Abstract: Diagnostic output is received from an endpoint device connected to a conference. At least one of a location or an orientation of the endpoint device is determined based on the diagnostic output. A configuration setting for the endpoint device is determined based on at least one of the location, or the orientation of the endpoint device. The configuration setting may be obtained from an artificial intelligence engine that is trained based on various configurations of endpoint devices.

Abstract: An addition of a new endpoint device to a virtual conference that includes one or more current endpoint devices is identified. Diagnostic data is received from the new endpoint device responsive to a diagnostic operation initiated in response to identifying the addition of the new endpoint device. A setting configuration for one of the one or more current endpoint devices is determined based on the diagnostic data and on current configuration settings associated with at least some of the one or more current endpoint devices. The one of the one or more current endpoint devices is caused to be configured based on the setting configuration.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media relate to a method for providing video communications with dynamic virtual backgrounds within a communication platform. The system establishes a connection with the calendar account of a user. The calendar account maintains historic and planned meeting details for the user. The system may evaluate the calendar account of the user and automatically generate use rules for virtual backgrounds to be used for planned meetings. Based on contextual information of a planned meeting, the system may apply one of the generated rules and select a virtual background to be used for video communications during the meeting.

Abstract: Selections of content shared from a remote device during a video conference are copied to a destination of a computing device connected to the video conference live or at which a recording of the video conference is viewed. The content shared from the remote device during the video conference is output at a display of the computing device. A portion of the content is selected according to an instruction received from a user of the computing device while output at the display of the computing device to copy to a destination associated with software running at the computing device. The portion of the content is identified using a machine vision process performed against the content while output at the display of the computing device. The portion of the content is then copied to the destination.

Abstract: A processing system may receive an input for scheduling an in-person meeting between meeting participants. The input may include an indication of the meeting participants. The processing system may use a machine learning model to predict preferences of one or more of the meeting participants for attending the physical meeting. The preferences may include a physical location and an availability. The machine learning model may be trained using historical information including a past physical location and a past availability of the one or more meeting participants. The processing system may determine scheduling information for the in-person meeting based on the input and the preferences. The scheduling information may include a time, a date, and a physical location for the in-person meeting. The processing system may transmit the scheduling information to a meeting participant.

Abstract: Illumination testing is performed to passively check the health of a display of a shared device within a physical space, such as a conference room. A test pattern is output to the display within the physical space. Using a camera within the physical space, a test image of the physical space is captured while the test pattern is output to the display. A determination is then made as to whether the display is in a fail state by comparing the test image against a reference image depicting an expected illumination of the physical space according to the test pattern. Where the device is determined to be in a fail state, a notification indicating the fail state is transmitted to an administrator device to alert an administrator associated therewith of the fail state.

Abstract: In some aspects, techniques may include receiving media streams from one or more client devices. The media streams can be received by a virtual conference provider. Also, the techniques may include selecting a subset of the media streams based on one or more characteristics of the media streams. The streams may be selected using a machine learning (ML) model. In addition, the techniques may include identifying one or more segments of the subset of media streams satisfying an inclusion criteria. Moreover, the techniques may include generating a recording of the virtual conference including the one or more identified segments.

Abstract: A computer stores a reference image representing a physical background within a field of view of a camera of a client device. The computer receives, via the camera and during a video conference to which the client device is connected, camera-generated visual data for output to at least one remote device connected to the video conference. The computer identifies, based on facial recognition applied to the camera-generated visual data, foreground imagery representing at least one person and background imagery representing content of the camera-generated visual data other than the foreground imagery. The computer identifies a difference between the background imagery and the reference image. The computer generates a composite image by replacing, within the background imagery of the camera-generated visual data, an item represented within the background imagery and within the identified difference with a co-located part of the reference image.

Abstract: A computing device outputs, to a display of the computing device during a video conference, remotely-generated visual data obtained from at least one remote device and camera-generated visual data captured using a camera of the computing device. The computing device identifies, within the camera-generated visual data, a reflection of at least a portion of data displayed at the display of the computing device. The computing device modifies the camera-generated visual data to remove the reflection. The computing device outputs, to the display of the computing device during the video conference, the modified camera-generated visual data. The computing device transmits the modified camera-generated visual data to the at least one remote device for display thereat during the video conference.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media relate to a method for providing multi-point video presentations with live annotations within a communication platform. First, the system receives video feeds depicting imagery of a number of users. The system then determines a boundary about each user in the video feeds, with the boundaries each having an interior portion and an exterior portion. The system provides a media background for the exterior portions, then generates a composite video for each of the feeds. The system then determines that one or more client devices have annotation permissions, and receives one or more annotation inputs corresponding to at least one of the composite videos. Finally, the system updates at least one of the composite videos to additionally depict the annotation inputs within a third layer.

Abstract: A recording of a conference is selectively configured to include only certain conference content. A server receives, from a requesting user device, a request to generate a recording of a conference. The server outputs, to the requesting user device based on the request, a graphical user interface listing content of the conference to include within the recording of the conference. The content comprises at least one of: audio content from one or more participant user devices connected to the conference, camera-generated video content from the one or more participant user devices, or screensharing video content from the one or more participant user devices. The server receives, via the graphical user interface, a selection of a subset of the content to include in the recording of the conference. The server generates the recording of the conference according to the selection of the subset of the content.

Abstract: A recording of a conference is selectively configured to include only certain conference content. A server receives, from a requesting user device, a request to generate a recording of a conference. The server outputs, to the requesting user device based on the request, a graphical user interface listing content of the conference to include within the recording of the conference. The content comprises at least one of: audio content from one or more participant user devices connected to the conference, camera-generated video content from the one or more participant user devices, or screensharing video content from the one or more participant user devices. The server receives, via the graphical user interface, a selection of a subset of the content to include in the recording of the conference. The server generates the recording of the conference according to the selection of the subset of the content.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media provide for the intelligent configuration of endpoint devices for video conferencing. First, the system identifies a plurality of endpoint devices within a room which are communicatively connected. The system then determines a quantity of the endpoint devices. For each of the endpoint devices, the system performs one or more diagnostic operations to receive diagnostic output from the endpoint device, determines a location and an orientation of the endpoint device within the room using the received diagnostic output, and determines whether the diagnostic output meets or exceeds a threshold for output quality. Finally, the system processes the diagnostic outputs of the endpoint devices to determine an optimal settings configuration for each of the endpoint devices. The optimal settings configuration is dependent on at least the quantity, location, orientation, and output quality of the endpoint devices.

Abstract: A source device provides, during a conference, shared data from the source device participating in the conference to one or more destination devices participating in the conference. The source device receives a representation of a download progress of the shared data at the one or more destination devices. A presenter device prompts a user of the presenter device to select a presentation time of the shared data based on the download progress. The presenter device is the source device or one of the one or more destination devices.

Abstract: Methods and systems provide for preventing content capture within a communication session. In one embodiment, a method maintains a communication session with a number of participants, where session content is presented during the communication session to the participants, and where participants can request the session content to be captured for later access. The system receives or identifies one or more signals for capture prevention to be initiated for at least a portion of the session content. The system further receives, in real time during the communication session, a request from one of the participants for a current portion of session content to be captured. The system then determines, via processing of the one or more signals, that the current portion of session content is to be prevented from capture, and then prevents the current portion of session content from being captured.

Abstract: A virtual background template is identified for a conference. The virtual background template includes a placement of a virtual background boundary area and a tag associated with the virtual background boundary area. Contextual information of the conference is determined to include the tag. In response to determining that the contextual information of the conference includes the tag, a media file is identified based on the tag. The media file is displayed in the virtual background boundary area during the conference. The tag may be received, via a user interface, as textual input into the virtual background boundary area.

Abstract: Session content is presented during a communication session to the participant devices. The participant devices transmit requests for notes to be generated for the session content. One or more segments of the communication session are determined when a threshold number of participant devices that requested notes to be generated is exceeded. Information associated with the one or more segments is transmitted to a participant device of the participant devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media relate to a method for providing video communications with dynamic virtual backgrounds within a communication platform. The system provides a user interface for the configuration of a virtual background configuration template. The user interface receives the placement of at least one virtual background boundary areas that may be associated with at least one particular virtual backgrounds to be used for video communications. The selection of the configuration template to be used and/or the specific virtual backgrounds to be used for a video meeting may be determined based on rules as applied to contextual information of a planned meeting defined in a calendaring system.

Abstract: Methods and systems provide for preventing content capture within a communication session. In one embodiment, a method maintains a communication session with a number of participants, where session content is presented during the communication session to the participants, and where participants can request the session content to be captured for later access. The system receives or identifies one or more signals for capture prevention to be initiated for at least a portion of the session content. The system further receives, in real time during the communication session, a request from one of the participants for a current portion of session content to be captured. The system then determines, via processing of the one or more signals, that the current portion of session content is to be prevented from capture, and then prevents the current portion of session content from being captured.

Abstract: Systems and methods for enforcing consent requirements for sharing virtual meeting recordings are provided herein. In an example, a method may include receiving, from a first client device, a recording privacy request associated with a virtual meeting, and receiving, from a second client device, a request to share a recording of the virtual meeting with one or more recipients. The method may also include modifying, by a video conference provider, at least one of a first audio stream or a first video stream associated with the first client device in the recording based on the recording privacy request, and generating, by the video conference provider, a privatized recording based on the modification of at least one of the first audio stream or the first video stream. The method may also include transmitting, by the video conference provider, the privatized recording to the one or more recipients.