Abstract: Systems and methods for generating virtual characters for video conferencing with feature enhancement are provided. In an example, a computing device access a source human face model, a target human face model, and a source virtual character face model. The device further accesses a first virtual feature triangle marked on the source human face model and a second virtual feature triangle marked on the source virtual character face model. The second virtual feature triangle corresponds to the first virtual feature triangle. The device deforms the source virtual character face model based on the source human face model and the target human face model to generate a target virtual character face model. The deforming includes minimizing a loss function comprising a term defined based on a difference between the second virtual feature triangle and the first virtual feature triangle. The device renders the target virtual character face model.

Abstract: Systems and methods for generating virtual characters for video conferencing via a two-stage process are provided. In an example, a computing device accesses a source human face model, a target human face model, and a source virtual character face model. The computing device deforms the source virtual character face model based on the source human face model and the target human face model to generate a target virtual character face model. The source virtual character face model includes a face region and a non-face region. Deforming the source virtual character face model includes deforming the face region by fixing the non-face region and deforming the non-face region by fixing the deformed face region. The computing device renders the target virtual character face model.

Abstract: Systems and methods for generating virtual characters for video conferencing are provided. In an example, a computing device accesses a source human face model, a target human face model, and a source virtual character face model as well as feature curves marked on the source human face model and the source virtual character face model. The computing device deforms the source virtual character face model based on the source human face model and the target human face model to generate a target virtual character face model. Deforming the source virtual character face model includes minimizing a loss function that includes terms defined based on the feature curves to preserve features of the source virtual character face model on the target virtual character face model. The computing device further renders the target virtual character face model.

Abstract: An example method for AI-assisted notifications of relevant content during a virtual conference includes joining, by a client device, a virtual conference attended by one or more participants using a client application. For example, the client device may receive, a transcript of the virtual conference from a server during the virtual conference and determine if the transcript includes a phrase associated with the participant. In response to determining that the transcript includes the phrase associated with the participant, outputting a notification to the participant on a graphical user interface (GUI) provided by the client application.

Abstract: Systems and methods for generating virtual characters for video conferencing are provided. In an example, a computing device joins a video conference and determines an expression parameter vector from a video of a participant during the video conference. The device further generates a virtual character customized for the participant from a virtual character face model. The virtual character is generated by at least applying the expression parameter vector to a set of virtual character expressions customized for the participant and by incorporating a virtual character neutral face model customized for the participant. Each of the virtual character expressions describes a facial expression of the virtual character customized for the participant and the virtual character neutral face model describes a neutral face of the virtual character customized for the participant. The computing device renders the virtual character in a video stream of the participant.

Abstract: Systems and methods for generating virtual characters for video conferencing are provided. In an example, a computing device accesses a source human face model, a target human face model, and a source virtual character model. The computing device deforms the source virtual character model based on the source human face model and the target human face model to generate a target virtual character model. The source virtual character model includes a face region and a non-face region. Deforming the source virtual character model includes generating, for the source virtual character model, virtual triangles connecting the face region and the non-face region of the source virtual character model, deforming the source virtual character model with minimized deformation to the virtual triangles to generate the target virtual character model, and removing the virtual triangles from the target virtual character model. The computing device renders the target virtual character model.

Abstract: One example method includes receiving, by a display management device, one or more display configuration selections for one or more corresponding video conference displays for a hybrid conference location, the hybrid conference location providing a real-world space associated with a corresponding virtual conference hosted by a virtual conference provider; accessing, by the display management device, the corresponding virtual conference via the virtual conference provider; requesting, by the display management device, a plurality of video streams of the virtual conference from the virtual conference provider, each video stream corresponding to a virtual participant, the display management device not corresponding to any virtual participant; generating, for each video conference display of the one or more video conference displays, a real-time video rendering of a respective subset of the plurality of video streams according to the one or more display configurations; and providing, to the one or more video conf

Abstract: Systems and methods for providing multi-meeting modes for virtual meetings are provided. In aspects, a system including a non-transitory computer-readable medium, a communications interface, and a processor is provided. The processor may be configured to execute instructions to establish a first virtual meeting and establish a second virtual meeting. The second virtual meeting may run concurrent with the first virtual meeting. The instructions may further cause the processor to receive, from a first client device, a first request to join the first virtual meeting and a second request to join the second virtual meeting, and transmit to the first client device: a first set of multimedia streams and a second set of multimedia streams. The instructions may further cause the processor to determine a primary virtual meeting and modify one of the first set of multimedia streams or the second set of multimedia streams based on the primary virtual meeting.

Abstract: One example method includes transmitting a message to a first client device indicating a transition to a first sub-meeting of a webinar, the first client device connected to a main meeting of the webinar and associated with a first participant, receiving, from the first client device, a request for access information to join the first sub-meeting; transmitting the access information for the first sub-meeting to the first client device, receiving, from the first client device, a request to join the first sub-meeting, the request based on the access information for the first sub-meeting, and joining the first client device to the first sub-meeting.

Abstract: In various embodiments, a group photograph system coordinates and creates a group photograph of participants of a video conferencing session. Using inputs from the participants, the group photograph system captures images of individual participants and selectively assembles a group photograph based on the rating of each individual participant. In one embodiment, the group photograph system sends a countdown signal to a first participant and a second participant wherein the first participant and the second participant are part of a group photograph within a video conferencing session wherein the countdown signal represents an amount of time before a first participant image is captured of the first participant. In another embodiment, the group photography system captures the first participant image and a second participant image of the first participant and the second participant, respectively and creates a first group photograph which includes the first participant image and the second participant image.

Abstract: One example method for controlling online meeting attendance includes obtaining meeting information associated with a meeting, the meeting information comprising a meeting identifier; receiving, by a video conferencing system from a client device, a request to join the meeting, the request comprising the meeting identifier; receiving a user identifier corresponding to a user; accessing a set of guest identifiers corresponding to a plurality of meeting guests invited to the meeting; determining that the user is a meeting guest of the plurality of meeting guests based on the user identifier and a correspondence to a guest identifier of the set of guest identifier, wherein the user identifier is not in the set of guest identifiers; and responsive to determining that the user is a meeting guest of the plurality of meeting guests, connecting the client device to the meeting.

Abstract: Example methods and systems for providing notifications of unread messages is provided. A client device detects an input action proximate to a displayed grouping of one or more chat sessions associated with a recipient user account. At least one chat session of the one or more chat sessions comprises at least one unread message. The client device provides a notification associated with the at least one unread message. The notification includes at least one chat identity corresponding to the at least one chat session of the one or more chat sessions. The client device displays the at least one unread message in the at least one chat session based on a triggering action associated with the notification.

Abstract: Systems and methods for enhancing group sound during a networked conference are provided. A computer device accesses audio data, detects a first group sound in the audio data, and generates a first group sound identifier that identifies the first group sound. The computer device is one of a plurality of computer devices connected to the networked conference. The computer device transmits the first group sound identifier to a network server and receives a control signal from the network server. The network server receives multiple group sound identifiers from the plurality of computer devices and generates the control signal based on the multiple group sound identifiers. The multiple group sound identifiers include the first group sound identifier and a second group identifier. The control signal includes the second group sound identifier. The computer device reproduces a second group sound based on the second group sound identifier.

Abstract: One example method includes receiving, during a virtual conference from a client device, a request to generate a real-time summary of the virtual conference, a plurality of client devices participating in the virtual conference and exchanging audio and video streams; receiving, during the virtual conference, a plurality of utterances generated by automatic speech recognition (“ASR”) of the audio streams; generating a group of consecutive utterances from the plurality of utterances; determining a segment based on the group of consecutive utterances; generating, using a large language model (“LLM”), a segment summary based on the segment; and providing the segment summary to the client device.

Abstract: Example methods and systems provide a workplace assistant application that can detect electronic content associated with a remote user and access multiple communication channels connected to a workplace assistant client application. The system can submit the electronic content to one or more predictive models to provide a context for the electronic content. The context is based at least in part on information from multiple channels. The system can generate, using the predictive model(s), an action item based at least in part on the context of the electronic content as well as display or store the action item using the workplace assistant client application. An action item, as examples, can be a “to do” item, a meeting agenda, a reminder, a meeting, a task, or some combination of one or more of these.

Abstract: One example method includes joining, by a client application executed by a client device, a virtual conference hosted by a virtual conference provider, a plurality of participants attending the virtual conference; receiving, by the client application, a question associated with the virtual conference; generating a query context based on a real-time transcript of the virtual conference; providing the query context and the question to a trained large language model (“LLM”); and receiving a response from the LLM based on the question and the query context.

Abstract: Some examples relate to locally storing a chat conversation history at an on-premises data center. As one example, a system can receive a chat message from a first client device of a first participant in a chat conversation. In response to receiving the chat message, the system can determine a data center associated with the first participant. The system can then transmit the text chat message to a server node in the data center. The server node can be configured to transmit a command to a database system of the data center. The command can be configured to cause the database system to store a copy of the text chat message in a chat log associated with the chat conversation. The system can also transmit the text chat message to a second client device of a second participant in the chat conversation.

Abstract: One example method includes transmitting, by a client device, a request for a reduced large language model (“LLM”) to a remote server; receiving, by the client device from the remote server, and storing the reduced LLM, the reduced LLM based on a trained general LLM; receiving, by the client device, a request to generate content using the reduced LLM; providing the request to the reduced LLM; and receiving generated content from the reduced LLM based on the request.

Abstract: Systems and methods for providing instant processing of virtual meeting recordings are provided.