Technical solutions for video event recognition relate to the fields of knowledge graphs, deep learning and computer vision. A video event graph is constructed, and each event in the video event graph includes: M argument roles of the event and respective arguments of the argument roles, with M being a positive integer greater than one. For a to-be-recognized video, respective arguments of the M argument roles of a to-be-recognized event corresponding to the video are acquired. According to the arguments acquired, an event is selected from the video event graph as a recognized event corresponding to the video.

A facial verification method includes separating a query face image into color channel images of different color channels, obtaining a multi-color channel target face image with a reduced shading of the query face image based on a smoothed image and a gradient image of each of the color channel images, extracting a face feature from the multi-color channel target face image, and determining whether face verification is successful based on the extracted face feature.

The present invention provides a method of facial expression recognition including 3 steps: step 1: collecting facial expression data, which contributes to solve the problem of lacking data, disparate and bias data, that cause the overfitting problem when training the deep learning model; step 2: designing a new deep learning network that able to focus on special regions of the face to extract and learn the important features of facial expressions by intergating ensemble attention modules into basic deep network architecture like ResNet; step 3: training the ensemble attention deep learning model in step 2 on the collected dataset in step 1, using the combination of two loss functions including ArcFace and Softmax to reduce the overfitting problem.

Embodiments of the present invention provide a system for determining real-time resource capacity of entity devices based on performing predictive analysis. In particular, the system may be configured to identify one or more users at a location of an entity device waiting to perform one or more interactions via the entity device, establish a communication link with the entity device, determine identity of the one or more users based on communicating with the entity device, calculate an estimated interaction amount associated with the one or more interactions of the one or more users, determine capacity of the entity device in real-time, identify that the capacity of the entity device does not meet the calculated estimated interaction amount, and transmit a notification to at least one user of the one or more users via the entity application present on a user device of the at least one user.

A processor-implemented method with data recognition includes: extracting input feature data from input data; calculating a matching score between the extracted input feature data and enrolled feature data of an enrolled user, based on the extracted input feature data, common component data of a plurality of enrolled feature data corresponding to the enrolled user, and distribution component data of the plurality of enrolled feature data corresponding to the enrolled user; and recognizing the input data based on the matching score.

Aspects of the present disclosure include methods for generating a heatmap including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light, identifying one or more macroblocks each includes a subset of the plurality of sampling points, calculating a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks, generating a first array including a plurality of weighted values by calculating the plurality of weighted values based on the numbers of occurrences of the local pattern value and corresponding sizes of the one or more macroblocks, assigning a unique index to each of the plurality of weighted values, generating a second array of the unique index by ranking the plurality of weighted values, and generating a third array including a plurality of ranking distances.

An on-person portable device and/or app that allows for constant location monitoring of dementia patients is disclosed. Such a device and/or app also includes automated communication of facial recognition of persons proximally near such a patient as well as possible generation of certain music in response to patient status and/or location. The patient is provided the device and/or app for handling or wearing, such as a phone or pair of glasses, in order to follow location through GPS monitoring, and a reactive program therein that automatically views another person and provides an identification thereof coupled with a voice modulator within an earpiece or like device for memory stimulation pertaining to loved ones or friends, and the like. The same program may also provide the music response to comments, movement, or any other external stimuli to the subject patient, again, to evoke a memory stimulus, as well.

A media source is configured to provide a media stream that includes an audio-video recording. The audio-video recording comprises image frames. A video presentation device receives the media stream provided by the media source and selects a portion of the image frames of the media stream. The device determines, based at least in part on characteristics of the video presentation device and properties of the selected portion of the image frames, a processing resource for executing an algorithm configured to determine a probability that the media stream includes synthetic media. The selected portion of the frames and an indication of the algorithm are provided to the processing resource. The processing resource executes the algorithm to determine the probability that the media stream includes synthetic media. The audio-video recording and a representation of the probability that the media stream includes synthetic media are displayed.

A system for data recording across a network includes a session border controller connecting incoming data from the network to an endpoint recorder. A load balancer is connected to the network between the session border controller and the endpoint and receives the incoming data from the session border controller, wherein the load balancer comprises computer memory and a processor configured to parse the incoming data into video data and audio data according to identification protocols accessible by the processor from the computer memory. A recording apparatus includes recording memory that receives the incoming data from the load balancer, stores a duplicate version of the incoming data in the recording memory, and connects the incoming data to the endpoint.

Techniques for changing the presentation of information on a user interface based on presence are described. In an example, a computer system determines, based on an image sensor associated with the system, a first presence of a first user relative to a computing device. The computer system also determines an identifier of the first user. The identifier is associated with operating the computing device. The operating comprises a presentation of the user interface by the computing device. The computer system also determines, based on the image sensor, a second presence of a second person relative to the computing device. The computer system causes an update to the user interface based on the second presence.