There is provided a method for searching a plurality of information sources using a multimedia element, the method may include receiving at least one multimedia element; generating, by a signature generator, for the at least one multimedia element at least one signature that is unidirectional, and yields compression; generating at least one textual search query using the at least one signature; wherein the generating of the textual search query comprises: (a) searching for at least one matching stored signature that matches one or more of the at least one signature; and (b) using a mapping between stored signatures and textual search queries, selecting at least one textual search query mapped to at least one matching stored signature; searching the plurality of information sources using the at least one textual search query; and causing a display of search results retrieved from the plurality of information sources.

This disclosure provides a video generation method, a video generation apparatus, an electronic device, a storage medium and a program product, and relates to the field of artificial intelligence technology, and in particular to the field of computer vision technology and deep learning technology. A specific implementation includes: obtaining document content information of a document; extracting, from the document content information, populating information for multiple scenes in a preset video template; populating the populating information for the multiple scenes into corresponding scenes in the preset video template, respectively, to obtain image information of the multiple scenes; generating audio information of the multiple scenes according to the populating information for the multiple scenes; generating a video of the document based on the image information and audio information of the multiple scenes.

Embodiments relate to systems, processes and devices for an information delivery platform or data hub with an alert processor that can be configured to receive a request to generate an alert configuration at the data hub, the request indicating a target unit; generate and store an alert rule corresponding to the alert configuration, the alert rule having a trigger and an action; detect an event at the data hub based on a set of data of the data stored at the data hub, the event having event data; convert the event data to an alert trigger at the data hub based on the trigger of the alert rule; generate an alert notification for the alert trigger based on the action of the alert rule; and transmit the alert notification to the target unit.

System and methods are provided that generate a three-dimensional model from a physical space. While a user is scanning and/or recording the physical space with a user computing device, user speech describing the physical space is recorded. A transcript is generated from the audio captured during the scan and/or image recording of the physical space. Keywords from the transcript are used to improve computer-vision object identification, which is incorporated in the three-dimensional model.

A computer-implemented method, a computer program product, and a computer system for dynamically creating a composition reference video to support a user activity. In response to that a user selects a reference video for performing an activity, the computer system identifies a search query of a reference video. The computer system identifies personalized parameters of the user, based on a knowledge corpus user preferences of performing activities, and the search query. The computer system identifies appropriate videos and video transcripts in an online video repository and identifies textual contents through document and text search, based on a prediction about how the user is to perform the activity. The computer system draws series of images based on the textual contents. The computer system normalizes contents from the appropriate videos and the series of images and normalizes voices in the contents from the appropriate videos.

Automated product identification within hosted and streamed videos is performed based on video content of a video received at an online video platform and text content associated with the video. First embeddings representative of one or more first candidate products are determined based on video content of the video, such as one or more frames selected from within the video. Second embeddings representative of one or more second candidate products are determined based on text content associated with the video, such as a title, description, or transcript of the video. A product candidate index is produced based on the second embeddings. A product identification representative of a product featured in the video is determined based on a comparison of the first embeddings against entries of the product candidate index, such as including by a nearest neighbor search responsive to the comparison. An indication of the product identification is then output at the online video platform.

Method and apparatus for obtaining audio corresponding to a plurality of images, based on semantic information and the emotion information of the plurality of images.

A term weight determination method includes: obtaining a video and video-associated text, the video-associated text including at least one term; generating a halfway vector of the term by performing multimodal feature fusion on the features of the video, the video-associated text and the at least one term; and generating the weight of the at least one term based on the halfway vector of the at least one term.

Techniques for using contextual information relating to content presented by a television as part of a search query for an information search are presented. A search management component, at a given moment in time during presentation of television-related content by a communication device in or associated with a television, identifies contextual information associated with a section of the television-related content and generates a content identifier timestamp associated with the contextual information and the section of television-related content. A search component augments a search query using the contextual information to facilitate customization of a subset of search results based on the contextual information. The contextual information in the search query can facilitate disambiguating the search query or promoting a search result over another search result in the subset of search results, based on the contextual information, to facilitate customization of the subset of search results.

A method for indexing objects in a computerized system having an index, comprising identifying in the computerized system an at least one indexed object that meets an at least one criterion related to contents of the at least one indexed object, detecting an at least one non-indexed object having a property similar to an at least one property of the at least one indexed object that was identified, and indexing the at least one non-indexed object in the index, wherein the method is performed by the computerized system, and an apparatus for performing the same.