Systems and methods for adaptive input thresholding

1. A computer-implemented method comprising:

detecting, by a computing system, a gesture that appears to be intended to trigger a response by the computing system;

identifying, by the computing system for performing on the computing system, an action that is based on the detected gesture;

determining, by the computing system, an estimate of a temporal cost of performing the action and an estimate of a temporal cost of not performing the action;

identifying, by the computing system, a context in which the gesture was performed; and

adjusting a threshold for determining whether to trigger the response to the gesture in a manner that causes the computing system to perform the action, the adjusting based on at least one of the context in which the gesture was performed, the estimate of the temporal cost of performing the action, and the estimate of the temporal cost of not performing the action.

2. The computer-implemented method of claim 1 , wherein:

the estimate of the temporal cost of performing the action comprises an estimated time involved in undoing the action; and

adjusting the threshold for determining whether to trigger the response to the gesture is based on the estimated time involved in undoing the action if the gesture was not intended to trigger the response and the action was performed.

3. The computer-implemented method of claim 1 , wherein:

the estimate of the temporal cost of not performing the action comprises an estimated time involved in recovering from not performing the action; and

adjusting a threshold for determining whether to trigger the response to the gesture is based on an estimated time involved in recovering from not performing the action if the gesture was intended to trigger the response and the action was not performed.

4. The computer-implemented method of claim 1 , further comprising calculating a recognizer score that indicates a clarity of the gesture via a probability that the computing system has accurately interpreted the gesture, wherein:

the context in which the gesture was performed comprises the clarity of the gesture; and

adjusting the threshold for determining whether to trigger the response to the gesture is based on the probability that the gesture is intended to trigger the response.

5. The computer-implemented method of claim 1 , further comprising determining whether a user who performed the gesture is involved in multitasking on the computing system, wherein:

the context in which the gesture was performed comprises a degree of the multitasking occurring when the gesture is detected; and

adjusting the threshold for determining whether to trigger the response to the gesture is based on the degree of the multitasking occurring when the gesture is detected by the computing system.

6. The computer-implemented method of claim 5 , wherein the degree of multitasking is based on at least one of a number of applications running on the computing system or a number of activities being performed by a user of the computing system.

7. The computer-implemented method of claim 1 , wherein:

the context in which the gesture was performed comprises an amount of time involved in detecting the gesture; and

adjusting the threshold for determining whether to trigger the response to the gesture is based on the amount of time involved in detecting the gesture.

8. The computer-implemented method of claim 7 , wherein the amount of time involved in detecting the gesture is based on at least one of an application running on the computing system, an activity being performed by a user of the computing system, or a speed of a behavior of a user of the computing system.

9. The computer-implemented method of claim 1 , wherein:

detecting the gesture comprises detecting one of a sequence of gestures intended to trigger the response by the computing system; and

performing the action based on the detected gesture comprises performing the action based on the sequence of gestures.

10. The computer-implemented method of claim 1 , wherein the context in which the gesture was performed comprises one or more of:

a time-of-day;

a level of ambient lighting;

a state of the computing system; or

a location where the gesture was performed.

11. A system comprising:

at least one physical processor; and

physical memory comprising computer-executable instructions that, when executed by the physical processor, cause the physical processor to:

detect, by a computing device, a gesture that appears to be intended to trigger a response by the system;

identify, by the computing device for performing on the computing device, an action that is based on the detected gesture;

determine, by the computing device, an estimate of a temporal cost of performing the action and an estimate of a temporal cost of not performing the action;

identify, by the computing device, a context in which the gesture was performed; and

adjust a threshold for determining whether to trigger the response to the gesture in a manner that causes the system to perform the action, the adjusting based on at least one of the context in which the gesture was performed, the estimate of the temporal cost of performing the action, and the estimate of the temporal cost of not performing the action.

12. The system of claim 11 , wherein:

the estimate of the temporal cost of performing the action comprises an estimated time involved in recovering from performing the action; and

adjusting the threshold for determining whether to trigger the response to the gesture is based on the estimated time involved in recovering from performing the action if the gesture was not intended to trigger the response and the action was performed.

13. The system of claim 11 , wherein:

the estimate of the temporal cost of not performing the action comprises an estimated time involved in recovering from not performing the action; and

adjusting a threshold for determining whether to trigger the response to the gesture is based on an estimated time involved in recovering from not performing the action if the gesture was intended to trigger the response and the action was not performed.

14. The system of claim 11 , further comprising computer-executable instructions that, when executed by the physical processor, cause the physical processor to calculate a recognizer score that indicates a clarity of the gesture via a probability that the system has accurately interpreted the gesture, wherein:

the context in which the gesture was performed comprises the clarity of the gesture; and

adjusting the threshold for determining whether to trigger the response to the gesture is based on the probability that the gesture is intended to trigger the response.

15. The system of claim 11 , further comprising computer-executable instructions that, when executed by the physical processor, cause the physical processor to determine whether a user who performed the gesture is involved in multitasking on the system, wherein:

the context in which the gesture was performed comprises a degree of the multitasking occurring when the gesture is detected; and

adjusting the threshold for determining whether to trigger the response to the gesture is based on the degree of the multitasking occurring when the gesture is detected by the system.

16. The system of claim 15 , wherein the degree of multitasking is based on at least one of a number of applications running on the system or a number of activities being performed by a user of the system.

17. The system of claim 11 , wherein:

the context in which the gesture was performed comprises an amount of time involved in detecting the gesture; and

adjusting the threshold for determining whether to trigger the response to the gesture is based on the amount of time involved in detecting the gesture.

18. The system of claim 17 , wherein the amount of time involved in detecting the gesture is based on at least one of an application running on the system, an activity being performed by a user of the system, or a speed of a behavior of a user of the system.

19. The system of claim 11 , wherein:

detecting the gesture comprises detecting one of a sequence of gestures intended to trigger the response by the system; and

performing the action based on the detected gesture comprises performing the action based on the sequence of gestures.

20. A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device of a computing system, cause the computing device to:

identify, for performing on the computing device, an action that is based on a detected gesture;

determine an estimate of a temporal cost of performing the action and an estimate of a temporal cost of not performing the action;

detect a gesture that appears to be intended to trigger a response by the computing system;

identify, by the computing device, a context in which the gesture was performed; and

adjust a threshold for determining whether to trigger the response to the gesture in a manner that causes the computing system to perform the action, the adjusting based on at least one of the context in which the gesture was performed, the estimate of the temporal cost of performing the action, and the estimate of the temporal cost of not performing the action.