Safe and Privacy Preserving Video Representation

A computing system for videoconferencing, the computing system comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
• obtaining data associated with a video stream associated with a user of a videoconferencing system;
• detecting a semantic status of the user within the video stream, wherein the semantic status describes a meaning of an activity of the user relative to a videoconference;
• generating a generalized video representation of the user based on the semantic status of the user, wherein the generalized video representation depicts a generalized representation of the semantic status of the user, and wherein generating the generalized video representation comprises:
• determining a first subset of a plurality of image elements of the video stream as being indicative of the semantic status of the user;
• determining a second subset of the plurality of image elements as being indicative of content unrelated to the semantic status of the user;
• and
• generating the generalized video representation based on the semantic status of the user, wherein the generalized video representation comprises a generalized representation of each of the first subset of the plurality of image elements, and wherein the generalized video representation excludes a generalized representation of at least some of the second subset of the plurality of image elements;
• and
• transmitting data descriptive of the generalized video representation to one or more additional computing devices for presentation within the videoconference.

A computer-implemented method, comprising:

• obtaining, by a computing system comprising one or more processor devices, data associated with a video stream associated with a user of a videoconferencing system;
• detecting, by the computing system, a semantic status of the user within the video stream, wherein the semantic status describes a meaning of an activity of the user relative to a videoconference;
• generating, by the computing system, a generalized video representation of the user based on the semantic status of the user, wherein the generalized video representation depicts a generalized representation of the semantic status of the user, and wherein generating the generalized video representation comprises:
• determining, by the computing system, a first subset of a plurality of image elements of the video stream as being indicative of the semantic status of the user;
• determining, by the computing system, a second subset of the plurality of image elements as being indicative of content unrelated to the semantic status of the user;
• and
• generating, by the computing system, the generalized video representation based on the semantic status of the user, wherein the generalized video representation comprises a generalized representation of each of the first subset of the plurality of image elements, and wherein the generalized video representation excludes a generalized representation of at least some of the second subset of the plurality of image elements;
• and
• transmitting, by the computing system, data descriptive of the generalized video representation to one or more additional computing devices for presentation within the videoconference.

One or more non-transitory computer readable media that collectively store instructions that, when executed by one or more computing devices, causes the one or more computing devices to perform operations, the operations comprising:

• obtaining data associated with a video stream associated with a user of a videoconferencing system;
• detecting a semantic status of the user within the video stream, wherein the semantic status describes a meaning of an activity of the user relative to a videoconference;
• generating a generalized video representation of the user based on the semantic status of the user, wherein the generalized video representation depicts a generalized representation of the semantic status of the user, and wherein generating the generalized video representation comprises:
• determining a first subset of a plurality of image elements of the video stream as being indicative of the semantic status of the user;
• determining a second subset of the plurality of image elements as being indicative of content unrelated to the semantic status of the user;
• and
• generating the generalized video representation based on the semantic status of the user, wherein the generalized video representation comprises a generalized representation of each of the first subset of the plurality of image elements, and wherein the generalized video representation excludes a generalized representation of at least some of the second subset of the plurality of image elements;
• and
• transmitting data descriptive of the generalized video representation to one or more additional computing devices for presentation within the videoconference.