Abstract: A method for predicting walking behaviors includes: encoding walking behavior information of at least one target object in a target scene within a historical time period M to obtain a first offset matrix for representing the walking behavior information of the at least one target object within the historical time period M; inputting the first offset matrix into a neural network, and outputting by the neural network a second offset matrix for representing walking behavior information of the at least one target object within a future time period M?; and decoding the second offset matrix to obtain the walking behavior prediction information of the at least one target object within the future time period M?.

Abstract: Described are techniques for performing system management. A first policy definition of a first policy is received. The first policy definition includes information identifying a first criterion, a first resource of the system, and a first action to be taken. It is determined whether a condition of the first policy is met. The condition includes the first criterion. Responsive to determining that the condition is met, first processing is performed that includes performing the first action.

Abstract: The application relates to a method and system for tracking a target object in a video. The method includes: extracting, from the video, a 3-dimension (3D) feature block containing the target object; decomposing the extracted 3D feature block into a 2-dimension (2D) spatial feature map containing spatial information of the target object and a 2D spatial-temporal feature map containing spatial-temporal information of the target object; estimating, in the 2D spatial feature map, a location of the target object; determining, in the 2D spatial-temporal feature map, a speed and an acceleration of the target object; calibrating the estimated location of the target object according to the determined speed and acceleration; and tracking the target object in the video according to the calibrated location.

Abstract: The present invention discloses an image correction method for an adjustable virtual reality helmet. The method comprises the steps of: pre-storing in the helmet a corresponding relation table between a configuration parameter and an image correction parameter and an image correction formula of the helmet; acquiring a real-time configuration parameter of the helmet; searching in the corresponding relation table an image correction parameter corresponding to a configuration parameter closest to the real-time configuration parameter; and performing image correction by calling the image correction formula based on a searched image correction parameter. The present invention also provides an image correction system for an adjustable virtual reality helmet. The present invention can provide better image correction effects for an adjustable virtual reality helmet.

Abstract: Disclosed are methods, apparatuses and systems for CNN network adaption and object online tracking. The CNN network adaption method comprises: transforming a first feature map into a plurality of sub-feature maps, wherein the first feature map is generated by the pre-trained CNN according to a frame of the target video; convolving each of the sub-feature maps with one of a plurality of adaptive convolution kernels, respectively, to output a plurality of second feature maps with improved adaptability; training, frame by frame, the adaptive convolution kernels.

Abstract: A body relationship estimation method and apparatus are disclosed. The method includes obtaining a target picture, calculating a first body relationship feature of two persons according to at least one of first location information of a body part of each person of the two persons in the target picture or second location information of body parts of the two persons, where the first location information is obtained by performing single-person gesture estimation on each person, and the second location information is obtained by performing two-person joint gesture estimation on the two persons when the first location information indicates that the body parts of the two persons overlap, and determining a body relationship between the two persons according to the first body relationship feature.

Abstract: An image characteristic estimation method and device is presented, where content of the method includes extracting at least two eigenvalues of input image data, and executing the following operations for each extracted eigenvalue, until execution for the extracted eigenvalues is completed. Selecting an eigenvalue, and performing at least two matrix transformations on the eigenvalue using a pre-obtained matrix parameter in order to obtain a first matrix vector corresponding to the eigenvalue; when a first matrix vector corresponding to each extracted eigenvalue is obtained, obtaining second matrix vectors with respect to the at least two extracted eigenvalues using a convolutional network calculation method according to the obtained first matrix vector corresponding to each eigenvalue; and obtaining a status of an image characteristic in the image data by means of estimation according to the second matrix vectors. In this way, accuracy of estimation is effectively improved.

Abstract: An improved method of analyzing software issues may include retrieving and storing selected data elements from the operating system kernel data prior to performing a memory dump. The method of retrieving the selected kernel data may include creating a thread dedicated to collecting the data and storing it in a memory location for analysis after the memory dump. The operating system kernel data may be analyzed in conjunction with the prior art dump data to identify a root cause of the software issue.

Abstract: A power inverter with liquid cooled busbars includes multiple AC power outlets. The power inverter also includes a busbar having a busbar arm connected to one of the AC power outlets, and a busbar leg having a first end connected to the busbar arm. The busbar leg is at least partially situated in a cooling channel of the power inverter, which may be a built-in cooling channel or a detachable cooling channel. A second end of the busbar leg extends beyond the cooling channel and is exposed for electrical connection.

Abstract: An electrical machine includes an electric motor, a cooling jacket over the electric motor, and a power inverter having multiple AC power outlets. The electrical machine also includes an elongated busbar having an end adjacent to and coupled to an AC power outlet. The other end of the elongated busbar is adjacent to and coupled to the electric motor. The elongated busbar traverses from one end of the electric motor to a second end of the electric motor over, and in thermal contact with, the cooling jacket so as to reduce a high temperature at the electric motor to a low temperature at the AC power outlet.

Abstract: Disclosed is a co-segmentation method and apparatus for a three-dimensional model set, which includes: obtaining a super patch set for the three-dimensional model set which includes at least two three-dimensional models, each of the three-dimensional models including at least two super patches; obtaining a consistent affinity propagation model according to a first predefined condition and a conventional affinity propagation model, the consistent affinity propagation model being constraint by the first predefined condition which is position information for at least two super patches that are in the super patch set and belong to a common three-dimensional model set; converting the consistent affinity propagation model into a consistent convergence affinity propagation model; clustering the super patch set through the consistent convergence affinity propagation model to generate a co-segmentation outcome for the three-dimensional model set.

Abstract: Disclosed herein are a system and method for verifying face images based on canonical images. The method includes: retrieving, from a plurality of face images of an identity, a face image with a smallest frontal measurement value as a representative image of the identity; determining parameters of an image reconstruction network based on mappings between the retrieved representative image and the plurality of face images of the identity; reconstructing, by the image reconstruction network with the determined parameters, at least two input face images into corresponding canonical images respectively; and comparing the reconstructed canonical images to verify whether they belong to a same identity, where the representative image is a frontal image and the frontal measurement value represents symmetry of each face image and sharpness of the image. Thus, canonical face images can be reconstructed using only 2D information from face images under an arbitrary pose and lighting condition.

Abstract: A method and a system for a mobile robot to self-establish a map indoors are provided, and the method comprises: forming an initialized map (101); marking a coordinate origin in the initialized map (102); causing the robot to travel throughout indoor accessible regions to record path information and environment information (103); causing the robot to calculate and mark a CV value of each grid in the map (104); and establishing the map according to the path information and the CV value (105), the path information and the CV value being obtained through calculation by using a mathematic algorithm. By adopting a grid map to perform modeling, real-time adjustment and correspondence of an indoor environment and grid information are realized and effectiveness of a map model is ensured; further, the grid map is easy to be maintained and is convenient for quick access of map data.

Abstract: Disclosed are methods for object tracking. In an example, the method comprises: determining a region of interest (ROI) in a first frame of a video sequences; feeding the determined ROI forward through a first CNN (convolutional network) to obtain a plurality of first feature maps in a higher layer of the CNN and a plurality of second feature maps in a lower layer of the first CNN; selecting a plurality of feature maps from the first and second feature maps, respectively; predicting, based on the selected first and second feature maps, two target heat maps indicating a target location for said objects in the current frame, respectively; and estimating, based on the two predicated target heat maps, a final target location for the object in the current frame.

Abstract: The present application relates to post estimation methods and apparatuses, and computer systems, wherein the method includes: extracting a feature in each body part of body parts of an object in an image to generate feature maps for the each body part, wherein the each body part corresponds to at least one part type; predicting part type scores respectively for features in each of the feature maps and establishing part type score maps based on the predicted part type scores; optimizing, for at least one point in each of the part type score maps, the established part type score maps based on a message related to an adjacent body part of a body part corresponding to the point; and determining an estimated position and an estimated part type of the each body part based on the optimized part type score maps to obtain an estimated pose of the object.

Abstract: Present invention provides a ranking convolutional neural network constructing method and an image processing method and apparatus thereof. The ranking convolutional neural network includes a ranking layer that is configured to sort an output of a previous layer of the ranking layer, generate an output of the ranking layer according to the sorted output, and output the output of the ranking layer to a next layer of the ranking layer. Using the ranking convolutional neural network enables obtaining an output feature corresponding to the input feature image through automatic learning. Compared with prior art methods that obtain features through manual calculation, the method of the present invention is superior in terms of reflecting the objective laws contained by the patterns of the actual scene. When applied to the field of image processing, the method can significantly improve the effect of image processing.

Abstract: Dynamic security code speech-based identity authentication system and method having self-learning function, being equipped with: a time-varying data storage unit for storing speech data of each user with time labels; a time-varying data update module (23) for storing the latest speech data into the time-varying data storage unit; a time window channel construction module (24) for extracting speech data from the time-varying data storage unit in the order of the time labels, constructing and updating the time window channel comprising multiple sets of speech data; a voiceprint model reconstruction module (25) reconstructing the user voiceprint model by using the multiple sets of speech data comprised in the updated time window channel.

Abstract: Disclosed are a method and an apparatus for face verification. The apparatus comprises a feature extracting unit configured to extract HIFs (Hidden Identity Features) for different regions of faces by using differently trained ConvNets, wherein last hidden layer neuron activations of said ConvNets are considered as the HIFs. The apparatus further comprises a verification unit configured to concatenate the extracted HIFs of each of the faces to form a feature vector, and then compare two of the formed feature vectors to determine if they are from the same identity or not.

Abstract: A reticle shape regulation device includes: an adsorption device having an upper surface and a lower surface; and a limit mechanism having a limit surface. The adsorption device is movable relative to the limit mechanism at least in a vertical direction. The upper surface of the adsorption device faces toward and is engagable with the limit surface. The lower surface of the adsorption device defines a vacuum chamber that is configured for communication with a negative-pressure source so as to adsorb the reticle by a negative pressure. The lower surface of the adsorption device further defines at least one positive-pressure outlet that is in communication with a positive-pressure source and is configured to supply a continuous positive-pressure air flow between the lower surface of the adsorption device and the reticle during the adsorption of the reticle.

Abstract: Methods and electronic devices for adjusting an operating frequency of a memory are disclosed. The method includes: transmitting to the memory a first command that instructs the memory to hold the data information in the memory; transmitting to the memory controller a second command that adjusts the first frequency of the memory controller to a second frequency; and transmitting to the memory a third command that instructs the memory to exchange the data information according to the second frequency of the memory controller. According to the disclosure, it is possible to dynamically adjust the frequency of the memory during operation, avoiding the need of the user to turn off and then turn on the electronic device to adjust the frequency of the memory.