The one or more sets of describer data are processed to generate one or more models. Each of the one or more models is associated with a specific stimulus from the one or more stimuli.

Abstract: A method of inserting concealed information in image data, the method including: dividing the image data into predetermined groups; determining whether to transform at least one pixel value included in each of the predetermined groups is transformed, according to concealed information; transforming the at least one pixel value according to the determination, and inserting the concealed information in the image data depending on whether the transformed pixel value is included in a predetermined color region.