Abstract: Real-time modification of audio of humans allows for the audio to be modified so that an expression of a subject human may be changed. Customer service agents may have more successful interactions with customers if they provide vocalization attribute in their speech that are appropriate, such as to provide a particular emotional state. By determining an appropriate vocalization attribute, and any deviation from a customer service agent's current vocalization attribute, a modification to the audio of the customer service agent's speech may be determined and applied. As a result, agents may not have a vocalization attribute that is best suited to successfully resolve a purpose of the interaction, altered to have the customer be presented with the customer service agent's speech having the best-suited vocalization attribute.

Abstract: A medical image display apparatus according to an embodiment includes processing circuitry. The processing circuitry is configured to obtain an image data set of volume data or image data at multiple points in time. The processing circuitry is configured to specify an image of interest indicating an observation cross-sectional plane from the image data set. The processing circuitry is configured to specify a region of interest on the basis of the image data set. The processing circuitry is configured to cause the image of interest and information about the region of interest to be displayed.

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: 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: System and methods for compressing image-to-image models. Generative Adversarial Networks (GANs) have achieved success in generating high-fidelity images. An image compression system and method adds a novel variant to class-dependent parameters (CLADE), referred to as CLADE-Avg, which recovers the image quality without introducing extra computational cost. An extra layer of average smoothing is performed between the parameter and normalization layers. Compared to CLADE, this image compression system and method smooths abrupt boundaries, and introduces more possible values for the scaling and shift. In addition, the kernel size for the average smoothing can be selected as a hyperparameter, such as a 3×3 kernel size. This method does not introduce extra multiplications but only addition, and thus does not introduce much computational overhead, as the division can be absorbed into the parameters after training.

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: An image processing device includes: a first processor configured to perform image processing on an inputted image, the image processing including diagnostic process; a second processor configured to perform selection processing to select and transmit a portion of the inputted image to an external image processing apparatus connected to an external network; and an interface configured to receive a processing result of the diagnostic process by the external image processing apparatus.

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: 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: A method for detecting a cue (e.g., a visual cue or a visual cue combined with an audible cue) occurring together in an input video includes: presenting a user interface to record an example video of a user performing an act including the cue; determining a part of the example video where the cue occurs; applying a feature of the part to a neural network to generate a positive embedding; dividing the input video into a plurality of chunks and applying a feature of each chunk to the neural network to generate a plurality of negative embeddings; applying a feature of a given one of the chunks to the neural network to output a query embedding; and determining whether the cue occurs in the input video from the query embedding, the positive embedding, and the negative embeddings.

Abstract: A video processing method, an electronic device and a storage medium are provided, and relate to the field of artificial intelligence, and particularly relates to the fields of deep learning, model training, knowledge mapping, video processing and the like. The method includes: acquiring a plurality of first video frames, and performing fine-grained splitting on the plurality of first video frames to obtain a plurality of second video frames; performing feature encoding on the plurality of second video frames according to multi-mode information related to the plurality of second video frames, to obtain feature fusion information for characterizing fusion of the multi-mode information; and performing similarity matching on the plurality of second video frames according to the feature fusion information, and obtaining a target video according to a result of the similarity matching.

Abstract: The present invention discloses a medical image project management platform comprising a project management module and a radiomic feature extracting module. The project management module comprises a multi-module management interface and a labeling unit. An image is input by the multi-module management interface and received by the labeling unit. A first labeled image and a second labeled image are produced thereafter. The radiomic feature extracting module comprises an analysis unit and a feature extracting module. The analysis unit analyzes the first labeled image and gives the first labeled image a first labeling unit. The analysis unit analyzes the second labeled image and gives the second labeled image a second labeling unit. The radiomic feature extracting unit receives the first and the second labeling units and proceeds radiomic computation to output a radiomic feature.

Abstract: In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.

Abstract: A computer-implemented method of processing target footage of a target human face includes training an encoder-decoder network comprising an encoder network, a first decoder network, and a second decoder network. The training includes training a first path through the encoder-decoder network including the encoder network and the first decoder network to reconstruct the target footage of the target human face, and training a second path through the encoder-decoder network including the encoder network and the second decoder network to process renders of a synthetic face model exhibiting a range of poses and expressions to determine parameter values for the synthetic face model corresponding to the range of poses and expressions. The method includes processing, using a trained network path comprising or trained using the encoder network and comprising the first decoder network, source data representing the synthetic face model exhibiting a source sequence of expressions, to generate output video data.

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.

Abstract: Dispatch-aiding communications between computing devices of a responder and a dispatch unit include a computing device of the responder determining that an event occurred, automatically sending an indication of the event to a computing device of the dispatch unit, receiving a request for information from the computing device of the dispatch unit, obtaining the information requested by the computing device of the dispatch unit, and sending the information requested by the computing device of the dispatch unit to the computing device of the dispatch unit. The computing device of the dispatch unit sends the request for information to the computing device of the responder in response to receiving the indication of the event.

Abstract: Systems and methods may display and/or provide analysis of a number of selected images of a patients gastrointestinal tract collected in-vivo by a swallowable capsule. Images may be displayed for review (e.g., as a study) and/or for further analysis by a user. A subset of images representing the stream of images and automatically selected according to a first selection method may be displayed. On user input, additional images corresponding to a currently displayed image may be displayed, where the additional images are automatically selected according to a second selection method. The second selection method may be based on a relation between images of the stream of in-vivo images and the currently displayed image.

Abstract: Various embodiments of the present disclosure are directed to a salient medical imaging controller (80) employing an artificial intelligence engine (40) and a graphical user interface (70). In operation, the artificial intelligence engine (40) includes one or more machine learning models (42) trained to render a feature assessment of a medical image. The graphical user interface (70) provides a user interaction with the artificial intelligence engine (40) to manipulate a salient visualization of the feature assessment of the medical image by the machine learning model(s) (42).

Abstract: A system and a method for detecting animals in a region of interest are disclosed. An image that captures a scene in the region of interest is received. The image is fed to an animal detection model to produce a group of probability maps for a group of key points and a group of affinity field maps for a group of key point sets. One or more connection graphs are determined based on the group of probability maps and the group of affinity field maps. Each connection graph outlines a presence of an animal in the image. One or more animals present in the region of interest are detected based on the one or more connection graphs.

Abstract: Embodiments disclose a method and system for a scene-aware audio-video representation of a scene. The scene-aware audio video representation corresponds to a graph of nodes connected by edges. A node in the graph is indicative of the video features of an object in the scene. An edge in the graph connecting two nodes indicates an interaction of the corresponding two objects in the scene. In the graph, at least one or more edges are associated with audio features of a sound generated by the interaction of the corresponding two objects. The graph of the audio-video representation of the scene may be used to perform a variety of different tasks. Examples of the tasks include one or a combination of an action recognition, an anomaly detection, a sound localization and enhancement, a noisy-background sound removal, and a system control.