Method for recognizing actions, device and storage medium

A device, comprising:

• one or more processors;
• a memory configured to store one or more programs;
• wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform a method for recognizing actions comprising:
• determining, based on key points of skeleton of at least one video frame in a video to be recognized, shallow features of the at least one video frame;
• acquiring image features of the at least one video frame;
• acquiring action features of the at least one video frame based on the shallow features and the image features;
• acquiring an action recognition result of the at least one video frame by inputting the action features of the at least one video frame into an action recognition model, wherein the action recognition result comprises states and state probabilities of actions in the at least one video frame;
• and
• determining an execution state of a target action in the at least one video frame based on the action recognition result of the at least one video frame.

A non-volatile computer-readable storage medium storing at least one computer program, wherein the at least one computer program, when run by a processor, causes the processor to perform a method for recognizing actions comprising:

• determining, based on key points of skeleton of at least one video frame in a video to be recognized, shallow features of the at least one video frame;
• acquiring image features of the at least one video frame;
• acquiring action features of the at least one video frame based on the shallow features and the image features;
• acquiring an action recognition result of the at least one video frame by inputting the action features of the at least one video frame into an action recognition model, wherein the action recognition result comprises states and state probabilities of actions in the at least one video frame;
• and
• determining an execution state of a target action in the at least one video frame based on the action recognition result of the at least one video frame.