Abstract: A gesture recognition system comprises: a signal collection terminal, configured to collect and preprocess gesture data of a gesture object; a local recognition device, configured to extract features from the gesture data received from the signal collection terminal, form a multi-dimensional feature vector based on extracted features, establish local gesture models based on the multi-dimensional feature vector and perform local gesture recognition according to the local gesture models; and a cloud server, configured to receive the multi-dimensional feature vector from the local recognition device when there is a network connection between the local recognition device and the cloud server, establish cloud gesture models based on the received multi-dimensional feature vector and perform cloud gesture recognition according to the cloud gesture models. A gesture recognition method is also disclosed.

Abstract: A virtual inputting device comprises: a signal collection unit including a bioelectrical sensor for collecting bioelectrical signals and an acceleration sensor for collecting acceleration signals; a signal preprocessing unit for performing preprocessing for the bioelectrical signals and the acceleration signals collected by the signal collection unit; a signal segmentation unit for performing segmentation processing for the preprocessed bioelectrical signals and acceleration signals so as to obtain a plurality of gesture segments; a feature extracting unit for extracting feature values from the bioelectrical signals and the acceleration signals for respective gesture segments; a feature combination unit for combining feature values extracted from the feature extracting unit to form a combined feature vector; a gesture recognition unit for performing gesture recognition based on the combined feature vector; and a character mapping unit for obtaining characters corresponding to the recognized gesture according

Abstract: A virtual inputting device comprises: a signal collection unit including a bioelectrical sensor for collecting bioelectrical signals and an acceleration sensor for collecting acceleration signals; a signal preprocessing unit for performing preprocessing for the bioelectrical signals and the acceleration signals collected by the signal collection unit; a signal segmentation unit for performing segmentation processing for the preprocessed bioelectrical signals and acceleration signals so as to obtain a plurality of gesture segments; a feature extracting unit for extracting feature values from the bioelectrical signals and the acceleration signals for respective gesture segments; a feature combination unit for combining feature values extracted from the feature extracting unit to form a combined feature vector; a gesture recognition unit for performing gesture recognition based on the combined feature vector; and a character mapping unit for obtaining characters corresponding to the recognized gesture according

Abstract: A gesture recognition system comprises: a signal collection terminal, configured to collect and preprocess gesture data of a gesture object; a local recognition device, configured to extract features from the gesture data received from the signal collection terminal, form a multi-dimensional feature vector based on extracted features, establish local gesture models based on the multi-dimensional feature vector and perform local gesture recognition according to the local gesture models; and a cloud server, configured to receive the multi-dimensional feature vector from the local recognition device when there is a network connection between the local recognition device and the cloud server, establish cloud gesture models based on the received multi-dimensional feature vector and perform cloud gesture recognition according to the cloud gesture models. A gesture recognition method is also disclosed.

Abstract: A method of compiling code that includes partitioning instructions in the code among a plurality of processors based on memory access latency associated with the instructions is disclosed. According to one aspect of the invention, partitioning instructions includes partitioning memory access dependence chains. Other embodiments are described and claimed.

Abstract: In one embodiment, the present invention includes a method for partitioning a program segment into at least a first stage and a second stage, determining a live set of variables and control flow information alive at a boundary between the first and second stages, and controlling the first stage to transmit a trace-specific portion of the live set for a first trace to the second stage via a communication channel. In such manner, reduced transmission of data between the stages is effected. Other embodiments are described and claimed.

Abstract: A method of compiling code that includes partitioning instructions in the code among a plurality of processors based on memory access latency associated with the instructions is disclosed. According to one aspect of the invention, partitioning instructions includes partitioning memory access dependence chains. Other embodiments are described and claimed.

Abstract: In one embodiment, the present invention includes a method for partitioning a program segment into at least a first stage and a second stage, determining a live set of variables and control flow information alive at a boundary between the first and second stages, and controlling the first stage to transmit a trace-specific portion of the live set for a first trace to the second stage via a communication channel. In such manner, reduced transmission of data between the stages is effected. Other embodiments are described and claimed.