A method for providing searchable media content includes generating a text file that is representative of an instance of media content. The instance of media content comprises a first scene and a second scene. A first portion of the text file is representative of the first scene and a second portion of the text file is representative of the second scene. The method further includes indexing the first portion with the first scene and indexing the second portion with the second scene.

The present disclosure provides a video timing labeling method. The method includes: acquiring a video file to be labeled and text information to be inquired; acquiring a video segment matching the text information to be inquired based on a timing labeling network of a timing labeling model; acquiring a video feature of the video segment matching the text information to be inquired based on a feature extraction network of the timing labeling model; acquiring text information corresponding to the video segment labeled in the video file based on a visual text translation network of the timing labeling model; and outputting the video segment matching the text information to be inquired and the text information corresponding to the video segment labeled in the video file based on the timing labeling model.

Particular embodiments provide supplemental content that may be related to video content that a user is watching. A segment of closed-caption text from closed-captions for the video content is determined. A first set of information from the segment of closed-caption text, such as terms may be extracted. Particular embodiments use an external source that can be determined from a set of external sources. To determine the supplemental content, particular embodiments may extract a second set of information from the external source. Because the external source may be more robust and include more text than the segment of closed-caption text, the second set of information may include terms that better represent the segment of closed-caption text. Particular embodiments thus use the second set of information to determine supplemental content for the video content, and can provide the supplemental content to a user watching the video content.

Systems and methods for searching, identifying, scoring, and providing access to companion media assets for a primary media asset are disclosed. In response to a request for companion content, metadata within a predefined time period of a play position when the request was made, is downloaded. A dynamic search template that contains search parameters based on the downloaded metadata is generated. In response to the search conducted using the search template, a plurality of companion media assets are identified and then verified. A trust score for the companion media asset is accessed. The trust score may be analyzed and modified based on its contextual relationship to the play position of the primary media asset. If the trust score is within a rating range, then a link to access the companion media asset, or a specific segment or play position within the companion media asset, is provided.

Systems, methods and articles of manufacture for modeling a joint language-visual space. A textual query to be evaluated relative to a video library is received from a requesting entity. The video library contains a plurality of instances of video content. One or more instances of video content from the video library that correspond to the textual query are determined, by analyzing the textual query using a data model that includes a soft-attention neural network module that is jointly trained with a language Long Short-term Memory (LSTM) neural network module and a video LSTM neural network module. At least an indication of the one or more instances of video content is returned to the requesting entity.

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.

The invention relates to a display device and method for controlling the same, the method mainly comprising: capturing a screen in which content is reproduced; extracting a first keyword from an image of the captured screen, generating reliability corresponding to the first keyword, when an input of selecting the first keyword is received from an external remote controller, transmitting the first keyword, feedback information and the reliability to an external server, receiving a second keyword, corrected reliability, and feedback information from the external server, and when an input of selecting the second keyword is received, displaying a screen corresponding to the second keyword.

Disclosed herein are methods, and program products for creating automatically a short video clip summarizing highlights of a long video stream, comprising identifying a plurality of topics in a video stream based on analysis of the video stream's content, extracting a plurality of sentences based on analysis of a textual representation of the content, computing a score for each of the sentences indicating a relation of the respective sentence to each of the topics, selecting a plurality of sentence subsets each comprising one or more sentences having a highest score with respect to a receptive one of the topics, selecting a plurality of video sections of the video stream each mapped to the one or more sentences of a respective sentence subset, and creating a video clip by merging the plurality of video sections each relating to one of the plurality of topics.

Video search mechanism using text based accelerator strip is disclosed. It utilizes the text and timestamp information found in the closed caption and subtitle files to locate specific video content. Knowing a single word in a phrase will create the foundation of a meaningful search. No words are typed directly into the system. The text is arranged in alphabetical order and placed into buckets, which are quickly and easily searched, leaving the user to within 2 seconds of the desired content.

An approach is provided for an information handling system to present knowledge-based information. In the approach, a semantic analysis is performed on the document with the analysis resulting in various sets of semantic content. Each of the sets of semantic content corresponds to an area in the document. The areas of the document are visually highlighted using visual indicators that show the availability of the sets of semantic content to a user via a user interface. In response to a user selection, such as a selection using the user interface or a user specified configuration setting, a selected set of semantic content is displayed to the user using the interface.