Video calling method and apparatus

1. A video calling method, comprising:

obtaining a first video image acquired by a first terminal;

performing action recognition on the first video image; and

sending, in response to determining that an action recognition result matches a first preset action, a first preset animation corresponding to the first preset action and the first video image to a second terminal performing video calling with the first terminal for displaying by the second terminal,

wherein the method further comprises:

displaying an animation selection window in a video window of the first terminal;

determining, when receiving a first preset animation selection instruction that is input based on the animation selection window, a first preset action prompt template corresponding to the first preset animation selection instruction; and

displaying the first preset action prompt template in the video window of the first terminal, wherein

the first preset animation selection instruction corresponds to the first preset action and the first preset animation.

2. The video calling method according to claim 1 , wherein the sending a first preset animation corresponding to the first preset action and the first video image to a second terminal performing video calling with the first terminal for displaying by the second terminal comprises:

determining the first preset animation corresponding to the first preset action and a loading location of the first preset animation;

performing composition processing on the first preset animation and the first video image according to the loading location, to generate a composite video image; and

sending the composite video image to the second terminal performing video calling with the first terminal for displaying by the second terminal.

3. The video calling method according to claim 1 , wherein the sending a first preset animation corresponding to the first preset action and the first video image to a second terminal performing video calling with the first terminal for displaying by the second terminal comprises:

determining the first preset animation corresponding to the first preset action and a loading location of the first preset animation; and

sending the first preset animation, the loading location, and the first video image to the second terminal performing video calling with the first terminal for displaying by the second terminal, wherein

the second terminal loads the first preset animation according to the loading location, and displays the first video image that is obtained after the first preset animation is loaded.

4. The video calling method according to claim 1 , wherein the method further comprises:

continuing performing action recognition on the first video image;

obtaining a second video image acquired by the second terminal, and performing action recognition on the second video image; and

sending, when an action recognition result based on the first video image or an action recognition result based on the second video image matches a second preset action, a second preset animation associated with the first preset animation and the first video image to the second terminal for displaying by the second terminal.

5. The video calling method according to claim 4 , wherein the method further comprises:

determining a second preset action prompt template associated with the first preset animation; and

displaying the second preset action prompt template on the first terminal and/or the second terminal.

6. A video calling apparatus, the video calling apparatus comprising:

at least one memory configured to store computer program code; and

at least one processor configured to access the at least one memory and operate according to the computer program code, the computer program code including:

obtaining code configured to cause at least one of the at least one processor to obtain a first video image acquired by a first terminal;

action recognition code configured to cause at least one of the at least one processor to perform action recognition on the first video image; and

sending code configured to cause at least one of the at least one processor to send, in response to determining an action recognition result matches a first preset action, a first preset animation corresponding to the first preset action and the first video image to a second terminal performing video calling with the first terminal for displaying by the second terminal,

wherein the apparatus further comprises:

first display code configured to cause at least one of the at least one processor to: display an animation selection window in a video window of the first terminal, and display a first preset action prompt template in the video window of the first terminal; and

first determining code configured to cause at least one of the at least one processor to determine, in response to receiving a first preset animation selection instruction that is input based on the animation selection window, the first preset action prompt template corresponding to the first preset animation selection instruction, wherein

the first preset animation selection instruction corresponds to the first preset action and the first preset animation.

7. The video calling apparatus according to claim 6 , wherein the sending code comprises:

determining code configured to cause at least one of the at least one processor to determine the first preset animation corresponding to the first preset action and a loading location of the first preset animation;

composition code configured to cause at least one of the at least one processor to perform composition processing on the first preset animation and the first video image according to the loading location, to generate a composite video image; and

first sending code configured to cause at least one of the at least one processor to send the composite video image to the second terminal performing video calling with the first terminal for displaying by the second terminal.

8. The video calling apparatus according to claim 6 , wherein the sending code comprises:

determining code configured to cause at least one of the at least one processor to determine the first preset animation corresponding to the first preset action and a loading location of the first preset animation; and

second sending code configured to cause at least one of the at least one processor to send the first preset animation, the loading location, and the first video image to the second terminal performing video calling with the first terminal for displaying by the second terminal,

wherein the second terminal loads the first preset animation according to the loading location, and displays the first video image that is obtained after the first preset animation is loaded.

9. The video calling apparatus according to claim 6 , wherein

the action recognition code is further configured to cause the at least one of the at least one processor to continue performing action recognition on the first video image;

the action recognition code is further configured to cause the at least one of the at least one processor to obtain a second video image acquired by the second terminal, and perform action recognition on the second video image; and

the sending code is further configured to cause the at least one of the at least one processor to send, in response to determining an action recognition result based on the first video image or an action recognition result based on the second video image matches a second preset action, a second preset animation associated with the first preset animation and the first video image to the second terminal for displaying by the second terminal.

10. The video calling apparatus according to claim 9 , wherein the apparatus further comprises:

second determining code configured to cause at least one of the at least one processor to determine a second preset action prompt template associated with the first preset animation; and

second display module code configured to cause at least one of the at least one processor to display the second preset action prompt template on the first terminal and/or the second terminal.

11. A non-transitory computer readable medium configured to store computer program code which, when executed by at least one processor, cause the at least one processor to:

obtain a first video image acquired by a first terminal;

perform action recognition on the first video image; and

send, in response to determining that an action recognition result matches a first preset action, a first preset animation corresponding to the first preset action and the first video image to a second terminal performing video calling with the first terminal for displaying by the second terminal,

wherein the instructions further cause the computer to:

display an animation selection window in a video window of the first terminal;

determine, in response to receiving a first preset animation selection instruction that is input based on the animation selection window, a first preset action prompt template corresponding to the first preset animation selection instruction; and

display the first preset action prompt template in the video window of the first terminal, wherein

the first preset animation selection instruction corresponds to the first preset action and the first preset animation.

12. The non-transitory computer readable medium of claim 11 , wherein the computer program code further causes the at least one processor to:

determine the first preset animation corresponding to the first preset action and a loading location of the first preset animation;

perform composition processing on the first preset animation and the first video image according to the loading location to generate a composite video image; and

send the composite video image to the second terminal performing video calling with the first terminal for displaying by the second terminal.

13. The non-transitory computer readable medium of claim 11 , wherein the computer program code further causes the at least one processor to:

determine the first preset animation corresponding to the first preset action and a loading location of the first preset animation; and

send the first preset animation, the loading location, and the first video image to the second terminal performing video calling with the first terminal for displaying by the second terminal, wherein

the second terminal loads the first preset animation according to the loading location, and displays the first video image that is obtained after the first preset animation is loaded.

14. The non-transitory computer readable medium of claim 11 , wherein the computer program code further causes the at least one processor to:

continue performing action recognition on the first video image;

obtain a second video image acquired by the second terminal and perform action recognition on the second video image; and

send, in response to determining that an action recognition result based on the first video image or an action recognition result based on the second video image matches a second preset action, a second preset animation associated with the first preset animation and the first video image to the second terminal for displaying by the second terminal.

15. The non-transitory computer readable medium of claim 14 , wherein the computer program code further causes the at least one processor to:

determine a second preset action prompt template associated with the first preset animation; and

display the second preset action prompt template on the first terminal and/or the second terminal.