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 constructing a hierarchical multi-faceted classification structure includes organizing a plurality of visual categories into a multi-relational reference ontology that accounts for a plurality of different types of relationships. Media artifacts are categorized into the plurality of visual categories. The categories of artifacts are refined based on faceted ontology relationships or constraints from the multi-relational reference ontology. The multi-relational reference ontology and the one or more media artifacts with relationships are stored as the hierarchical multi-faceted classification structure in computer readable memory storage.

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: Techniques for tracking one or more objects at each position in an interval in a video input with the use of a Kalman filter, including obtaining a first location estimate of an object with an object detector, obtaining a second location estimate and a movement estimate of the object with an object tracker, determining a final estimate of a position and/or a velocity of the object with the Kalman filter.

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: Techniques for tracking one or more objects at each position in an interval in a video input with the use of a Kalman filter, including obtaining a first location estimate of an object with an object detector, obtaining a second location estimate and a movement estimate of the object with an object tracker, determining a final estimate of a position and/or a velocity of the object with the Kalman filter.

Abstract: A technique for semantic video compression is shown in block (120). Uncompressed video data (210), including a plurality of video data segments (S1, S2, . . . Sn), are organized into two or more buffer slots (220), such that each of the two or more buffer slots is filled with one or more of the received video data segments, thereby forming two or more buffered video portions corresponding to the two or more buffer slots. The buffered video data is then processed by a leaking rule, to extract one or more buffered video portions, while outputting one or more non-extracted buffered video portions, as compressed video data (230). The leaking rule data is stored in a histogram (240) and later used to organize and index data according to a users request.

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: 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: Each video segment in a plurality of video segments is annotated with an indicator of the likelihood that the respective video segment shows a particular feature. The plurality of video segments forms an episode of interest from a given video domain. Initial feature probabilities are calculated for respective ones of the plurality of video segments using a machine learning algorithm. Each initial feature probability indicates the likelihood that its respective video segment shows the particular feature. Refined feature probabilities are determined for respective ones of the plurality of video segments by finding the most probable state sequence in a finite state machine. This is accomplished at least in part using the determined initial feature probabilities. Finally, each of the video segments in the plurality of vides segments is annotated with its respective refined feature probability.

Abstract: A system and method for constructing a hierarchical multi-faceted classification structure includes organizing a plurality of visual categories into a multi-relational reference ontology that accounts for a plurality of different types of relationships. Media artifacts are categorized into the plurality of visual categories. The categories of artifacts are refined based on faceted ontology relationships or constraints from the multi-relational reference ontology. The multi-relational reference ontology and the one or more media artifacts with relationships are stored as the hierarchical multi-faceted classification structure in computer readable memory storage.

Abstract: A method for selecting a subsequence of video frames (72-84) from a sequence of video frames (70) comprising defining a distance function between video frames (72-84) in the sequence of video frames (70). An optimization criterion is defined to express a feature of a plurality of subsequences of video frames (72-84) selected from the sequence of video frames (70). A method is disclosed for displaying key frames for browsing and streaming.

Abstract: A technique for semantic video compression is shown in block (120). Uncompressed video data (210), including a plurality of video data segments (S1, S2, . . . Sn), are organized into two or more buffer slots (220), such that each of the two or more buffer slots is filled with one or more of the received video data segments, thereby forming two or more buffered video portions corresponding to the two or more buffer slots. The buffered video data is then processed by a leaking rule, to extract one or more buffered video portions, while outputting one or more non-extracted buffered video portions, as compressed video data (230). The leaking rule data is stored in a histogram (240) and later used to organize and index data according to a users request.

Abstract: A method, system and program product developing an annotation lexicon are described. Under aspects of the present invention, annotation(s) to piece(s) of content are received and analyzed using one or more computational analyses. Based on the analyses, feedback will be generated to improve the annotation lexicon and/or the ontology thereof. Such improvement can lead to, among other things: the re-arrangement of interrelationships of terms in the annotation lexicon; the addition, modification or deletion of terms from the annotation lexicon; the re-arrangement or clustering of terms within the annotation lexicon; etc.

Abstract: A technique for semantic video compression is shown in block (120). Uncompressed video data (210), including a plurality of video data segments (S1, S2, . . . Sn), are organized into two or more buffer slots (220), such that each of the two or more buffer slots is filled with one or more of the received video data segments, thereby forming two or more buffered video portions corresponding to the two or more buffer slots. The buffered video data is then processed by a leaking rule, to extract one or more buffered video portions, while outputting one or more non-extracted buffered video portions, as compressed video data (230). The leaking rule data is stored in a histogram (240) and later used to organize and index data according to a users request.