Disclosed are systems and methods that convert digital video data, such as two-dimensional digital video data, into a natural language text description describing the subject matter represented in the video. For example, the disclosed implementations may process video data in real-time, near real-time, or after the video data is created and generate a text-based video narrative describing the subject matter of the video. In addition, the disclosed implementations may also support a question and answer session in which a user may submit queries about the subject matter of one or more videos and the disclosed implementations will present natural language responses based on the subject matter of the video and any corresponding context.

Disclosed are various embodiments for processing verbal queries relative to video content. A verbal query that is associated with a portion of video content is received. The verbal query specifies a relative frame location. An action is performed based at least in part on the portion of the video content at the relative frame location.

Disclosed are various embodiments for processing verbal queries relative to video content. A verbal query that is associated with a portion of video content is received. The verbal query specifies a relative frame location. An item depicted in the portion of the video content at the relative frame location is identified. Information about the item is determined as an answer to the verbal query. Information about the item is then presented to a user.

Methods, systems, and products index digital scenes in digital media. A uniform resource locator is assigned to each different digital scene within the digital media. The uniform resource locator uniquely identifies a resource from which each different digital scene may be retrieved. Individual scenes may thus be retrieved, thus conserving bandwidth and memory.

A system and method for training a search query classifier may be used to develop a large database of search queries used to access inappropriate sensitive or offensive content in multiple languages.

Methods, systems, and products index digital scenes in digital media. A uniform resource locator is assigned to each different digital scene within the digital media. The uniform resource locator uniquely identifies a resource from which each different digital scene may be retrieved. Individual scenes may thus be retrieved, thus conserving bandwidth and memory.

A method of real-time video event detection includes: obtaining, based on a natural language query, a query vector; performing multimodal feature extraction on a video stream to obtain a video vector, obtaining a similarity score by comparing the query vector to the video vector; comparing the similarity score to a predetermined threshold; and activating, based on the similarity score being above the predetermined threshold, an action trigger. The multimodal feature extraction is performed using a plurality of overlapping windows that include sequential frames of the video stream.

Fast string search and matching is critical for many security tasks in particular if these have gate functionality for instance as found in access control applications, firewalls, routers, and load balancers. The fast matching of strings is essential to impose and enforce access control policies without creating bottlenecks. Firewalls protect networks by monitoring the traffic crossing the network perimeter. The number of packet matching rules firewalls can effectively handle is limited by the matching time and space complexity of the algorithms employed. A new approach implements matching independent of the number of rules and linear in the length of the rule to be matched. A data structure used in this approach is referred to as a Bipartite Concatenated Representation (BCR). The space complexity of the BCR within this application scenario scales as O(N log.sup.2 N) where N is the number of rules.

A computer-implemented method for on-device video query and search using an artificial neural network (ANN) includes receiving by the ANN, a video and a search query. The video includes a sequence of frames and associated subtitle information. First representations for a first set of words in the search query and second representations for a second set of words in the subtitle information are generated, at the mobile device by the ANN. A correlation between the search query and the subtitle information is determined at the mobile device by the ANN based on the first representations and the second representations. The ANN, at the mobile device. predicts a portion of the video including content responsive to the search query based on the correlation.

One method includes receiving a database query, receiving information about a database table in data storage populated with data elements, producing a structural representation of the database table that includes a formatted data organization reflective of the database table and is absent the data elements of the database table, and providing the structural representation and the database query to a plan generator capable of producing a query plan representing operations for executing the database query on the database table. Another method includes receiving a query plan from a plan generator, the plan representing operations for executing a database query on a database table, and producing a dataflow graph from the query plan, wherein the dataflow graph includes at least one node that represents at least one operation represented by the query plan, and includes at least one link that represents at least one dataflow associated with the query plan.