Systems for improving pose determination based on video data

A system comprising:

• a first computing device comprising:
• one or more first memories storing first computer-executable instructions;
• and
• one or more first hardware processors to execute the first computer-executable instructions to:
• acquire video data representing a user performing an activity;
• use a first pose extraction algorithm to determine first pose data representing a first pose of the user within a frame of the video data, wherein the first pose data includes a first plurality of points, and each point of the first plurality of points represents a location of a respective body part of the user;
• use a second pose extraction algorithm to determine second pose data representing a second pose of the user within the frame of the video data, wherein the second pose data includes a second plurality of points, and each point of the second plurality of points represents a location of a respective body part of the user;
• determine that a first location of a first point of the first plurality of points differs from a second location of a second point of the second plurality of points by at least a threshold distance;
• in response to the first location differing from the second location by at least the threshold distance, present a first output that indicates the frame of the video data and requests authorization to send the frame to a second computing device;
• receive input data indicating the authorization to provide the frame to the second computing device;
• in response to the input data, send the frame to the second computing device;
• receive, from the second computing device, third pose data representing a third pose of the user within the frame of the video data, wherein the third pose data includes a third plurality of points, and each point of the third plurality of points represents a location of a respective body part of the user;
• and
• present a second output based on the third pose data.