A deep learning-based video editing method can allow for automated editing of a video, reducing or eliminating user input, saving time and labor investments, and thereby improving video editing efficiency. Attribute recognition is performed on an object in a target video using a deep learning model. A target object is selected that satisfies an editing requirement of the target video. A plurality of groups of pictures associated with the target object from the target video are obtained using editing. An edited video corresponding to the target video is generated using the plurality of groups of pictures.

Techniques are disclosed for performing video synthesis of audiovisual content. In an example, a computing system may determine first parameters of a face and body of a source person from a first frame in a video shot. The system also determines second parameters of a face and body of a target person. The system determines that the target person is a replacement for the source person in the first frame. The system generates third parameters of the target person based on merging the first parameters with the second parameters. The system then performs deferred neural rendering of the target person based on a neural texture that corresponds to a texture space of the video shot. The system then outputs a second frame that shows the target person as the replacement for the source person.

Techniques are disclosed for performing video synthesis of audiovisual content. In an example, a computing system may determine first facial parameters of a face of a particular person from a first frame in a video shot, whereby the video shot shows the particular person speaking a message. The system may determine second facial parameters based on an audio file that corresponds to the message being spoken in a different way from the video shot. The system may generate third facial parameters by merging the first and the second facial parameters. The system may identify a region of the face that is associated with a difference between the first and second facial parameters, render the region of the face based on a neural texture of the video shot, and then output a new frame showing the face of the particular person speaking the message in the different way.

A method including providing a sensor device including one or several sensors. The sensor device is arranged to perform at least one high-power type measurement and at least one low-power type measurement and includes at least one image sensor arranged to depict a person by a measurement of said high-power type. Each of the low-power type measurements over time requires less electric power for operation as compared to each of the high-power type measurements. The method includes detecting a potential presence of the person using at least one of said low-power type measurements. The method includes producing, using one of the high-power type measurements, an image depicting a person and detecting a presence of the person based on im-age analysis of the image. The method includes detecting, using at least one of the low-power type measurements, a maintained presence of the person. The method includes failing to detect a maintained presence of the person.

A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

A visual tracking system for tracking and identifying persons within a monitored location, comprising a plurality of cameras and a visual processing unit, each camera produces a sequence of video frames depicting one or more of the persons, the visual processing unit is adapted to maintain a coherent track identity for each person across the plurality of cameras using a combination of motion data and visual featurization data, and further determine demographic data and sentiment data using the visual featurization data, the visual tracking system further having a recommendation module adapted to identify a customer need for each person using the sentiment data of the person in addition to context data, and generate an action recommendation for addressing the customer need, the visual tracking system is operably connected to a customer-oriented device configured to perform a customer-oriented action in accordance with the action recommendation.

A method for driver identification including recording a first image of a vehicle driver; extracting a set of values for a set of facial features of the vehicle driver from the first image; determining a filtering parameter; selecting a cluster of driver identifiers from a set of clusters, based on the filtering parameter; computing a probability that the set of values is associated with each driver identifier of the cluster; determining, at the vehicle sensor system, driving characterization data for the driving session; and in response to the computed probability exceeding a first threshold probability: determining that the new set of values corresponds to one driver identifier within the selected cluster, and associating the driving characterization data with the one driver identifier.

A system for authenticating a user attempting to access a computing device or a software application executing thereon. A data storage device stores one or more digital images or frames of video of face(s) of authorized user(s) of the device. The system subsequently receives from a first video camera one or more digital images or frames of video of a face of the user attempting to access the device and compares the image of the face of the user attempting to access the device with the stored image of the face of the authorized user of the device. To ensure the received video of the face of the user attempting to access the device is a real-time video of that user, and not a forgery, the system further receives a first photoplethysmogram (PPG) obtained from a first body part (e.g., a face) of the user attempting to access the device, receives a second PPG obtained from a second body part (e.g., a fingertip) of the user attempting to access the device, and compares the first PPG with the second PPG. The system authenticates the user attempting to access the device based on a successful comparison of (e.g., correlation between, consistency of) the first PPG and the second PPG and based on a successful comparison of the image of the face of the user attempting to access the device with the stored image of the face of the authorized user of the device.

Systems and methods include an image capture component configured to capture infrared images of a scene, and a logic device configured to identify a target in the images, acquire temperature data associated with the target based on the images, evaluate the temperature data and determine a corresponding temperature classification, and process the identified target in accordance with the temperature classification. The logic device identifies a person and tracks the person across a subset of the images, identify a measurement location for the target in a subset of the images based on target feature points identified by a neural network, and measure a temperature of the location using corresponding values from one or more captured thermal images. The logic device is further configured calculate a core body temperature of the target using the temperature data to determine whether the target has a fever and calibrate using one or more black bodies.

Provided are systems and methods for personalized videos featuring multiple persons. An example method includes receiving a user selection of a video having at least one frame with metadata that include a first location and a second location and receiving an image of a source face and a further image of a further source face, modifying the image of the source face to generate an image of a modified source face and modifying the further image of the further source face to generate an image of a modified further source face, inserting, in the at least one frame of the video, the image of the modified source face at the first location and the image of the modified further source face at the second location to generate a personalized video, and sending the personalized video via a communication chat.