Abstract: A classification system classifies different aspects of content of an input image stream, such as faces, landmarks, events, and so forth. The classification system includes a general classifier and at least one specialized classifier template. The general classifier is trained to classify a large number of different aspects of content, and a specialized classifier can be trained based on a specialized classifier template during operation of the classification system to classify a particular subset of the multiple different aspects of content. The classification system determines when to use the general classifier and when to use a specialized classifier based on class skew, which refers to the temporal locality of a subset of aspects of content in the image stream.

Abstract: Wearable audio accessories for computing devices are described. In one embodiment the wearable audio accessory provides a speech based interface between the user and a nearby computing device for the performance of user-initiated or computing device initiated microtasks. Information is provided to the user via a loudspeaker and the user can provide input via a microphone. An audio sensing channel within the accessory continuously monitors the audio signal as detected by the microphone and in various embodiments will trigger more complex audio processing based on this monitoring. A wireless communication link is provided between the accessory and the nearby computing device. To mitigate any delay caused by the switching between audio processing techniques, the audio accessory may include a rolling buffer which continuously stores the audio signal and outputs a delayed audio signal to the audio processing engines.

Abstract: A digest generation system obtains video streams and includes an admission control module that selects, for each video stream, a subset of the frames of the video stream to analyze. A frame-to-text classifier generates a digest for each selected frame and the generated digests are stored in a digest store in a manner so that each digest is associated with the video stream from which the digest was generated. The digest for a frame is text that describes the frame, such as objects identified in the frame. A viewer desiring to view a video stream having particular characteristics inputs a text search query to a search system. The search system, based on the digests, generates search results that are an indication of video streams that satisfy the search criteria. The search results are presented to the user, allowing the user to select and view one of the video streams.

Abstract: Multiple machine learning models can be jointly trained in parallel. An example process for jointly training multiple machine learning models includes providing a set of machine learning models that are to learn a respective task, the set of machine learning models including a first machine learning model and a second machine learning model. The process can initiate training of the first machine learning model to learn a task using training data. During the training of the first machine learning model, information can be passed between the first machine learning model and the second machine learning model. Such passing of information (or “transfer of knowledge”) between the machine learning models can be accomplished via the formulation, and optimization, of an objective function that comprises model parameters that are based on the multiple machine learning models in the set.

Abstract: Aspects extend to methods, systems, and computer program products for sensing object depth within an image. In general, aspects of the invention implement object depth detection techniques having reduced power consumption. The reduced power consumption permits mobile and wearable devices, as well as other devices with reduced power resources, to detect and record objects (e.g., human features). For example, a camera can efficiently detect a conversational partner or attendees at a meeting (possibly providing related real-time cues about people in front of a user). As another example, a human hand detection solution can determine the objects a user is pointing at (by following the direction of the arm) and provide other interaction modalities. Aspects of the invention can use a lower power depth sensor to identify and capture pixels corresponding to objects of interest.

Abstract: The personal translator implementations described herein provide a speech translation device that pairs with a computing device to translate in-person conversations. The speech translation device can be wearable. In one implementation the personal translator comprises a speech translation device with at least one microphone that captures input signals representing nearby speech of a first user/wearer of the device and at least one other nearby person in a conversation in two languages; a wireless communication unit that sends the captured input signals representing speech to a nearby computing device, and receives for each language in the conversation, language translations from the computing device; and at least one loudspeaker that outputs the language translations to the first user/wearer and at least one other nearby person. The language translations in text form can be displayed on a display at the same time the language translations are output to the loudspeaker(s).

Abstract: The subject disclosure is directed towards energy saving mechanisms of image sensor circuitry (e.g., in a camera). Image quality data, such as provided by an application, is processed to make energy consumption of image sensor circuitry more proportional to output image quality by controlling the operation of one or more controllable power saving mechanisms of the image sensor circuitry. Power saving mechanisms may include a frequency controlled clock, the ability to turn off unneeded components, an inter-frame standby mode that puts the image sensor circuitry into a standby mode between capturing sequential frames, selectable parallel analog chains having different energy usage properties and column circuitry that allows turning off circuitry corresponding to unneeded columns of the sensor array.

Abstract: A development system is described for facilitating the development of a spoken natural language (SNL) interface. The development system receives seed templates from a developer, each of which provides a command phrasing that can be used to invoke a function, when spoken by an end user. The development system then uses one or more development resources, such as a crowdsourcing system and a paraphrasing system, to provide additional templates. This yields an extended set of templates. A generation system then generates one or more models based on the extended set of templates. A user device may install the model(s) for use in interpreting commands spoken by an end user. When the user device recognizes a command, it may automatically invoke a function associated with that command. Overall, the development system provides an easy-to-use tool for producing an SNL interface.

Abstract: A method to record video with a video camera while respecting bystander privacy includes acquiring sensory data separate from the video, parsing the sensory data for evidence of a human being in a field of view of the video camera, and recording video with the video camera if no human being is detected in the field of view, based upon the sensory data.

Abstract: Aspects of the subject disclosure are directed towards saving resources such as energy, computing, and communication by capturing evaluation (e.g., low-resolution) images periodically or otherwise, such as in a continuous mobile vision system, and processing each evaluation to determine whether a likely event is present that warrants capturing another (e.g., higher-resolution) image for further image processing. In one aspect, only the region or regions of interest of the high-resolution image is provided to an image processing algorithm for further image processing. Also described is the use of infrared sensing, such as to determine whether an image/event location/region of interest includes thermal data indicative of human features.

Abstract: Wearable audio accessories for computing devices are described. In one embodiment the wearable audio accessory provides a speech based interface between the user and a nearby computing device for the performance of user-initiated or computing device initiated microtasks. Information is provided to the user via a loudspeaker and the user can provide input via a microphone. An audio sensing channel within the accessory continuously monitors the audio signal as detected by the microphone and in various embodiments will trigger more complex audio processing based on this monitoring. A wireless communication link is provided between the accessory and the nearby computing device. To mitigate any delay caused by the switching between audio processing techniques, the audio accessory may include a rolling buffer which continuously stores the audio signal and outputs a delayed audio signal to the audio processing engines.

Abstract: A development system is described for facilitating the development of a spoken natural language (SNL) interface. The development system receives seed templates from a developer, each of which provides a command phrasing that can be used to invoke a function, when spoken by an end user. The development system then uses one or more development resources, such as a crowdsourcing system and a paraphrasing system, to provide additional templates. This yields an extended set of templates. A generation system then generates one or more models based on the extended set of templates. A user device may install the model(s) for use in interpreting commands spoken by an end user. When the user device recognizes a command, it may automatically invoke a function associated with that command. Overall, the development system provides an easy-to-use tool for producing an SNL interface.

Abstract: The subject disclosure is directed towards energy saving mechanisms of image sensor circuitry (e.g., in a camera). Image quality data, such as provided by an application, is processed to make energy consumption of image sensor circuitry more proportional to output image quality by controlling the operation of one or more controllable power saving mechanisms of the image sensor circuitry. Power saving mechanisms may include a frequency controlled clock, the ability to turn off unneeded components, an inter-frame standby mode that puts the image sensor circuitry into a standby mode between capturing sequential frames, selectable parallel analog chains having different energy usage properties and column circuitry that allows turning off circuitry corresponding to unneeded columns of the sensor array.

Abstract: Low frequency harmonics detected by an accelerometer in a wrist-mounted device are used to infer ambulation. The fundamental rhythm or pitch is extracted from gathered accelerometer data and the determined pitch and associated properties are used to infer whether a subject is walking or not walking.

Abstract: An electronic system for health based behavior modification may receive real time data to assess behavioral state changes. The real time data may be used as an input to a database that matches states and trait-based typologies to determine motivational profiles. A rules database may be used to develop recommended motivational coaching changes based on the real time inputs.

Abstract: User self-installation of a sensor network for activity monitoring may be facilitated by providing a computer system that prompts the user through the installation process. Particularly, the computer system may prompt the user to identify an object to which a sensor has been attached and the activities with which identified objects are associated. The computer may prompt with potential activities based on the object identified by the user. The elicited information may be used to automatically generate a model, which may be automatically improved over time by examining the history of sensor readings. Thereafter, based on the data produced by the sensors, the system identifies what activities are actually being completed.

Abstract: Embodiments of methods and apparatus for operating an ensemble of wireless electronic devices based on user activity are generally described herein. Other embodiments may be described and claimed.

Abstract: Low frequency harmonics detected by an accelerometer in a wrist-mounted device are used to infer ambulation. The fundamental rhythm or pitch is extracted from gathered accelerometer data and the determined pitch and associated properties are used to infer whether a subject is walking or not walking.

Abstract: One or more switches may be coupled to a radio frequency identification (RFID) tag, so that the response of the RFID tag indicates the state of the switch(es). The RFID tag and the switch(es) may be coupled together in various ways so that the state of the switches affects the response of the RFID tag to an RFID reader.

Abstract: One or more inertially controlled switches may be coupled to a radio frequency identification (RFID) tag, so that the response of the RFID tag indicates the state of the switch(es). The RFID tag and the switch(es) may be coupled together in various ways so that the state of the switches affects the response of the RFID tag to an RFID reader.