An occupant monitoring device includes: an acquisition unit that acquires a captured image obtained by imaging a region in which there is a probability that a face of an occupant is present in a vehicle; a determination unit that determines whether the captured image acquired by the acquisition unit corresponds to a first image including the face a part of which is hidden by an accessory or a second image including the face a part of which is hidden by a non-accessory object other than the accessory; and a processing unit that detects face information regarding the face of the occupant based on the captured image in different modes according to a determination result in the determination unit, and monitors a state change of the face of the occupant based on a detection result.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining the number of speakers in a video and a corresponding audio using visual context. In one aspect, a method includes detecting within the video multiple speakers, determining a bounding box for each detected speaker that includes the detected person and objects within a threshold distance of the detected person in an image frame, determining a unique descriptor for that person based in part on image information depicting the objects within the bounding box, determining a cardinality of unique speakers in the video, providing to the speaker diarization system the cardinality of unique speakers.

Aspects of the disclosure can provide method for identifying a face where multiple images to be identified are received. Each of the multiple images includes a face image part. Each face image of face images in the multiple images to be identified is extracted. An initial figure identification result of identifying a figure in the each face image is determined by matching a face in the each face image respectively to a face in a target image in an image identification library. The face images are grouped. A target figure identification result for each face image in each group is determined according to the initial figure identification result for the each face image in the each group.

A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analysis of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.

Techniques for automated facial measurement are provided. A set of coordinate locations for a set of facial landmarks on a face of a user are extracted by processing a first image using one or more landmark-detection machine learning models. An orientation of the face of the user is determined. It is determined that impedance conditions are not present in the set of images, and a reference distance on the face of the user is estimated based on the first image, where the first image depicts the user facing towards the imaging sensor. A nose depth of the user is estimated based on a second image of the set of images based at least in part on the reference distance, where the second image depicts the user facing at an angle relative to the imaging sensor. A facial mask is selected for the user based on the nose depth.

A method by one or more network devices executing one or more smart contracts stored in a blockchain for anonymizing faces appearing in digital media content. The method includes obtaining, for each of a plurality of users, a facial model associated with that user, obtaining digital media content digital media content, determining whether that detected face matches the face of any of the plurality of users based on applying one or more of the facial models associated with the plurality of users to that detected face, anonymizing that detected face to generate an anonymized face in response to a determination that that detected face matches the face of one of the plurality of users, and providing the anonymized face to the media platform.

Methods for face detection to address privacy in publishing image datasets is described. A method may include face classification in an online marketplace. A server system may receive, from a seller user device, a listing including an image for the online marketplace. The server system may classify, by at least one processor that implement a distribution-balance trained machine learning model, each human face candidate within the image as being one of a private human face or a non-private human face. The server system may receive, from a buyer user device, a search query that is mapped to the listing in the online marketplace. The server system may transmit, to the buyer user device, a query response including the listing that includes the image determined to not include any private human faces or obscures any private human faces within the image based on the classifying.

Described is an apparatus (1) and a method for recognizing facial orientation comprising a storage unit (2), at least one optical instrument (3) and a control unit (4). The storage unit (2) is designed to record a plurality of predetermined positions of interest (5) belonging to an exposure surface (6). The optical facial recognition instrument (3) is configured for acquiring data relating to a face (7) of at least one observer (8). The control unit (4) is connected to the storage unit (2) and to the at least one optical instrument (3) with the aim of estimating a pose vector (B) and identifying when the latter is stationary in the positions of interest (5).

The disclosure provides a method for processing a video, an electronic device, and a computer storage medium. The method includes: determining a plurality of first identifiers related to a first object based on a plurality of frames including the first object in a target video; determining a plurality of attribute values associated with the plurality of first identifiers based on a knowledge base related to the first object; determining a set of frames from the plurality of frames, in which one or more attribute values associated with one or more first identifiers determined from each one of the set of frames are predetermined values; and splitting the target video into a plurality of video clips based on positions of the set of frames in the plurality of frames.

Various aspects of the subject technology relate to systems, methods, and machine-readable media for virtual fitting of items such as spectacles and/or spectacle frames. A user interface for virtual fitting may be implemented at a server or at a user device, and utilize three-dimensional information for the user and three-dimensional information for each frame, with frame information stored in a frame database, to identify and/or recommend frames that are likely to fit the user. Fit information can be provided for a group of frames or for each individual frame selected by the user. The fit information can be provided with a static image of the frames and/or within a virtual try-on operation in which the frames are virtually placed on a real-time image of the user.