Methods and systems are described for managing access to a virtual session. A user device can send a request for a virtual session to a virtual desktop interface (“VDI”) server. The VDI server can send details of a user's account to a management server. The management server can send a machine learning (“ML”) model trained to identify the user's face to the user device. The user device can apply the ML model to a video feed of the viewing area of the user device to verify the user's face. The VDI server can initialize the virtual session if the user's face is verified. The user device can monitor the video feed during the virtual session to detect unauthorized objects. If an unauthorized object is detected, the user device can terminate or minimize the session.

In some examples, a computer system may receive video from one or more video sources. The computer system may detect a plurality of faces in a first video portion of the received video. Further, the computer system may determine that a first face of the plurality of faces has features indicative of an emotion of interest. Based on determining that the first face has the features indicative of the emotion of interest, the computer system may redact other faces of the plurality of faces while leaving the first face unredacted in the first video portion. The computer system may send the first video portion with the first face unredacted and the other faces redacted to at least one computing device.

Disclosed are systems and methods for improving interactions with and between computers in computerized security and content monitoring, hosting and providing devices, systems and/or platforms. The disclosed systems and methods provide a novel framework that adaptively distinguishes between known people versus unknown people based on a dynamically applied, anonymous facial recognition methodology. The disclosed framework provides such functionality by recognizing faces within captured images without storing any information or annotations regarding or revealing the captured person's identity. The framework is configured to adaptively learn to distinguish between faces seen for the first time and faces it has previously seen by locally processing a captured image and only sending face embeddings to a network location for future comparisons of subsequently, anonymously captured images.

Methods, systems, and apparatuses, among other things, may detect and store activity in videos based on a spatiotemporal graph representation. Spatiotemporal proximity graphs may be built based on one or more received tracks and may include one or more nodes and each node may include one or more attributes associated with a corresponding entity. One or more spatiotemporal relationships may be identified between the entities based on each spatiotemporal proximity graph one or more activities of the entities may be identified based on the spatiotemporal relationships.

Extracting demographic features from audio streams in a crowd environment includes receiving audio stream signals from a predefined geographical area containing a plurality of individuals, recording the received audio stream signals, extracting demographic features from the recorded audio stream signals, aggregating the extracted demographic features, storing the aggregated demographic features in a database and analyzing aggregated demographic features to generate a summary of demographic characteristics of the plurality of individuals in the predefined geographical area. Demographic features may be aggregated at different levels of granularity. The method and system may include extracting spatial information of the recorded audio stream signals within the geographical area, determining spatial distribution of the aggregated demographic features within the geographical area based on the extracted spatial information and including the spatial distribution in the summary of demographic characteristics. The evolution over time of the aggregated demographic features may be predicted using a machine learning model.

An identity of a customer within an establishment is authenticated using a variety of captured biometric features obtained from sensors and/or video. Video capturing movements/interactions of the customer is analyzed in real time to identify the customer's behavior and actions. Any staff of the establishment who interact with the customer are identified from the video. Transaction data and other data retained for the customer by the establishment are aggregated and linked with the video and the customer identity. The linked data is analyzed in combination with the customer behavior and actions to determine responses within the establishment to customer-initiated transactions. In an embodiment, the customer is authorized to perform at least one transaction within the establishment based on the authenticated identity and linked data without a presentation by the customer of an identification card, a Personal Identification Number (PIN), a password and/or verification by a staff member.

The present disclosure provides examples of a method and apparatus for processing a video, a device and a storage medium. The method may include: acquiring a target video and a target comment of the target video; recognizing a picture in the target video to obtain text information of the picture; determining a target comment matching a content of the text information; and inserting, in response to displaying the picture in the target video, the target comment matching the content in a form of a bullet screen.

A visual search method, a computer device, and a non-transitory computer readable storage medium are provided. An i.sup.th image frame is received. The location and the classification of the subject in the i.sup.th image frame are extracted. A detection block corresponding to the subject is generated. In subsequent image frames of the i.sup.th image frame, the subject is tracked on the basis of the location of the subject in the i.sup.th image frame. The detection block is adjusted on the basis of the tracking result.

A signal transmitting method comprising: inserting a context identifier and a keyword in service data to generate a content; extracting the service data from the content; inserting a description including the context identifier and the keyword to generate media data; generating signaling information including the context identifier and the keyword; and transmitting a signal including the media data and the signaling information.

Systems and methods for identifying related videos based on elements tagged in the videos are presented. In an aspect, a system includes an identification component configured to identify tagged elements in a video, a matching component configured to identify other videos that include one or more of the tagged elements, and a recommendation component configured to recommend the other videos for viewing based on a current or past request to play the video.