Abstract: A computing system for recognizing salient events depicted in a video utilizes learning algorithms to detect audio and visual features of the video. The computing system identifies one or more salient events depicted in the video based on the audio and visual features.

Abstract: A device, method and system for automatically inferring a mobile user's current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

Abstract: A computer vision service includes technologies to, among other things, analyze computer vision or learning tasks requested by computer applications, select computer vision or learning algorithms to execute the requested tasks based on one or more performance capabilities of the computer vision or learning algorithms, perform the computer vision or learning tasks for the computer applications using the selected algorithms, and expose the results of performing the computer vision or learning tasks for use by the computer applications.

Abstract: A device, method and system for automatically inferring a mobile user's current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

Abstract: A computer vision service includes technologies to, among other things, analyze computer vision or learning tasks requested by computer applications, select computer vision or learning algorithms to execute the requested tasks based on one or more performance capabilities of the computer vision or learning algorithms, perform the computer vision or learning tasks for the computer applications using the selected algorithms, and expose the results of performing the computer vision or learning tasks for use by the computer applications.

Abstract: A computer vision service includes technologies to, among other things, analyze computer vision or learning tasks requested by computer applications, select computer vision or learning algorithms to execute the requested tasks based on one or more performance capabilities of the computer vision or learning algorithms, perform the computer vision or learning tasks for the computer applications using the selected algorithms, and expose the results of performing the computer vision or learning tasks for use by the computer applications.

Abstract: A computing system for recognizing salient events depicted in a video utilizes learning algorithms to detect audio and visual features of the video. The computing system identifies one or more salient events depicted in the video based on the audio and visual features.

Abstract: A computer vision service includes technologies to, among other things, analyze computer vision or learning tasks requested by computer applications, select computer vision or learning algorithms to execute the requested tasks based on one or more performance capabilities of the computer vision or learning algorithms, perform the computer vision or learning tasks for the computer applications using the selected algorithms, and expose the results of performing the computer vision or learning tasks for use by the computer applications.

Abstract: A device, method and system for automatically inferring a mobile user's current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

Abstract: A device, method and system for automatically inferring a mobile user's current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

Abstract: Methods are disclosed to support adaptive interaction with legacy software applications, without a need for rewriting those applications. The methods are for use with an interactive electronic system including a processor, a display, and an input device with user-manipulated controls. When the legacy application is executed, a supplemental software program, such as a plugin, is also executed and is utilized in order to identify currently relevant interactive features of the legacy application during execution. Functionality is dynamically assigned to the various user-manipulated controls based on the identified features. In one embodiment, detection of objects (particularly the user's hands) proximate to the input controls is also employed in determining the assignment of functionality and/or in displaying a visual representation to the user of the available interactive choices.

Abstract: A computing system for identifying, describing, and sharing salient events depicted in images and videos executes feature detection algorithms on multimedia input (e.g., video and/or images). The computing system applies semantic reasoning techniques to the output of the feature detection algorithms. The computing system identifies salient event segments of the multimedia input as a result of the semantic reasoning. The computing system can incorporate the salient event segments into a visual presentation, such as a video clip. Alternatively or in addition, the computing system can generate a natural language description of the content of the multimedia input.

Abstract: A computer vision service includes technologies to, among other things, analyze computer vision or learning tasks requested by computer applications, select computer vision or learning algorithms to execute the requested tasks based on one or more performance capabilities of the computer vision or learning algorithms, perform the computer vision or learning tasks for the computer applications using the selected algorithms, and expose the results of performing the computer vision or learning tasks for use by the computer applications.

Abstract: A device, method and system for automatically inferring a mobile user's current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

Abstract: A device, method and system for automatically inferring a mobile user's current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

Abstract: Methods are disclosed to support adaptive interaction with legacy software applications, without a need for rewriting those applications. The methods are for use with an interactive electronic system including a processor, a display, and an input device with user-manipulated controls. When the legacy application is executed, a supplemental software program, such as a plugin, is also executed and is utilized in order to identify currently relevant interactive features of the legacy application during execution. Functionality is dynamically assigned to the various user-manipulated controls based on the identified features. In one embodiment, detection of objects (particularly the user's hands) proximate to the input controls is also employed in determining the assignment of functionality and/or in displaying a visual representation to the user of the available interactive choices.

Abstract: A hardware input device is disclosed in which at least two modes of manual user input can be provided within the same surface area of the device, including actuating or pressing multiple keys or buttons etc. as well as touch and/or gesturing by the user. A disclosed embodiment has actuated keys/buttons with associated sensors for detecting actuation; a second set of sensors for detecting proximity e.g. of a user's extremities is co-located on the input device. In one embodiment, infrared sensors for proximity detection are integrated with the traditional plastic keys/buttons of a computer keyboard or other personal electronics device. In some embodiments, the elevation of actuated input elements can be controlled by a processor, so that the physical configuration of keys/buttons available to the user can be dynamically reconfigured under program control. Methods are disclosed for using the input device to facilitate a heads-up style of interaction.