Abstract: Computer-based skimming and scrolling of aurally presented information is described. Different levels of skimming are achieved in aural presentations with allowing a user to navigate an aural presentation according to significant points identified within an information source. The significant points are identified using various indicia that suggest logical arrangements for the information contained within the source, such as semantics, syntax, typography, formatting, named entities, and markup tags. The identified significant points signal changes in playback mode for the audio presentation, such as different tones, pitches, volumes, or voices. Similar indicia may be used to generate identifying markers from the information source that can be aurally presented in lieu of the information source itself to allow for aural scrolling of the information.

Abstract: Exemplary methods and apparatuses are provided which may be implemented using one or more computing devices to allow for super clustering of clusters of electronic documents based, at least in part, on structural and static content features.

Abstract: Web pages are efficiently categorized in a data processor without analyzing the content of the web pages. According to at least one embodiment, data is maintained that represents sample URLs grouped into a plurality of clusters. The sample URLs of a cluster are used to produce a URL regular expression pattern (“URL-regex”) that differentiates the sample URLs of the cluster from the sample URLs of other clusters and that covers at least a specified percentage of the sample URLs in the cluster. The process of producing a URL-regex is repeated for each of the clusters producing a URL-regex for each cluster. Web pages are then categorized into one of the clusters by determining which of the URL-regex patterns produced for the clusters match URLs that refer to the web pages. Thus, a web page may be categorized based on a URL that refers to the web page without having to obtain and analyze the content of the web page.

Abstract: Methods and systems are provided that may be used to determine a whether an image contains spam. In one particular embodiment, an image is transformed and spam is detected based on such a transformed image.

Abstract: An example of a method of identifying objects having desired characteristics includes obtaining images of objects and metadata associated with each image. Further, the method includes automatically initializing a portion of the each image as at least one of a foreground portion and a background portion according to the metadata associated with the each image. Furthermore, the method includes segmenting the each image into the foreground portion and the background portion. In addition, the method includes determining at least one foreground portion depicting an object of the desired characteristics. Further, the method includes electronically providing an image corresponding to the at least one foreground portion.

Abstract: Slideshow video file detection. A method includes receiving a search query for video files of a desired type. A portion of a video file is extracted. A frame difference based histogram and an active pixel based histogram are generated for the portion. Further, the frame difference based histogram and an active pixel based histogram are provided to a machine learning tool. An indicator is determined for the portion based on a plurality of parameters. The video file is classified as the desired type based on the indicator. The video file is provided to the user.

Abstract: The present invention provides a method and system for determining near-duplicate images. The method and system includes performing a Fourier-Mellin transform on each of a plurality of images. For each image of the plurality of images, the method and system includes generating a signature based on the Fourier-Mellin transform. The method and system includes comparing the signature of at least one of the images to at least one of the signatures of the other plurality of images and determining any near duplicate images based on the comparing of the signatures.

Abstract: A method for achieving uninterrupted interactivity for user watching a video yet clicking on an advertisement is provided. A method for delayed interactivity is provided herein. Delayed interactivity is implemented in the form of delayed insertions. When a user clicks on an object in hypervideo, presentation of or any action on the related information is deferred rather than played immediately. Delayed interactivity also is implemented in the form of video bookmarks. When a user clicks on an actual advertisement, related information is stored, i.e., bookmarked, along with video content. In this way, the user can pursue the related information at a later time and at the user's convenience.

Abstract: The present invention is directed towards systems and methods for filtering unsafe content items within a multimedia repository. The method of the present invention comprises automatically identifying a first plurality of unsafe content items from the content items and automatically identifying a second plurality of unclassifiable content items from the content items. The method identifies a third plurality of unsafe content items from the content items, the third plurality of unsafe content items identified according to a similarity to the first plurality and manually identifying a fourth plurality of unsafe content items, the fourth plurality of unsafe content items comprising a subset of the second plurality of unclassifiable items. A fifth plurality of unsafe content items is then identified, the fifth plurality of unsafe content items identified according to a similarity to the fourth plurality.

Abstract: A method for deriving probabilistic association scores based on image content is provided. A bipartite graph is constructed based on a database of image content and associated textual content. One partition of the bipartite graph contains image content and the other partition of the bipartite graph contains textual content. Weighted edges between nodes in the two partitions represent associations between the image content and textual content in the database. Random walks on the bipartite graph are performed to derive probabilistic association scores between image content and textual content. Association scores are used to automatically annotate images and detect spurious image tags.

Abstract: Exemplary methods and apparatuses are provided which may be implemented using one or more computing devices to allow for super clustering of clusters of electronic documents based, at least in part, on structural and static content features.

Abstract: Web pages are efficiently categorized in a data processor without analyzing the content of the web pages. According to at least one embodiment, data is maintained that represents sample URLs grouped into a plurality of clusters. The sample URLs of a cluster are used to produce a URL regular expression pattern (“URL-regex”) that differentiates the sample URLs of the cluster from the sample URLs of other clusters and that covers at least a specified percentage of the sample URLs in the cluster. The process of producing a URL-regex is repeated for each of the clusters producing a URL-regex for each cluster. Web pages are then categorized into one of the clusters by determining which of the URL-regex patterns produced for the clusters match URLs that refer to the web pages. Thus, a web page may be categorized based on a URL that refers to the web page without having to obtain and analyze the content of the web page.

Abstract: The present invention is directed towards systems and methods for improving image labeling using content-based image retrieval. The method according to one embodiment of the present invention comprises selecting an image query and identifying a first image related to the image query. The method then selects a plurality of second images related to the first image and assigns weights to the plurality of second images. Finally, the method displays the first images and the second images on a client device.

Abstract: A method for expanding a query to include additional terms associated through visual content is provided. A bipartite graph is constructed based on a database of visual content and associated textual content. One partition of the bipartite graph contains visual content and the other partition of the bipartite graph contains textual content. Weighted edges between nodes in the two partitions represent associations between the visual content and textual content in the database. Random walks on the bipartite graph are performed to derive probabilistic association scores between textual content that are indirectly associated with each other through visual content. The query is expanded to include additional terms whose equivalent textual content is highly associated with the query's equivalent textual content.

Abstract: Techniques for high precision web extraction using site knowledge are provided. Portions of repeating text are identified in unlabeled web pages from a particular web site. Based on the portions of repeating text, the unlabeled web pages are partitioned into a set of segments. Multiple labels are assigned to respectively corresponding multiple attributes in the set of segments, where assigning the multiple labels comprises applying a classification model to each separate segment in the set of segments. First one or more labels are identified that were erroneously assigned to one or more attributes in the set of segments. Second one or more correct labels for the one or more attributes are determined. The first one or more labels in the set of segments are corrected by assigning the second one or more labels to the one or more attributes.

Abstract: A method and apparatus for improved sampling documents for training sets input to information extraction systems is provided, which improves the recall and robustness of wrapper extraction. A passive sampling technique provides a list of documents to present for human annotation ordered by representativeness of the document based on structural and content statistics. Thus, the document with the most interesting attributes and which is most representative of the cluster of structurally similar documents to which the document pertains is presented for annotation first. The problem is mapped to classical ‘Set-Cover’ problem and solved using greedy approach. An active sampling technique refines and reorders the sample list produced by the passive sampling technique after initial annotations, based on the human annotation, spatial boundaries of the documents, and structural and content statistics.

Abstract: A method and apparatus for automatically extracting information from a large number of documents through applying machine learning techniques and exploiting structural similarities among documents. A machine learning model is trained to have at least 50% accuracy. The trained machine learning model is used to identify information attributes in a sample of pages from a cluster of structurally similar documents. A structure-specific model of the cluster is created by compiling a list of top-K locations for each attribute identified by the trained machine learning model in the sample. These top-K lists are used to extract information from the pages of the cluster from which the sample of pages was taken.

Abstract: Embodiments of methods, apparatuses, or systems relating to updating wrapper annotations are disclosed.

Abstract: Embodiments of methods, apparatuses, or systems relating to identifying previously annotated web page information are disclosed.

Abstract: Slideshow video file detection. A method includes receiving a search query for video files of a desired type. A portion of a video file is extracted. A frame difference based histogram and an active pixel based histogram are generated for the portion. Further, the frame difference based histogram and an active pixel based histogram are provided to a machine learning tool. An indicator is determined for the portion based on a plurality of parameters. The video file is classified as the desired type based on the indicator. The video file is provided to the user.