Abstract: A medical diagnosis assistance system, a medical diagnosis assistance method, and a training method for training an artificial intelligence entity are disclosed. The medical diagnosis assistance system includes: an input interface configured to receive medical image data of a patient; a computing device configured to implement: a classification module configured to classify parts of interest, POI, comprising objects of interest, OOI, and/or regions of interest, ROI, within the received medical image data, and to assign a corresponding reliability metric to each of the classified POI; and an analysis module configured to determine, based on the POI and the assigned reliability metric, an analysis of the medical image data; and an output interface configured to output an output signal indicating the analysis.

Abstract: Provided is a computer-implemented method for training a machine learning (ML) model using labelled and unlabelled data, the method comprising obtaining a set or training data comprising a set of labelled data items and a set of unlabelled data items, training a loss module of the ML model using labels in the set of labelled data items, to generate a trained loss module capable of estimating a likelihood of a label for a data item, and training a task module of the ML model using the loss module, the set of labelled data items, and the set of unlabelled data items, to generate a trained task module capable of making a prediction of a label for input data.

Abstract: Computing platforms and methods are disclosed for verification of cleaning services to be performed in an area to be cleaned. Exemplary implementations may: identify, from among a plurality of cleaning regions relating to the area to be cleaned, a group of designated cleaning regions; randomly generate, with respect to the plurality of cleaning regions, a set of inspection regions; provide a user interface to prompt a user to capture an image of each inspection region; directly capture the images of each inspection region via the user interface; compare the captured images of each inspection region with corresponding reference images to determine whether each of the inspection regions has been properly cleaned; and output an inspection result based on the comparison of the captured images with the corresponding reference images. Implementations provide a method for virtually supervising otherwise unsupervised workers, which increases accountability and generates unprecedented visibility.

Abstract: An information processing apparatus includes a processor configured to: classify an acquired image by using a rule in which an element of an image, which is common in each type of a form shown by the image, is defined; and perform a process of setting a region in which at least one element is displayed except for the element defined by the rule used in classification in the classified image, to be unclear, and cause a display device to display the processed image.

Abstract: A display device includes a touch sensor, a fingerprint sensor, and a sensor driver. The touch sensor generates a touch sensing signal in response to touch of an object on a display panel. The fingerprint sensor detects the object in a first mode to generate a first sensing signal and detects the object in a second mode to generate a second sensing signal. The sensor driver calculates a touch position and a moisture level of the object based on the touch sensing signal, generates fingerprint information based on the first sensing signal, and corrects the moisture level based on the second sensing signal.

Abstract: Systems and methods include performing inline monitoring of production traffic between users, the Internet, and cloud services via a cloud-based system; utilizing a trained machine learning model to inspect static properties of files in the production traffic; and classifying the traffic as one of malicious or benign based on the trained machine learning model.

Abstract: Techniques are disclosed for using and training a descriptor network. An image may be received and provided to the descriptor network. The descriptor network may generate an image descriptor based on the image. The image descriptor may include a set of elements distributed between a major vector comprising a first subset of the set of elements and a minor vector comprising a second subset of the set of elements. The second subset of the set of elements may include more elements than the first subset of the set of elements. A hierarchical normalization may be imposed onto the image descriptor by normalizing the major vector to a major normalization amount and normalizing the minor vector to a minor normalization amount. The minor normalization amount may be less than the major normalization amount.

Abstract: This disclosure provides a moving object tracking method and apparatus. The method includes: obtaining a current frame captured by a camera; predicting a current state vector of the camera based on an inertial measurement unit IMU and the current frame, to obtain a predicted value of the current state vector of the camera; predicting a current state vector of a target object that is moving in the current frame, to obtain a predicted value of the current state vector of the target object; and updating a Kalman state vector based on a measurement result of an image feature in the current frame. According to technical solutions provided in this disclosure, a target object that is moving in a surrounding environment can be tracked and a pose of the target object can be estimated while a pose of a system can be estimated.

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

Abstract: The description relates the feature matching. Our approach establishes pointwise correspondences between challenging image pairs. It takes off-the-shelf local features as input and uses an attentional graph neural network to solve an assignment optimization problem. The deep middle-end matcher acts as a middle-end and handles partial point visibility and occlusion elegantly, producing a partial assignment matrix.

Abstract: A genetic loss function optimization (hereafter “GLO”) process uses a genetic algorithm to construct candidate loss functions as trees. The process takes the best candidate loss functions from this set and optimizes the coefficients thereof using covariance-matrix adaptation evolutionary strategy (hereafter “CMA-ES”), resulting in new loss functions showing substantial improvements in accuracy, convergence speed, and data requirements.

Abstract: Techniques regarding transferring learning outcomes across machine learning tasks in automated machine learning systems are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a transfer learning component that can executes a machine learning task using an existing artificial intelligence model on a sample dataset based on a similarity between the sample dataset and a historical dataset. The existing artificial intelligence model can be generated by automated machine learning and trained on the historical dataset.

Abstract: An apparatus includes a processing resource configured to receive a feature vector of a data stream. The feature vector includes a set of feature values. The processing resource is further configured to calculate a set of feature labels based at least in part on the set of feature values to generate a label vector, provide the label vector to another processing resource, and receive a plurality of classifications corresponding to each feature label of the label vector from the other processing resource. The plurality of classifications are generated based at least in part on a respective range of feature values of the set of feature values. The processing resource is configured to then combine the plurality of classifications to generate a final classification of the data stream.

Abstract: A semiconductor image classifier. Convolution functions are applied to modify the wafer images in order to extract key information about the image. The modified images are condensed then processed through a series of pairwise classifiers, each classifier configured to determine that the image is more like one of the pair than the other. Probabilities from each classifier are collected to form a prediction for each image.

Abstract: System and method for intelligently monitoring the production line that can monitor an inspected object image captured by an image capturing device, thereby allowing an operating station host to provide a labeling module to reinspect a classification decision of a classifier subsystem, to achieve the purpose of verifying the classification decision or checking whether there are missed inspections. In addition, the classifier subsystem can automatically filter out classification decisions with lower reliability to effectively reduce the number of reinspection. Moreover, a group of inspected object images can be analyzed first to obtain image difference features through comparison, which is suitable for insufficient training samples. Furthermore, the labeling module can simultaneously reinspect highly relevant historical classification decisions.

Abstract: A character restoration method and apparatus, a storage medium, and an electronic device are provided. The character restoration method includes: a character identifier of a character in a text region is determined, where the character identifier is used for uniquely identifying the character; and encoding is performed at least according to the character identifier, and encoded data is sent to a receiving end, where the encoded data is used for the receiving end to decode the encoded data and restore the character according to the character identifier obtained after decoding, that is, encoding is performed merely according to a small amount of information, and then the information is obtained by decoding, so as to restore the character.

Abstract: A security platform employs a variety techniques and mechanisms to detect security related anomalies and threats in a computer network environment. The security platform is “big data” driven and employs machine learning to perform security analytics. The security platform performs user/entity behavioral analytics (UEBA) to detect the security related anomalies and threats, regardless of whether such anomalies/threats were previously known. The security platform can include both real-time and batch paths/modes for detecting anomalies and threats. By visually presenting analytical results scored with risk ratings and supporting evidence, the security platform enables network security administrators to respond to a detected anomaly or threat, and to take action promptly.

Abstract: Systems, and method and computer readable media that store instructions for configuring spanning elements of a signature generator.

Abstract: The present disclosure provides a method and a system for training a machine learning system. Multiple pieces of sample data are used for training the machine learning system. The method includes acquiring multiple sample sets, each sample set including sample data in a corresponding sampling time period; setting a sampling rate for each sample set according to the corresponding sampling time period; acquiring multiple sample sets sampled according to set sampling rates; determining importance values of the multiple sampled sample sets; correcting each piece of sample data in the multiple sampled sample sets by using a corresponding importance value to obtain corrected sample data; and inputting the corrected sample data into the machine learning system to train the machine learning system.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for generating a single-index model (SIM) tree. An example method includes receiving a data set and a maximum tree depth. The example method further includes screening a set of variables from the data set to form split variables. The method may include, while maximum tree depth has not been reached, (i) generating a fast SIM estimation for nodes of a tree level, (ii) for each node, selecting a split point and split variable based on the fast SIM estimation, (iii) based on the selected split points and split variables, generating nodes for a next tree level, each including a subset of data, and (iv) repeating steps (i), (ii), and (iii). The method may include fitting a SIM for each leaf node at maximum tree depth based on a subset of the data set represented by the leaf node.

Abstract: Provided is an apparatus for classifying an attribute of an image object, including: a first memory configured to store target object images that are indexed; a second memory configured to store target object images that are un-indexed; and an object attribute classification module configured to perform learning on the un-indexed target object images to construct a classifier for classifying a detailed attribute of target object, and finely adjust the classifier on the basis of the indexed target object images.

Abstract: Modifying an index for a database is provided. An index tree for the database is traversed by: identifying a next node in the index tree, requesting a lock of the next node in the index tree, responsive to locking of the next node in the index tree, releasing a lock of a current node of the index tree, and making the next node in the index tree the current node of the index tree, until the current node of the index tree is a leaf node of the index tree. Responsive to determining to split the leaf node, the lock of the leaf node is released and, after releasing the lock of the leaf node, a lock of a non-leaf node parent of the leaf node in the index tree is requested.

Abstract: There is provided a system and method of segmenting an image of a fabricated semiconductor specimen. The method includes: obtaining a first probability map corresponding to the image representative of at least a portion of the fabricated semiconductor specimen and indicative of predicted probabilities of pixels in the image to correspond to one or more first structural elements presented in the image, obtaining a first label map informative of one or more segments representative of second structural elements and labels associated with the segments, performing simulation on the first label map to obtain a second probability map indicative of simulated probabilities of pixels in the first label map to correspond to the one or more segments, and generating a second label map based on the first probability map and the second probability map, the second label map being usable for segmentation of the image with enhanced repeatability.

Abstract: Aspects of the present disclosure involve a system and a method for performing operations comprising: identifying a plurality of features for an image received by a messaging application server; assigning a first of the plurality of features and a second of the plurality of features respectively to a first nearest visual codebook cluster and a second nearest visual codebook cluster; applying the first and second nearest visual codebook clusters to a visual search database to identify a plurality of candidate matching images; selecting a given matching image based on a geometric verification of the plurality of matching images and the received image; and accessing an augmented reality experience corresponding to the given matching image.

Abstract: A method for generating positive and negative training samples is presented. The method includes identifying false positive images of an object based on multiple images of an environment. The method also includes generating positive training samples from a set of images of the object. The method further includes generating a negative training sample from the false positive image. The method still further includes training an object detection system based on the positive training samples and the negative training sample.

Abstract: Virtual humans exhibit behaviors associated with inputs and outputs of an autonomous control system for medical monitoring of patients. To foster the awareness and trust, the virtual humans exhibit situational awareness via apparent (e.g., rendered) behaviors based on inputs such as physiological vital signs. The virtual humans also exhibit situational control via apparent behaviors associated with outputs such as direct control of devices, functions of control, actions based on high-level goals, and the optional use of virtual versions of conventional physical controls. A dynamic virtual human who continually exhibits awareness of the system state and relevant contextual circumstances, along with the ability to directly control the system, is used to reduce negative feelings associated with the system such as uncertainty, concern, stress, or anxiety on the part of real human patients.

Abstract: A computer-implemented method comprises displaying a grid comprising a plurality of cells; receiving user input modifying a state of one or more of the plurality of cells to create a graphical shape in the grid, wherein each of the plurality of cells is limited to one of a plurality of predefined states; requesting an internet protocol (IP) address corresponding to the graphical shape; and in response to receiving the IP address corresponding to the graphical shape, retrieving a web resource located at the IP address.

Abstract: The present disclosure relates to a semantic segmentation method and system for a remote sensing image fusing GIS data. The method includes: obtaining a first remote sensing data training set and first GIS data; preprocessing the first remote sensing data training set to obtain a second remote sensing data training set; preprocessing the first GIS data based on the second remote sensing data training set to obtain second GIS data; performing data enhancement on the second remote sensing data training set to obtain a third remote sensing data training set; training a semantic segmentation model based on the third remote sensing data training set and the second GIS data; and performing semantic segmentation on the remote sensing image to be segmented based on the first GIS data and the trained semantic segmentation model to obtain a semantic set.

Abstract: A field management apparatus 10 is provided with a learning model generation unit 11 that generates a learning model 15, to learn feature amounts of the image of the phenomenon that results from the fault in the field equipment, an image acquisition unit 12 that acquires an aerial image of a target region, an image specification unit 13 that applies the aerial image to the learning model 15, and specifies an image of the phenomenon that results from the fault in the field equipment in the aerial image, and a fault location specification unit 14 that specifies a fault location of the field equipment in the target region, based on the image of the phenomenon that results from the fault in the field equipment.

Abstract: A super-resolution method according to the inventive concept may include receiving an input image of low resolution, separating the input image into low resolution (LR) unit patches, classifying a texture type of each of pixels included in the input image using a local binary pattern for the LR unit patches, generating high resolution (HR) unit patches corresponding to each of the pixels based on a mapping kernel corresponding to the texture type, and combining the HR unit patches based on a predetermined setting to generate an output image of high resolution.

Abstract: A method for mapping brain function of a subject includes generating a lesion mask using a search light algorithm based on a plurality of anatomical images of the subject. The plurality of anatomical images are registered with atlas images by nonlinear atlas registration using the generated lesion mask to generate a warping map. A plurality of functional images of the subject are resampled using the warping map to generate a functional map, functional connectivity is computed using the functional map and a multi-layer perceptron.

Abstract: A learning and discrimination device configured to perform learning by gradient boosting, including: a histogram memory unit configured to store, for each value of a feature amount, a histogram obtained by integrating gradient information corresponding to the value in sample data; a category accumulated gradient calculator configured to calculate a histogram corresponding to a value of the feature amount corresponding to a threshold for the feature amount as a cumulative sum of the gradient information; a non-category accumulated gradient calculator configured to calculate, as a cumulative sum of the gradient information, a sum of a histogram corresponding to a value of the feature amount that is classified using a classification method with the threshold different from the category accumulated gradient calculator; and a cumulative sum selector configured to output the cumulative sum calculated by the category accumulated gradient calculator or the non-category accumulated gradient calculator.

Abstract: A signature verification system, which comprises a plurality of worn devices of signing users, each provided with one or more motion sensors, and a processor for receiving motion signals from the sensors, the processor is adapted to define a set of features that describe a signature and distinguish one signature from another; perform a training phase by obtaining motion signals from one or more motion sensors of the worn devices; training a machine learning classifier using the instances and labels; obtain motion signals from motion sensors of the a worn device, the motion being of an allegedly genuine signature of one of the users; scale and domain transform the allegedly genuine signature; calculate values of the features describing the allegedly genuine signature with respect to scaled and transformed reference signatures of the one of the users; and apply the trained classifier on the feature values, thereby classifying the allegedly genuine signature as genuine or forged.

Abstract: Systems, devices, media, and methods are presented for graphical icon identification within an image or video stream. The systems and methods receive an image including a graphical icon. The systems and methods identify a set of proposed regions of the image, at least one proposed region of the set of proposed regions containing the graphical icon and extract a set of semantic features for each proposed region of the set of proposed regions. Based on the set of semantic features of the set of proposed regions, the systems and methods identify a set of proposed icons corresponding to the graphical icon included in the image and determine a match between the graphical icon and at least one proposed icon of the set of proposed icons.

Abstract: An image processing method for performing image alignment includes: acquiring a moving image generated by a first imaging modality; acquiring a fixed image generated by a second imaging modality; jointly optimizing a generator model, a register model, and a segmentor model applied to the moving image and the fixed image according to a plurality of cost functions; and applying a spatial transformation corresponding to the optimized register model to the moving image to align the moving image to the fixed image; wherein: the generator model generates a synthesized image from the moving image conditioned on the fixed image; the register model estimates the spatial transformation to align the synthesized image to the fixed image; and the segmentor model estimates segmentation maps of the moving image, the fixed image, and the synthesized image.

Abstract: A method for super resolution of an image imitating optical zoom implemented on a resource-constrained mobile device is includes inputting a first-resolution image. The method also includes assigning a super resolution factor from a predefined set of super resolution factors that indicate increasing the first resolution to obtain a second-resolution image. The super resolution factor indicates a trained intelligent system imitating the operation of the corresponding optical system among a plurality of intelligent systems trained for each super resolution factor of the predefined set of super resolution factors. The method further includes transforming the first-resolution image into the second-resolution image using said trained intelligent system.

Abstract: A method, apparatus and system for visual grounding of a caption in an image include projecting at least two parsed phrases of the caption into a trained semantic embedding space, projecting extracted region proposals of the image into the trained semantic embedding space, aligning the extracted region proposals and the at least two parsed phrases, aggregating the aligned region proposals and the at least two parsed phrases to determine a caption-conditioned image representation and projecting the caption-conditioned image representation and the caption into a semantic embedding space to align the caption-conditioned image representation and the caption. The method, apparatus and system can further include a parser for parsing the caption into the at least two parsed phrases and a region proposal module for extracting the region proposals from the image.

Abstract: Abnormal motions are detected in sensor data collected with respect to performance of repetitive human activities. An autoencoder network model is trained based on a set of standard activity. Repetitive activity is extracted from sensor data. A first score is generated indicative of distance of a repetition of the repetitive activity from the standard activity. The repetitive activity is used to retrain the autoencoder network model, using weights of the autoencoder network model as initial values, the weights being based on the training of the autoencoder network model using the set of standard activity. A second score is generated indicative of whether the repetition is an outlier as compared to other repetitions of the repetitive activity. A final score is generated based on a weighting of the first score and the second score.

Abstract: A mobile device automatically determines which location of a plurality of locations of a vehicle a user of the mobile device is located at without knowing assistance of the user. The mobile device determines that the mobile device is likely in a moving vehicle and that the user is actively interacting with the mobile device. The mobile device captures an image via an optical sensor of the mobile device without assistance from the user for the capture. The mobile device determines a location of the user within the vehicle based upon an analysis of the image. The analysis includes an execution of a model that utilizes at least the captured image as an input to determine the location. The mobile device, after determining the location, performs one or more actions.

Abstract: An artificial intelligence (AI) system utilizing machine learning algorithm and application of an electronic apparatus includes a memory and a processor to store at least one obtained image in the memory, and based on the at least one image being classified on a basis of an aesthetic score through an AI model, sort and provide the at least one image based on the classification result, and the AI model may include a plurality of layers with different depths, extract a feature of the at least one image from each of the plurality of layers, and classify the at least one image on a basis of the aesthetic score in accordance with the plurality of extracted features.

Abstract: Disclosed is a learning method that may include generating learning data that may contain a composite image including a CG model of an object and may contain a training signal of the object. Further disclosed is a way of learning a recognition function of recognizing information regarding the object from the composite image by neuro computation using the learning data, the generated learning data including new learning data on the basis of a gradient of error for each of pixels of the composite image, which may be calculated from the composite image and the training signal by backpropagation. The disclosed learning may include learning the recognition function by using the new learning data.

Abstract: According to the embodiments of the present invention, there is provided a method for training an image semantics annotation apparatus, comprising: a. providing a plurality of training images, wherein semantics and visual attribution description of respective training images are known; b. inputting at least part of the training images to a locator of the image semantic annotation apparatus; c. determining, by the locator, at least one local area of each input training image, and inputting the determined respective local areas into an attribute predictor of the image semantic annotation apparatus; d. obtaining a visual attribute prediction result of each input local area from the attribute predictor; e. training the locator and the attribute predictor according to the obtained visual attribute prediction result of each local area and a known visual attribute description of the corresponding training image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying videos using neural networks. One of the methods includes obtaining a temporal sequence of video frames, wherein the temporal sequence comprises a respective video frame from a particular video at each of a plurality time steps; for each time step of the plurality of time steps: processing the video frame at the time step using a convolutional neural network to generate features of the video frame; and processing the features of the video frame using an LSTM neural network to generate a set of label scores for the time step and classifying the video as relating to one or more of the topics represented by labels in the set of labels from the label scores for each of the plurality of time steps.

Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.

Abstract: A multi-label heat map display system is operable to receive a medical scan and a set of heat maps set of heat maps that each correspond to probability matrix data generated for each of a set of abnormality classes. An interactive interface that displays image data of the medical scan and at least one of the set of heat maps is generated for display on a display device associated with the multi-label heat map display system. User input to a client device is received, and an updated interactive interface that includes a change to the display of the at least one of the set of heat maps by the second portion of the interactive interface in response to the user input is displayed.

Abstract: Feature descriptor matching described herein may include receiving a first input image and a second input image. A feature detector may detect features from the first and second input images. A descriptor extractor may learn local feature descriptors from the features of the first and second input images based on a feature descriptor matching model trained using a ground truth data set. The descriptor extractor may determine a listwise mean average precision (mAP) rank of a pool of candidate image patches from the second input image with respect to a queried image patch from the first input image based on the feature descriptor matching model, the first set of local feature descriptors, and the second set of local feature descriptors. The descriptor matcher may generate a geometric transformation between the first input image and the second input image based on the listwise mAP and a convolutional neural network.

Abstract: An image processing apparatus, includes an image classifier configured to determine whether an input image is a low-quality image or a high-quality image; and an image evaluator configured to determine a first predetermined number of clearest images from a plurality of low-quality images determined by the image classifier.

Abstract: Some implementations can include a computer-implemented method and/or system for automatic suggestion to share images. The method can include identifying a plurality of images associated with a user and detecting one or more entities in the plurality of images. The method can also include constructing an aggregate feature vector for the plurality of images based on the one or more entities in the plurality of images and determining that the aggregate feature vector matches a first cluster. The method can further include, in response to determining that the aggregate feature vector matches the first cluster, providing a suggestion to the user for an image composition based on the plurality of images.

Abstract: A vision-aided inertial navigation system determines navigation solutions for a traveling vehicle. A navigation solution module analyzes image sensor poses and estimated inertial navigation solutions to produce a time sequence of system navigation solution outputs that represent changing locations of the traveling vehicle. A loop closure detector performs a two-threshold image classification to classify an incoming navigation image as novel, loop-closing, or neither, and the navigation solution module resets the navigation solution output to represent a previous location when the loop closure detector classifies an incoming navigation image as loop-closing.

Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.