Abstract: A computer-implemented method for data labeling is provided. The computer-implemented method assigns pseudo-labels to unlabeled examples of data using a similarity metric on an embedding space to produce pseudo-labeled examples. A curriculum learning model is trained using the pseudo-labeled examples. The curriculum learning model trained with the pseudo-labeled examples is employed in in a fine-tuning task to enhance classification accuracy of the data.

Abstract: A computer-implemented method for data labeling is provided. The computer-implemented method assigns pseudo-labels to unlabeled examples of data using a similarity metric on an embedding space to produce pseudo-labeled examples. A curriculum learning model is trained using the pseudo-labeled examples. The curriculum learning model trained with the pseudo-labeled examples is employed in in a fine-tuning task to enhance classification accuracy of the data.

Abstract: A system and method for analyzing visual memes includes identifying visual memes associated with at least one topic in a data source. The visual memes propagated over time are tracked to extract information associated with identified visual memes. The information associated with the visual memes is analyzed to determine at least one of generation, propagation, and use of the identified memes.

Abstract: A system and method for analyzing visual memes includes identifying visual memes associated with at least one topic in a data source. The visual memes propagated over time are tracked to extract information associated with identified visual memes. The information associated with the visual memes is analyzed to determine at least one of generation, propagation, and use of the identified memes.

Abstract: A system and method for analyzing visual memes includes identifying visual memes associated with at least one topic in a data source. The visual memes propagated over time are tracked to extract information associated with identified visual memes. The information associated with the visual memes is analyzed to determine at least one of generation, propagation, and use of the identified memes.

Abstract: A system and method for analyzing video include segmenting video stored in computer readable storage media into keyframes. Near-duplicate keyframes are represented as a sequence of indices. The near-duplicate keyframes are rendered in a graphical representation to determine relationships between video content.

Abstract: A system and method for analyzing video include segmenting video stored in computer readable storage media into keyframes. Near-duplicate keyframes are represented as a sequence of indices. The near-duplicate keyframes are rendered in a graphical representation to determine relationships between video content.

Abstract: Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.

Abstract: Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.

Abstract: A system and method for analyzing video include segmenting video stored in computer readable storage media into keyframes. Near-duplicate keyframes are represented as a sequence of indices. The near-duplicate keyframes are rendered in a graphical representation to determine relationships between video content.

Abstract: Techniques are provided for rewriting queries during a database query processing operation to include auxiliary attributes not included in the original query, thus improving processing efficiency. For example, a technique for rewriting a query in a query processing operation includes the following steps. The query is processed in accordance with at least a portion of a data set, producing query results. Data attributes from the query results are analyzed. At least one new predicate from at least one auxiliary data attribute is appended on the query.

Abstract: A system and method for analyzing video include segmenting video stored in computer readable storage media into keyframes. Near-duplicate keyframes are represented as a sequence of indices. The near-duplicate keyframes are rendered in a graphical representation to determine relationships between video content.

Abstract: A system and method for analyzing visual memes includes identifying visual memes associated with at least one topic in a data source. The visual memes propagated over time are tracked to extract information associated with identified visual memes. The information associated with the visual memes is analyzed to determine at least one of generation, propagation, and use of the identified memes.

Abstract: Methods and apparatus are provided for rewriting queries during a database query processing operation to include auxiliary attributes not included in the original query, thus improving processing efficiency. For example, in one aspect of the invention, a technique for rewriting a query in a query processing operation includes the following steps. First, the query is processed in accordance with at least a portion of a data set, producing query results. Second, data attributes from the query results are analyzed. Finally, at least one new predicate from at least one auxiliary data attribute is appended on the query.

Abstract: A method and structure for storing information for one or more semantic objects derived from raw data. A semantic object extracted from the raw data and classified to comprise the semantic object is received, the received semantic object having one or more attributes. A summary of attributes of the semantic object by calculating one or more statistics of one or more of the one or more attributes of the received semantic object, a confidence level of the received semantic object that quantifies a degree of certainty that the received semantic object has been correctly classified and/or labeled; and a compact representation of raw data of the received semantic object are generated. Indexing information for one or more of the summary of attributes and the compact representation of the semantic object is generated.

Abstract: A method and apparatus is disclosed that receives an input narrative in a particular media format, and produces therefrom a multimedia enriched version of the input narrative. In one embodiment, a method is provided for enriching an input narrative with multimedia content, wherein the method includes the step of selectively segmenting the input narrative to form queries pertaining to different portions or elements of the input narrative. The method further comprises retrieving multimedia artifacts from one or more multimedia repositories, wherein each retrieved multimedia artifact is associated with one of the queries, and selecting a subset of the retrieved multimedia artifacts, wherein the subset includes artifacts comprising different types of multimedia content. The input narrative is then combined with respective multimedia artifacts of the subset, in order to provide an enriched and enhanced narrative.

Abstract: A method and structure for storing information for one or more semantic objects derived from raw data. A semantic object extracted from the raw data and classified to comprise the semantic object is received, the received semantic object having one or more attributes. A summary of attributes of the semantic object by calculating one or more statistics of one or more of the one or more attributes of the received semantic object, a confidence level of the received semantic object that quantifies a degree of certainty that the received semantic object has been correctly classified and/or labeled; and a compact representation of raw data of the received semantic object are generated. Indexing information for one or more of the summary of attributes and the compact representation of the semantic object is generated.

Abstract: A method and system for storing a semantic object includes summarizing the attributes of a semantic object, indexing the summary of attributes, and storing the summary of attributes and the index of the summary of attributes.

Abstract: Methods and apparatus are provided for rewriting queries during a database query processing operation to include auxiliary attributes not included in the original query, thus improving processing efficiency. For example, in one aspect of the invention, a technique for rewriting a query in a query processing operation includes the following steps. First, the query is processed in accordance with at least a portion of a data set, producing query results. Second, data attributes from the query results are analyzed. Finally, at least one new predicate from at least one auxiliary data attribute is appended on the query.

Abstract: A method and apparatus is disclosed that receives an input narrative in a particular media format, and produces therefrom a multimedia enriched version of the input narrative. In one embodiment, a method is provided for enriching an input narrative with multimedia content, wherein the method includes the step of selectively segmenting the input narrative to form queries pertaining to different portions or elements of the input narrative. The method further comprises retrieving multimedia artifacts from one or more multimedia repositories, wherein each retrieved multimedia artifact is associated with one of the queries, and selecting a subset of the retrieved multimedia artifacts, wherein the subset includes artifacts comprising different types of multimedia content. The input narrative is then combined with respective multimedia artifacts of the subset, in order to provide an enriched and enhanced narrative.