Abstract: We disclose multiband receivers for millimeter-wave devices, which may have reduced size and/or reduced power consumption. One multiband receiver comprises a first band path comprising a first passive mixer configured to receive a first input RF signal having a first frequency and to be driven by a first local oscillator signal having a frequency about ? the first frequency; a second band path comprising a second passive mixer configured to receive a second input RF signal having a second frequency and to be driven by a second local oscillator signal having a frequency about ? the second frequency; and a base band path comprising a third passive mixer configured to receive intermediate RF signals during a duty cycle and to be driven by a third local oscillator signal having a frequency about ? the first frequency or about ? the second frequency during the duty cycle.

Abstract: An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.

Abstract: A method of feature substitution for end-to-end image compression, is performed by at least one processor and includes encoding an input image, using a first neural network, to generate an encoded representation, and quantizing the generated encoded representation, using a second neural network, to generate a compressed representation. The first neural network and the second neural network are trained by determining a rate loss, based on a bitrate of the generated compressed representation, and updating the generated encoded representation, based on the determined rate loss.

Abstract: A computer-implemented method and system for determining the geographical location of a user based on the characteristics of intersecting features, such as a road intersection. Specifically, the geometry of each intersection in a geographical area is used to derive a unique fingerprint for each individual intersection, the fingerprint comprising information relating to the geometry, the geographical location of the intersection, and other characteristics. These fingerprints can then be stored locally to a device, for example, a mobile phone, a tablet, a wearable computing device, an in-vehicle infotainment (IVI) system and the like. To determine the geographical location of the device, the geometry of a nearby intersection may be analysed by some means and compared to the stored set of unique fingerprints to identify the intersection and its associated location.

Abstract: Systems and methods for identifying clouds and cloud shadows in satellite imagery are described herein. In an embodiment, a system receives a plurality of images of agronomic fields produced using one or more frequency bands. The system also receives corresponding data identifying cloud and cloud shadow locations in the images. The system trains. a machine learning system to identify at least cloud locations using the images as inputs and at least data identifying pixels as cloud pixels or non-cloud pixels as outputs. When the system receives one or more particular images of a particular agronomic field produced using the one or more frequency bands, the system uses the one or more particular images as inputs into the machine learning system to identify a plurality of pixels in the one or more particular images as particular cloud locations.

Abstract: Disclosed is a multi-modal convolutional neural network (CNN) for fusing image information from a frame based camera, such as, a near infra-red (NIR) camera and an event camera for analysing facial characteristics in order to produce classifications such as head pose or eye gaze. The neural network processes image frames acquired from each camera through a plurality of convolutional layers to provide a respective set of one or more intermediate images. The network fuses at least one corresponding pair of intermediate images generated from each of image frames through an array of fusing cells. Each fusing cell is connected to at least a respective element of each intermediate image and is trained to weight each element from each intermediate image to provide the fused output. The neural network further comprises at least one task network configured to generate one or more task outputs for the region of interest.

Abstract: In various examples, a deep neural network (DNN) is trained—using image data alone—to accurately predict distances to objects, obstacles, and/or a detected free-space boundary. The DNN may be trained with ground truth data that is generated using sensor data representative of motion of an ego-vehicle and/or sensor data from any number of depth predicting sensors—such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. The DNN may be trained using two or more loss functions each corresponding to a particular portion of the environment that depth is predicted for, such that—in deployment—more accurate depth estimates for objects, obstacles, and/or the detected free-space boundary are computed by the DNN. In some embodiments, a sampling algorithm may be used to sample depth values corresponding to an input resolution of the DNN from a predicted depth map of the DNN at an output resolution of the DNN.

Abstract: A communication apparatus includes: signal generation circuitry which, in operation, generates a control signal including a target reception power value regarding a target value of a reception power for the communication apparatus to receive an uplink (UL) response frame transmitted by each of one or more terminal stations, the control signal being a trigger frame that solicits transmission of the UL response frame from each of the one or more terminal stations; and transmission circuitry which, in operation, transmits the generated signal.

Abstract: A computer platform implements a precision agriculture system that predicts output conditions, such as diseases, salt damage, soil problems, water leaks and generic anomalies, for orchards under analysis. The computer platform stores site and crop datasets and processed satellite image for the orchards. An orchard data learned model predicts a propensity for existence of output conditions associated with the permanent crops based on the data values for the variables of the site and crop datasets. Also, a satellite model predicts a propensity for existence of the output conditions at the orchard based on processed satellite images. A precision agriculture management model is disclosed that integrates the orchard data learned model with the satellite model to accurately predict the output conditions.

Abstract: A computer platform implements a precision agriculture system that predicts output conditions, such as diseases, salt damage, soil problems, water leaks and generic anomalies, for orchards under analysis. The computer platform stores site and crop datasets and processed satellite image for the orchards. An orchard data learned model predicts a propensity for existence of output conditions associated with the permanent crops based on the data values for the variables of the site and crop datasets. Also, a satellite model predicts a propensity for existence of the output conditions at the orchard based on processed satellite images. A precision agriculture management model is disclosed that integrates the orchard data learned model with the satellite model to accurately predict the output conditions.

Abstract: A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. The method includes receiving, in a spiking neural network, a plurality of input values upon which a machine learning algorithm is based. The method also includes correlating, for each input value, a corresponding response speed of a corresponding neuron to a corresponding equivalence relationship between the input value to a corresponding latency of the corresponding neuron. Neurons that trigger faster than other neurons represent close relationships between input values and neuron latencies. Latencies of the neurons represent data points used in performing the machine learning. A plurality of equivalence relationships are formed as a result of correlating. The method includes performing the machine learning using the plurality of equivalence relationships.

Abstract: The present application discloses an image recognition method, apparatus, device, and a computer storage medium, which is related to a technical field of artificial intelligence, and in particular, to a technical field of image processing. The method includes: performing organ recognition on a human face image and marking positions of the human facial five sense organs in the human face image, obtaining a marked human face image; inputting the marked human face image into a backbone network model and performing feature extraction, obtaining defect features of the marked human face image outputted by different convolutional neural network levels of the backbone network model; and fusing the defect features of different levels that are located in a same area of the human face image, obtaining a defect recognition result of the human face image.

Abstract: Embodiments of the present disclosure disclose a method, apparatus, and device for fusing features applied to small target detection, and a storage medium, relate to the field of computer vision technology. A particular embodiment of the method for fusing features applied to small target detection comprises: acquiring feature maps output by convolutional layers in a Backbone network; performing convolution on the feature maps to obtain input feature maps of feature layers, the feature layers representing resolutions of the input feature maps; and fusing, based on densely connection feature pyramid network features, the input feature maps of each feature layer to obtain output feature maps of the feature layer. Since no additional convolutional layer is introduced for feature fusion, the detection performance for small targets may be enhanced without additional parameters, and the detection ability for small targets may be improved with computing resource constraints.

Abstract: Methods and systems for automatic estimation of object characteristics from a digital image are disclosed, including a method comprising sub-dividing into two or more segments a digital image comprising pixels and depicting an object of interest, wherein each segment comprises two or more pixels; assessing content depicted in one or more of the segments for a predetermined object characteristic using machine learning techniques comprising General Image Classification of the one or more segments using a convolutional neural network, wherein the General Image Classification comprises analyzing the segment as a whole and outputting a general classification for the segment as a whole as related to the one or more predetermined object characteristic; and determining a level of confidence of one or more of the segments having the one or more predetermined object characteristic based on the General Image Classification assessment.

Abstract: An embodiment of an image processing apparatus may comprise one or more processors, memory coupled to the one or more processor to store image and mask data, and logic coupled to the one or more processors and the memory, the logic to capture a volumetric broadcast video signal in real-time and generate a sequence of frame images from the captured real-time volumetric broadcast video signal, segment an input image, which corresponds to a single frame of the sequence of frame images, to generate a mask image associated with the input image, and determine a mask quality score based on the input image and the associated mask image in real-time. Other embodiments are disclosed and claimed.

Abstract: A method and system for locating a target object in a target scene. The method may include obtaining a depth image of the target scene. The depth image may include a plurality of pixels. The method may also include, for each of the plurality of pixels of the depth image, determining a first target coordinate under a target coordinate system. The method may further include generating a marking image according to the depth image and the first target coordinates of the plurality of pixels in the depth image. The marking image may represent potential target objects in the depth image. The method may also include determining a locating coordinate of the target object under the target coordinate system according to the marking image.

Abstract: There is described a neural network system for generating a graph, the graph comprising a set of nodes and edges. The system comprises one or more neural networks configured to represent a probability distribution over sequences of node generating decisions and/or edge generating decisions, and one or more computers configured to sample the probability distribution represented by the one or more neural networks to generate a graph.

Abstract: In a data processing method executed by a computer: inputting, in a third trained model, first output data corresponding to first input data for a first trained model to obtain second output data, the third trained model being acquired through training in which (i) output data of the first trained model is used as training data, and (ii) output data of a second trained model acquired by converting the first trained model is used as label data; obtaining first label data of the first input data; and retraining the first trained model using first differential data corresponding to differences between the second output data and the first label data.

Abstract: A system and method is disclosed for displaying augmented image data for invasive medical devices. A current orientation and a current position of the invasive medical device within a patient can be determined by applying a trained model of the invasive medical device to unannotated images of the invasive medical device as captured by an imaging device. The images of the invasive medical device can be displayed and overlaid with the current orientation and current position of the invasive medical device. User input can be received to initialize tracking of an orientation and a position of the invasive medical device as the invasive medical device is moved within the patient.

Abstract: A system and method is disclosed for augmenting image data of an invasive medical device using optical imaging. An optical imaging sensor, separate from the invasive medical device, can generate images of the medical device within a patient. A trained model for the invasive medical device can be trained on annotated images of the invasive medical device with orientation and distance information of the invasive medical device. An imaging computer system can apply the trained model to images of the invasive medical device within the patient to determine a current orientation and a current distance of the invasive medical device. The images of the invasive medical device as captured by the optical imaging sensor, visual orientation information representing the current orientation of the invasive medical device, and visual distance information representing the current distance of the invasive medical device within the patient can be displayed.