An apparatus includes a camera and a processor circuit. The camera may be configured to capture color images in response to visible light and monochrome infrared images in response to infrared light. The processor circuit may be configured to extract color features from the color images and add color to corresponding monochrome features detected in the monochrome infrared images.

Methods, computer program products, and/or systems are provided that perform the following operations: obtaining video data; dividing the video data into a plurality of video fragments based, at least in part, on page detection; extracting one or more elements from each of the plurality of video fragments; determining element type data for each of one or more extracted elements; generating element style data for the one or more extracted elements; determining page flow for the plurality of video fragments; and generating one or more pages based, at least in part, on the one or more elements extracted from the plurality of video fragments, the element type data, the element style data, and the page flow.

Systems, methods, and non-transitory computer-readable media can obtain a test content item having a plurality of video frames. At least one video fingerprint is determined based on a set of video frames corresponding to the test content item. At least one reference content item is determined using at least a portion of the video fingerprint. At least one portion of the test content item that matches at least one portion of the reference content item is determined based at least in part on the video fingerprint of the test content item and one or more video fingerprints of the reference content item.

Systems and methods for identifying and associating contextual metadata across related media.

A processor receives a first list comprising a plurality of events from a portion of digital data of an unknown work and one or more metrics between each pair of adjacent events from the plurality of events. The processor compares the first list to a second list comprising events and metrics between events for a known work to determine a first quantity of hits and a second quantity of misses. The processor determines whether the first list matches the second list based on the first quantity of hits and the second quantity of misses. The processor determines that the unknown work is a copy of the known work responsive to determining that the first list matches the second list.

An invention for identifying a spatial location of an event within video image data is provided. Disclosed are embodiments for detecting an object and obtaining trajectory data of a trajectory of the object within the video image data from a sensor device; converting the trajectory data into a contour-coded compressed image; generating, based on the trajectory data, a searchable code that contains a set of locations traversed by the trajectory of the object within the video image; associating the searchable code with the contour-coded compressed image in a database; and returning, in response to a query having a selected location that corresponds a location of the set of locations in the searchable code, an image of the trajectory data corresponding to the object based on the contour-coded compressed image in the database.

The disclosure includes a system and method for decomposing a video to salient fragments and synthesizing a video composition based on the salient fragments. A computer-implemented method receives a first set of salient fragments and a first set of clusters extracted from a video, where each cluster includes related salient fragments connected by a connectivity graph. The method determines a weight associated with each of the salient fragments and each of the clusters based on an activity level associated with the respective salient fragment or cluster and determine a permissible zone of activity. The method determines a spatial-temporal distortion to be applied to each salient fragment and cluster and synthesizes a video composition based on the first set of salient fragments, the first set of clusters and non-salient portions of the video using weighted editing.

Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.

The present disclosure relates to a terminal, an apparatus, and a method for providing search information based on color information, the method including, acquiring a search keyword; selecting one or more colors, correlated with the acquired keyword, based on a pre-stored keyword-color information correlation; searching for an object that matches with the selected color; and configuring an interface page information including information about the searched object.

A video abstract generation method is provided. The method includes obtaining a target searching condition; searching a video database for structured image data meeting the target searching condition, the structured image data being stored in the video database in a structured data format; and performing video synthesis on the structured image data meeting the target searching condition, to generate a video abstract.