Abstract: The disclosure relates to recognizing data such as items or entities in content. In some aspects, content may be received and feature information, such as face recognition data and voice recognition data may be generated. Scene segmentation may also be performed on the content, grouping the various shots of the video content into one or more shot collections, such as scenes. For example, a decision lattice representative of possible scene segmentations may be determined and the most probable path through the decision lattice may be selected as the scene segmentation. Upon generating the feature information and performing the scene segmentation, one or more items or entities that are present in the scene may be identified.

Abstract: Methods and apparatus for generating personalized menus and a media content interface are provided. In one example, different device specific media asset lists are generated at different user devices for the same user based on the media consumption history at each device. In another example, media asset listings are displayed for multicast and on-demand media assets determined to be of interest to the user. An on-demand media asset is listed at a time when no other multicast media assets are listed. In another example, media asset listings for successive episodes of a media series are displayed in sequential order in response to an input to view successive episodes of a media series. In another example, a text search for media content is performed in which the search priority of media provider results is decreased relative to the search priority of media asset results as additional characters are added to a search string.

Abstract: The disclosure relates to recognizing data such as items or entities in content. In some aspects, content may be received and feature information, such as face recognition data and voice recognition data may be generated. Scene segmentation may also be performed on the content, grouping the various shots of the video content into one or more shot collections, such as scenes. For example, a decision lattice representative of possible scene segmentations may be determined and the most probable path through the decision lattice may be selected as the scene segmentation. Upon generating the feature information and performing the scene segmentation, one or more items or entities that are present in the scene may be identified.

Abstract: Techniques are presented for analyzing audio-video segments, usually from multiple sources. A combined similarity measure is determined from text similarities and video similarities. The text and video similarities measure similarity between audio-video scenes for text and video, respectively. The combined similarity measure is then used to determine similar scenes in the audio-video segments. When the audio-video segments are from multiple audio-video sources, the similar scenes are common scenes in the audio-video segments. Similarities may be converted to or measured by distance. Distance matrices may be determined by using the similarity matrices. The text and video distance matrices are normalized before the combined similarity matrix is determined. Clustering is performed using distance values determined from the combined similarity matrix.

Abstract: A method and apparatus are provided for summarizing a text message, such as an email message or a transcribed audio message. A portion of each text message, such as a sentence, is extracted as an indicative summary of the text message based on a degree of overlap of words in the sentence with a set of words, such as words in the message subject or words in a related root message. The extracted portion is based on a score for each portion of the text message, such as a sentence. An interface is also provided for presenting the indicative summaries of a set of related text messages to a user.

Abstract: The disclosure relates to recognizing data such as items or entities in content. In some aspects, content may be received and feature information, such as face recognition data and voice recognition data may be generated. Scene segmentation may also be performed on the content, grouping the various shots of the video content into one or more shot collections, such as scenes. For example, a decision lattice representative of possible scene segmentations may be determined and the most probable path through the decision lattice may be selected as the scene segmentation. Upon generating the feature information and performing the scene segmentation, one or more items or entities that are present in the scene may be identified.

Abstract: Methods, systems, computer readable media, and apparatuses are disclosed for providing event messages to a user. The event messages may include video data or a link to video of the event. In some variations, a user or content provider may define criteria for the event messages that are to be displayed to the user. The event messages may be stored so that a user may be able to browse through the stored event messages and decide when to view the video of the event. Upon a user's selection of the event message, the video of the event may be displayed to the user on the same display device or another display device.

Abstract: A method and apparatus are provided for extracting information from a user's memory that will be easily recalled during future authentication yet is hard for an attacker to guess. The information might be a little-known fact of personal relevance to the user or the personal details surrounding a public event. The user is guided to appropriate topics and forms an indirect hint that is useful to the user yet not to an attacker. Information extraction techniques verify that the information is not easily attacked and to estimate how many bits of assurance the question and answer provide. The information extracted may be, e.g., Boolean (Yes/No), multiple choice, numeric, textual, or a combination of the foregoing. The enrollment process may schedule the sending of one or more reminder messages to the user containing the question (but not the answer) to reinforce the memory of the user.

Abstract: The disclosure relates to recognizing data such as items or entities in content. In some aspects, content may be received and feature information, such as face recognition data and voice recognition data may be generated. Scene segmentation may also be performed on the content, grouping the various shots of the video content into one or more shot collections, such as scenes. For example, a decision lattice representative of possible scene segmentations may be determined and the most probable path through the decision lattice may be selected as the scene segmentation. Upon generating the feature information and performing the scene segmentation, one or more items or entities that are present in the scene may be identified.

Abstract: Processes and systems are described herein that may be used to predict which content (e.g., programs, series, movies, channels etc.) will be popular in the future. The processes and systems may use a model that is trained using historical data reflecting information about past showings of programs, such as rating information, viewer behaviors (e.g., channel changes and DVR recordings), online social activity (e.g., Facebook likes and relevant Twitter messages), and/or other data. Accordingly, it may be possible to provide predictive recommendations of popular content before, for example, the content is scheduled or otherwise planned to be distributed or made available to viewers. The results of such prediction may be integrated with, for example, a program guide available to viewers.

Abstract: A method and apparatus are provided for generating passwords that may be memorized by a user, yet not easily guessed by an attacker. A user is presented with one or more textual, audio or visual hints. A password is automatically generated based on the selected hint (and possibly further input from the user). The presented hints may include poems, songs, jokes, pictures or words. The generated password and selected hint can be presented to the user during enrollment for further reinforcement and stored in a user database for subsequent reinforcement and verification. The enrollment process may schedule the sending of one or more reminder messages to the user containing the hint to reinforce the password in the user's memory.

Abstract: A method and apparatus are disclosed that enable a user who forgets one of his two passwords to securely recover the forgotten password. After a user logs in using one of his two passwords, the illustrative embodiment reveals the other password to the user. The passwords are stored in a persistent table in both hashed and encrypted forms, but not in their original forms. The illustrative embodiment is advantageous over the prior art, where forgotten passwords are reset to a default value, in two ways. First, it avoids the inconvenience of a user having to log in using the default password, think up a new string that would make a good password, and change the password from the default to the new string. Second, it avoids the use of default-value passwords that might compromise security.

Abstract: Methods and apparatus are disclosed for classifying the relative position of one or more text messages (including transcribed audio messages) in a related thread of text messages. One or more classifiers are applied to the text messages; and a classification of the text messages is obtained that indicates the relative position of the text messages in the thread. For example, a thread can include a root message, a leaf message and one or more inner messages, and the classification can indicate whether each text message is a root message, a leaf message or an inner message. The classifiers are trained on a set of training messages that have been previously classified to indicate a relative position of each training message in a corresponding thread. The classifiers employ one or more features that help to distinguish between root and non-root messages.

Abstract: A method and apparatus are provided for summarizing a text message, such as an email message or a transcribed audio message. A portion of each text message, such as a sentence, is extracted as an indicative summary of the text message based on a degree of overlap of words in the sentence with a set of words, such as words in the message subject or words in a related root message. The extracted portion is based on a score for each portion of the text message, such as a sentence. An interface is also provided for presenting the indicative summaries of a set of related text messages to a user.

Abstract: A method and apparatus are provided for extracting information from a user's memory that will be easily recalled during future authentication yet is hard for an attacker to guess. The information might be a little-known fact of personal relevance to the user or the personal details surrounding a public event. The user is guided to appropriate topics and forms an indirect hint that is useful to the user yet not to an attacker. Information extraction techniques verify that the information is not easily attacked and to estimate how many bits of assurance the question and answer provide. The information extracted may be, e.g., Boolean (Yes/No), multiple choice, numeric, textual, or a combination of the foregoing. The enrollment process may schedule the sending of one or more reminder messages to the user containing the question (but not the answer) to reinforce the memory of the user.

Abstract: A method and apparatus are provided for evaluating the security of authentication information that is extracted from a user. The disclosed authentication information security analysis techniques determine whether extracted authentication information can be obtained by an attacker. The extracted authentication information might be, for example, personal identification numbers (PINs), passwords and query based passwords (questions and answers). A disclosed authentication information security analysis process employs information extraction techniques to verify that the authentication information provided by a user is not easily obtained through an online search. The authentication information security analysis process measures the security of authentication information, such as query based passwords, provided by a user. Information extraction techniques are employed to find and report relations between the proposed password and certain user information that might make the proposed password vulnerable to attack.

Abstract: A method and apparatus are provided for generating passwords that may be memorized by a user, yet not easily guessed by an attacker. A user is presented with one or more textual, audio or visual hints. A password is automatically generated based on the selected hint (and possibly further input from the user). The presented hints may include poems, songs, jokes, pictures or words. The generated password and selected hint can be presented to the user during enrollment for further reinforcement and stored in a user database for subsequent reinforcement and verification. The enrollment process may schedule the sending of one or more reminder messages to the user containing the hint to reinforce the password in the user's memory.

Abstract: A three party authenticating protocol is disclosed. During an enrollment phase, a user contacts a call center and is directed to a user verification server. The user verification server instructs the user to select and answer a number of questions that will be used for verification. The selected questions along with identifying indices for each question are stored at the user's location and at the user verification server. The user verification server sends the question indices to the call center, which in turn sends these indices to the user to obtain answer indices for each question. During a verification phase, the user contacts the call center and an authentication module asks the user to provide an asserted identity. The authentication module provides a random selection of question indices from those selected by the user. The user provides answer indices for each question to the authentication module. If the number of correctly matching answers exceeds a threshold, then the user is verified.

Abstract: A query directed password scheme is disclosed that employs attack-resistant questions having answers that generally cannot be correlated with the user using online searching techniques, such as user opinions, trivial facts, or indirect facts. During an enrollment phase, the user is presented with a pool of questions from which the user must select a subset of such questions to answer. Information extraction techniques optionally ensure that the selected questions and answers cannot be correlated with the user. A security weight can optionally be assigned to each selected question. The selected questions should optionally meet predefined criteria for topic distribution. During a verification phase, the user is challenged with a random subset of the questions that the user has previously answered and answers these questions until a level of security for a given application is exceeded as measured by the number of correct questions out of the number of questions asked.

Abstract: ? Techniques are presented for analyzing audio-video segments, usually from multiple sources. A combined similarity measure is determined from text similarities and video similarities. The text and video similarities measure similarity between audio-video scenes for text and video, respectively. The combined similarity measure is then used to determine similar scenes in the audio-video segments. When the audio-video segments are from multiple audio-video sources, the similar scenes are common scenes in the audio-video segments. Similarities may be converted to or measured by distance. Distance matrices may be determined by using the similarity matrices. The text and video distance matrices are normalized before the combined similarity matrix is determined. Clustering is performed using distance values determined from the combined similarity matrix.