Abstract: A game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback.

Abstract: Apparatuses, systems, and techniques for test an application in a cloud environment. A method can include selecting an application hosted at a virtualized computing environment of an application hosting platform for a test session. Method further includes selecting a set of users associated with the application hosting platform to execute the application during the test session, select a set of observers associated with the application hosting platform to monitor the set of users. The method further includes initiating the test session, authenticating the set of users, causing content data corresponding to the application to be streamed to a user device of each user. The method further includes causing a video stream of the test session to be transmitted to a user device of a corresponding observer for presentation in a observer graphical user interface (GUI), the video stream reflecting interactions of the user with the content of the application.

Abstract: Apparatuses, systems, and techniques to determine position information for a gameplay session. In at least one embodiment, the position information is determined by at least matching features extracted from a mini-map to feature extracted from a map and determining a transformation matrix to be applied to a position within the mini-map.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Event data for detected events can be written to an event log in a form that is both human- and process-readable. Descriptive text for the event data can come from a common event dictionary that is hierarchical in nature, such that events of the same type can be correlated across different games even though the precise nature or appearance of those events may be different. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback. The event data may be determined based upon output from detectors such as optical character recognition (OCR) engines, and the regions may be upscaled and binarized before OCR processing.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback. The event data may be determined based upon output from detectors such as optical character recognition (OCR) engines, and the regions may be upscaled and binarized before OCR processing.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Event data for detected events can be written to an event log in a form that is both human- and process-readable. Descriptive text for the event data can come from a common event dictionary that is hierarchical in nature, such that events of the same type can be correlated across different games even though the precise nature or appearance of those events may be different. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback. The event data may be determined based upon output from detectors such as optical character recognition (OCR) engines, and the regions may be upscaled and binarized before OCR processing.

Abstract: A game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback.

Abstract: A method for displaying a live preview image on a mobile device is disclosed. The method includes computing a history color value and confidence value for each pixel of a sensor of a camera. Further, it includes obtaining a new frame of pixels from the camera. Subsequently, for each pixel in the new frame, the method includes: (a) determining if a pixel color is similar to a corresponding history color value and if a confidence corresponding to a pixel is above a predetermined threshold; (b) if the pixel color is not similar to the history color value and the confidence is above the predetermined threshold, displaying the history color value on the preview when displaying the new frame; and (c) if the pixel color is similar to the history color value or the confidence is below the threshold, displaying the pixel color on the preview instead.

Abstract: A method for tracking device orientation on a portable device is disclosed. The method comprises initializing a device orientation to a sensor orientation, wherein the sensor orientation is based on information from an inertial measurement unit (IMU) sensor. It also comprises initiating visual tracking using a camera on the portable device and capturing a frame. Next, it comprises determining a plurality of visual features in the frame and matching the frame to a keyframe, wherein capture of the keyframe precedes capture of the frame. Subsequently, it comprises computing a rotation amount between the frame and the keyframe. Responsive to a determination that a rotational distance between the frame and the keyframe exceeds a predetermined threshold, promoting the frame to a keyframe status and adding it to a first orientation map and adjusting the frame with all prior captured keyframes.

Abstract: A method for displaying a live preview image on a mobile device is disclosed. The method comprises computing a history color value and confidence value for each pixel of a sensor of a camera on the device. Further, it comprises obtaining a new frame of pixels from the camera. Subsequently, for each pixel in the new frame, the method comprises: (a) determining if a pixel color is similar to a corresponding history color value and if a confidence corresponding to a pixel is above a predetermined threshold; (b) if the pixel color is not similar to the history color value and the confidence is above the predetermined threshold, displaying the history color value on the preview when displaying the new frame; and (c) if the pixel color is similar to the history color value or the confidence is below the threshold, displaying the pixel color on the preview instead.

Abstract: Decoding a content of interest with optimal power usage. In an embodiment, a central processing unit (CPU) retrieves the frames of a data stream of interest from a secondary storage and stores them in a random access memory (RAM). The CPU forms an index table indicating the locations at which each of the frames is stored. The index table is provided to a decoder, which processes the frames in sequence to recover the original data from the encoded data. By using the index information, the power usage is reduced at least in an embodiment when the decoding is performed by an auxiliary processor.

Abstract: Decoding a content of interest with optimal power usage. In an embodiment, a central processing unit (CPU) retrieves the frames of a data stream of interest from a secondary storage and stores them in a random access memory (RAM). The CPU forms an index table indicating the locations at which each of the frames is stored. The index table is provided to a decoder, which processes the frames in sequence to recover the original data from the encoded data. By using the index information, the power usage is reduced at least in an embodiment when the decoding is performed by an auxiliary processor.