Abstract: An image processing method includes the following steps. A plurality of facial landmarks of a face frame are analyzed. A feature width is calculated according to the facial landmarks, and a head pose is analyzed according to the facial landmarks. The head pose is utilized to update the feature width to generate an updated width. A scale ratio of the updated width to an initial width is calculated. An object distance of a virtual camera is controlled according to the scale ratio. A two-dimensional image is captured from a virtual scene according to the object distance of the virtual camera.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for increasing dimensionality of data structures associated with filling positions. In some implementations, a prediction of desired experience for a given position to be filled may be incorporated into a searchable field of the data structure. Among other things, increasing the dimensionality of the data structure may facilitate more granular searching of positions and guided creation of new positions to be filled. In some implementations, a predicted desired experience may be used to notify a user posting a new position whether a specified desired experience corresponds to a predicted desired experience.

Abstract: A method for automatically classifying transition motion includes following steps performed by a computing device: obtaining a plurality of transition motions, with each transition motion being associated with a source motion, a destination motion, and a transition mechanism converting the source motion into the destination motion; extracting a property vector from each transition motion and thereby generating a plurality of property vectors, wherein each property vector includes a plurality of transition properties; and performing a clustering algorithm according to the property vectors to generate a plurality of transition types.

Abstract: A processing element array includes N processing elements (PE) arranged linearly, N?2, and an operating method of the PE array includes: performing a first data transmission procedure, where an initial value of I is 1 and the first data transmission procedure includes: operating, by an ith PE, according to a first datum stored in itself, and sending the first datum to other PEs for their operations, adding 1 to I when I<N, and performing the first data transmission procedure again, performing a second data transmission procedure when I is equal to N, which includes: operating, by the Jth PE, according to a second datum stored in itself, and sending the second datum to other PEs for their operations, reducing J by 1 when J>1 and the (J?1)th PE has the second datum, and performing the second data transmission procedure again.

Abstract: The present disclosure provides a packing method including following steps. Genetic algorithm is utilized to calculate multiple packing programs. Multiple candidate packing programs including all items are selected from the packing programs. Among each of the candidate packing programs, at least one of the items to be placed earlier is classified into a first subset, and at least another one of the items to be placed later is classified into a second subset. Among each of the candidate packing programs, a first packing for the first subset is maintained, and a second packing for the second subset is recalculated by using a greedy algorithm to generate an updated second packing.

Abstract: A machine learning model training method, for training a machine learning model, includes following steps. A first model is trained according to a first set of labels and a first training set. A third training set which is a portion of the training data not included in the first training set is labeled according to the first model, so as to generate a third set of labels. A second model is pre-trained according to the third set of labels and the third training set. The second model is fine-tuned according to the second set of labels and the second training set, so as to generate a third model.

Abstract: A touch-based method for user authentication includes a training stage and an authentication stage. The training stage includes: generating, by a touch interface, a plurality of training touch parameters; and generating, by a processor, a training heat map according to the plurality of training touch parameters. The authentication stage includes: generating, by the touch interface, a plurality of testing touch parameters; generating, by the processor, a testing heat map according to the plurality of testing touch parameters; comparing, by the processor, the testing heat map with the training heat map to generate an error map; and generating, by the processor, one of pass signal and fail signal according to the error map.

Abstract: An image data augmentation device is provided, which comprises an image capturing circuit and a processor. The processor is configured to execute the following operations: using an object detection model to generate multiple bounding boxes and respective classification labels of the bounding boxes from an image; identifying an overlap ratio between the two bounding boxes, and determining whether the overlap ratio between the two bounding boxes is more than a ratio threshold, where the two bounding boxes have the same classification label; and when the overlap ratio between the two bounding boxes is more than the ratio threshold, deleting one of the two bounding boxes to update the bounding boxes, thereby by using the bounding boxes and the respective classification labels of the bounding boxes for executing machine learning.

Abstract: A method for automatically classifying transition motion includes following steps performed by a computing device: obtaining a plurality of transition motions, with each transition motion being associated with a source motion, a destination motion, and a transition mechanism converting the source motion into the destination motion; extracting a property vector from each transition motion and thereby generating a plurality of property vectors, wherein each property vector includes a plurality of transition properties; and performing a clustering algorithm according to the property vectors to generate a plurality of transition types.

Abstract: A data splitting method for validating machine learning is adapted to a BP (blood pressure) dataset having a plurality of subjects and includes: dividing measurement ranges of the SBP (systolic blood pressure) data and the DBP (diastolic blood pressure) data into first intervals and second intervals; generating a plurality of classes according to the first and second intervals, wherein each class includes one of the first intervals and one of the second intervals; determining and recording a match condition of the BP data of each subject and classes, and thereby generating a plurality of match conditions corresponding the plurality of subjects, wherein each match condition includes a plurality of labels corresponding to the classes, each label has a first state or a second state; and performing a distribution procedure according to the matching conditions to distribute the BP data of subjects into a plurality of subsets.

Abstract: A method for establishing a complex motion controller includes following steps: obtaining a source controller and a destination controller, wherein the source controller is configured to generate a source motion, and the destination controller is configured to generate a destination motion; determining a transition tensor between the source controller and the destination controller, wherein the transition tensor has a plurality of indices, one of the plurality of indices corresponds to a plurality of phases of the source motion; calculating a plurality of transition outcomes of the transition tensor and recording the plurality of transition outcomes according to the plurality of indices; calculating a plurality of transition qualities according to the plurality of transition outcomes; and searching for an optimal transition quality from the plurality of transition qualities to establish a complex motion controller for generating a complex motion corresponding to one of the plurality of phases.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for increasing dimensionality of data structures associated with filling positions. In some implementations, a prediction of desired experience for a given position to be filled may be incorporated into a searchable field of the data structure. Among other things, increasing the dimensionality of the data structure may facilitate more granular searching of positions and guided creation of new positions to be filled. In some implementations, a predicted desired experience may be used to notify a user posting a new position whether a specified desired experience corresponds to a predicted desired experience.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for increasing dimensionality of data structures associated with filling positions. In some implementations, a prediction of desired experience for a given position to be filled may be used to increase the dimensionality of a searchable data structure that represents the given position. For example, the predicted desired experience may be incorporated into a searchable field of the data structure. Among other things, increasing the dimensionality of the data structure may facilitate more granular searching of positions and guided creation of new positions to be filled. In some implementations, a predicted desired experience may be used to notify a user posting a new position whether a specified desired experience corresponds to a predicted desired experience.

Abstract: The present disclosure provides a package packing method. The package packing method includes the following steps. An order including multiple items is received. The selected boxes with the same minimum width and minimum height are selected from multiple of boxes according to a length and a width of a main content item. The selection boxes have different depths. The minimum width and minimum height of the selection boxes are set as two-dimensional size dimension of a reference boxes. Under a condition of the two-dimensional size of the reference box, a minimum depth of the reference box and a packing scheme are calculated according to size of each of the main content item and attached content items, to fit the content items into the reference box. A target box is selected from these selected boxes according to the minimum depth of the reference box.

Abstract: An audiovisual device includes an input interface configured to receive a character indication signal, a display unit configured to display a video and output an audio signal of the video, wherein the video includes a plurality of characters, and the audio signal includes a plurality of audio tracks, and a processor configured to perform calculation on a motion waveform of each of the characters in the video and a plurality of sound waveforms of the audio tracks to generate a plurality of correlation coefficients, and determine a character audio track of each of the characters according to the correlation coefficients of each of the characters. The processor extracts a target character audio track corresponding to the character indication signal, and controls the display unit to adjust a relative volume between the target character audio track and other audio tracks among the audio tracks when receiving the character indication signal.

Abstract: The present disclosure provides an electronic device including a processor and a memory device. The memory device is configured to store a residual neural network group for restoring data and a multi-head neural network. The multi-head neural network contains multiple of self-attention neural modules. The processor is configured to perform the following steps. Multiple pieces of data corresponding to multiple of leads are input into residual neural network groups, respectively, to generate multiple of feature map groups respectively correspond to the leads. The feature map groups are classified to the self-attention neural modules according to labels of the feature map groups.

Abstract: A scheduling device is provided, which includes a memory and a processor. The processor is configured to execute instructions to perform the following operations: (a) according to an order, are generating multiple candidate multi-production line schedules respectively, and each of the multiple candidate multi-production line schedules is used to assign multiple products of the order to multiple production lines; (b) performing a first crossover processing for each of the multiple candidate multi-production lines; (c) calculating respective first fitness scores of the multiple candidate multi-production line schedules for an elimination processing; (d) performing a second crossover processing for each of the multiple candidate multi-production lines; (e) calculating respective second fitness scores of the multiple candidate multi-production line schedules for an elimination processing; (f) determining whether an recursive end condition has been met according to the multiple second fitness scores.

Abstract: A method for generating reconstruction a reconstructed image is adapted to an input image having a target object. The method comprises converting the input image into a feature map with vectors by an encoder; performing a training procedure according to training images of reference objects to generate feature prototypes associated with the training images and store the feature prototypes to a memory; selecting a part of feature prototypes from the feature prototypes stored in the memory according to similarities between the feature prototypes and the feature vectors; generating a similar feature map according the part of feature prototypes and weights, wherein the weights represents similarities between the part of feature prototypes and the feature vectors; and converting the similar feature map into the reconstructed image by a decoder; wherein the encoder, the decoder and the memory form an auto-encoder.

Abstract: A keyboard file verification method based on image processing comprises controlling a processor to perform following operations: obtaining a keyboard file; generating, according to the keyboard file, a search index and a feature image; obtaining a template image from a template database according to the search index; performing a calibration operation according to the feature image, wherein the calibration operation comprises: adjusting a resolution of the feature image according to a resolution of the template image; performing a shifting operation according to the feature image, to generate a plurality of candidate images; and comparing a key block of each of the plurality of candidate images with a key block of the template image to generate a difference map and a comparison result.

Abstract: A touch-based method for user authentication includes a training stage and an authentication stage. The training stage includes: generating, by a touch interface, a plurality of training touch parameters; and generating, by a processor, a training heat map according to the plurality of training touch parameters. The authentication stage includes: generating, by the touch interface, a plurality of testing touch parameters; generating, by the processor, a testing heat map according to the plurality of testing touch parameters; comparing, by the processor, the testing heat map with the training heat map to generate an error map; and generating, by the processor, one of pass signal and fail signal according to the error map.