Abstract: A method and system are arranged for fact checking electronically posted claims. The system includes an input/output device for inputting a textual complex claim as a natural language statement with a combination of two or more facts and outputting an indication that the textual complex claim is true or false. A processor connected to the input/output device generates, by a program generation module, a reasoning program for the input complex claim as a sequence of reasoning steps, where each step directs to a function in a set of sub-task functions. The processor generates, by a program execution module, each step in the reasoning program to a respective sub-task function and executes the respective sub-task function in order to provide the outputted indication.

Abstract: An automotive control system and method, includes a radar sensor, attached to a vehicle body panel, for receiving radar signals having a frequency, and processing circuitry configured with neural network encoders for encoding multiple frames of Angle-Doppler (AD), Range-Doppler (RD), and Range-Angle (RA) feature maps from the radar signals, an adaptive-directional attention block to sample rows and columns and apply self attention after each sampling instance, and a RD decoder and a RA decoder that generate RD and RA probability maps. Each map is a colorized feature map, with each pixel color representing a predicted class label for objects. An object detection component identifies the objects, and an object distance analysis component predicts a distance to the identified objects. An object velocity component predicts a velocity of the identified objects.

Abstract: A wireless communication network method and system that includes a central server, cellular base stations, edge computing devices, and client devices. The client devices send uplink pilot sequences, which are collected and aggregated by the base stations. The base stations then relay this aggregated pilot data to the central server. The central server deploys network weights for a global deep learning neural network model to the base stations for incorporation into respective local deep learning models, trained to predict optimal beamforming vectors, to the base stations for incorporation into respective local deep learning model. During training the central server integrates adaptive noise into weights received for each of the local deep learning models.

Abstract: An object detection system that can detect drone objects with high accuracy and low computational complexity, includes a camera for capturing an image, processing circuitry, and a display device. The processing circuitry is configured to input the image. The processing circuitry includes a machine learning network, having a feature extraction backbone with addition-based filters that use addition as a similarity measure to extract features of the image, a path to add low-level features to high-level features, and a single shot detector (SSD) network that outputs an image with possible classes of an object in the image based on the extracted features. The display device displays the image with a label for the detected object based on a selected class. The SSD network backbone can be configured with a SWIN transformer to extract features. The SWIN transformer includes a shifted window self-attention and allows training the SSD model with dynamic image sizes.

Abstract: A video system and method for person search includes video cameras for capturing video images, a display device, and a computer system. The computer system including a deep learning network to determine person images, from among the video images, matching a target query person. The deep learning network having a person detection branch, a person re-identification branch, and an attention-aware relation mixer connected to the person detection branch and to the person re-identification branch. The attention-aware relation mixer including a relation mixer having a spatial and channel mixer that performs spatial attention followed by spatial mixing (tokenized multi-layered perceptron) and channel attention followed by channel mixing (channel multi-layered perceptron), and a joint spatio-channel attention layer that utilizes 3D attention weights to modulate 3D spatio-channel region of interest features and aggregate the features with output of the relation mixer.

Abstract: A scholar system and method transforms search of academic knowledge. The system uses a combination of face recognition and language generation technology to effortlessly capture scholars in photos to give rich summaries of profiles of their work. The system also offers an interactive chat element for users to get more insights about a scholar, reducing online search efforts. The system ensures privacy and ethical compliance to rules and regulations.

Abstract: A safety-critical control system and method with train-time calibration of object detection. A controller calibrates prediction by a deep neural network. The train-time calibration includes a multi-class confidence calibration, and a bounding box localization calibration. The controller outputs a calibrated image with the object bounding box, the corresponding class label, and a respective confidence score. The confidence score is a probability associated with the predicted class label. The multi-class confidence calibration is determined as a difference between a fused mean confidence and a certainty with accuracy. The fused mean confidence is between a mean logits-based class-wise confidence and class wise certainty. The controller determines the localization calibration by determining a deviation between a predicted mean bounding box overlap and a predictive certainty of the bounding box.

Abstract: A system and method of fine-grained image category discovery with few human annotations includes a camera and a trained machine learning model, which predicts a label for an object in a captured image and outputs the predicted label. The machine learning model is trained by contrastive affinity learning, including retrieving images having an object, a warm-up stage in which semi-supervised contrastive learning is performed based on projected features of a class token and an ensembled prompt, respectively. In a contrastive affinity learning stage, a student model and an exponentially moving averaged teacher model are forwarded with different augmented views of the retrieved images. Teacher embeddings are enqueued into a token-specific memory. A semi-supervised contrastive loss is computed on a current batch and a contrastive affinity learning loss for student embeddings and the teacher embeddings with pseudo-labels from a affinity graph dynamically generated by semi-supervised affinity generation.

Abstract: An architecture and operational identify management and trust method and system includes a flexible digital wallet application, an interactive virtual environment within the metaverse, and a secure backend infrastructure on a blockchain network. By integrating self-sovereign identity and blockchain technology, this extended framework aims to establish a secure and user-centric decentralized metaverse.

Abstract: A method, apparatus, and system for detecting DeepFake videos, includes an input device for inputting a potential DeepFake video, the input device inputs a sequence of video frames of the video, and processing circuitry. The processing circuitry detects faces frame by frame in the video to obtain consecutive face images, creates UV texture maps from the face images, inputs both face images and corresponding UV texture maps, extracts image feature maps, by a convolution neural network (CNN) backbone, from the input face images and corresponding UV texture maps and forms an input data structure, receives the input data structure, by a video transformer model that includes multiple encoders, and computes, by the video transformer model, a classification of the video as being Real or Fake. A display device plays back the potential DeepFake video and an indication that the video is Real or Fake.

Abstract: A system and method of training a deep neural network for object detection in an object detection system. The object detection system including a camera and a controller including the DNN. The method including capturing an image by the camera, receiving the image, predicting, using the DNN, a bounding box and corresponding class label, evaluating the prediction with a total loss function including an object detection loss function, a box regression loss function, and a calibration loss function that takes into account precision and confidence. The method outputs a calibrated image with the object bounding box, the corresponding label, and a respective confidence score, in which the confidence score is a probability associated with the predicted class label.

Abstract: A system and method of open-world semi-supervised satellite object detection involves a machine learning engine configured with a training component and an inference component. The method of object detection detects objects in satellite imagery represents a solution for difficult challenges of arbitrary orientations, wide variation in object sizes, large number of densely packed objects, and highly complex background. A transformer network detects unknown objects in the satellite image. The transformer network includes a rotation-aware pyramidal pseudo-labeling operation that captures scale-specific pyramidal features at oriented box regions for pseudo-labeling unknown objects in the satellite image. A semi-supervised learning pipeline learns a new set of object classes to be detected. A prediction head outputs the satellite image annotated with a predicted object class for an unknown object.

Abstract: A system for 3D medical image segmentation includes a medical imaging device for obtaining a plurality of 2D images forming a volumetric image, processing circuitry, and a display. The processing circuitry is configured with a first stage to divide the volumetric image into 3D image patches, a hierarchical encoder-decoder structure in which resolution of features of the 3D image patches is decreased by a factor of two in each of a plurality of stages of the encoder, an encoder output connected to the decoder via skip connections, and a convolutional block to produce a voxel-wise final segmentation mask. The encoder includes a plurality of efficient paired attention blocks each with a spatial attention branch and a channel attention branch that learn respective spatial and channel attention feature maps. The display displays the final segmentation mask.

Abstract: A system, method and computer readable medium for emergency health response, including sensors for measuring health conditions of a user, a local machine learning device to predict abnormalities in health status of the user based on the measurements, a communications device for transmitting an emergency alert message to emergency response providers that are within range of the communications device, and for receiving response messages from emergency response providers that are available to provide emergency treatment. A health condition controller selecting a provider. When the provider is a hospital, the subject vehicle will set its destination to the hospital and will transmit health status information of the user to the provider. When the provider is an emergency response vehicle, the subject vehicle will communicate coordinates as a meeting destination for meeting the provider response vehicle and will transmit health status information of the user to the provider response vehicle.

Abstract: An apparatus, computer readable storage medium and method of generating a diverse set of images from few-shot images, includes a parameter input receiving values for control parameters to control an extent to which each reference image impacts a newly generated image. The apparatus involves an image generation deep learning network for generating an image for each of the values for the control parameters. The deep learning network has an encoder, a transformer-based fusion block, and a decoder. The transformer-based fusion block includes a mapping network that computes meta-weights from features extracted from the reference images and the control parameters, and a cross-attention block to generate modulation weights based on the meta-weights. An output displays high-quality and diverse images generated based on the values for the control parameter.

Abstract: A method and system for multi-modal prompt learning of vision-language models. Encodings of image-text pairs can be combined with image prompts and text prompts before being input into an image encoder and text encoder of a vision-language model respectively. The image prompt can be generated using the text prompt using a vision-language coupling function to encourage synergy between the two prompts. The combination of encodings and prompts can be fed through the transformer layers of the encoders, and the output of each layer can be combined with a new prompt before entering the next layer, up until a specific depth. The subsequent transformer layers can process the output and generate a final representation for the image and text which can then be used for downstream tasks.

Abstract: A deep learning training system and method, includes an imaging system for capturing medical images, a machine learning engine, and display. The machine learning engine selects a small-scale of images from a training dataset, generates global views by randomly selecting regions in one image, generates local views by randomly selecting regions covering less than a majority of the image, receives the generated global views as a first sequence of non-overlapping image patches, receives the generated global views and the generated local views as a second sequence of non-overlapping image patches, trains parameters in a student-teacher network to predict a class of objects by self-supervised view prediction using the first sequence and the second sequence. The teacher parameters are updated via exponential moving average of the student network parameters. The parameters in the teacher network are transferred to the vision transformer, and the vision transformer is trained by supervised learning.

Abstract: An apparatus and method for a machine learning engine for domain generalization which trains a vision transformer neural network using a training dataset including at least two domains for diagnosis of a medical condition. Image patches and class tokens are processed through a sequence of feature extraction transformer blocks to obtain a predicted class token. In parallel, intermediate class tokens are extracted as outputs of each of the feature extraction transformer blocks, where each transformer block is a sub-model. One sub-model is randomly sampled from the sub-models to obtain a sampled intermediate class token. The intermediate class token is used to make a sub-model prediction. The vision transformer neural network is optimized based on a difference between the predicted class token and the sub-model prediction. Inferencing is performed for a target medical image in a target domain that is different from the at least two domains.

Abstract: An object detection system and method in which a machine learning engine is configured with a region-based knowledge distillation stage that generates region embeddings from a training image having bounding boxes. A linear layer learns a region-level vision-language mapping for projecting feature embeddings from the training image to a common feature space shared by text embeddings to obtain the region embeddings. An image-level supervision stage generates pseudo-box labels for a classification training image and region embeddings from the training image having bounding boxes and corresponding class labels and the classification training image having an image-level label as input. Pseudo-box labels are determined on the classification training image as an image-level vision-language mapping. A weight transfer function conditions the image-level vision-language mapping on the learned region-level vision-language mapping.

Abstract: An edge computing system, computer readable storage medium and method for object detection, including processing circuitry. The processing circuitry is configured with a hybrid CNN and vision transformer backbone network in an object detection deep learning network. The backbone network receives an image, and includes a first convolutional encoder to extract local features from feature maps of the image, a second stage having consecutive second convolutional encoders, a positional encoding layer, split depth-wise transpose attention (SDTA) encoders, consecutive convolutional encoders, a third stage and a fourth stage SDTA encoder. Each of the SDTA encoders perform multi-headed self-attention by applying a dot product operation across channel dimensions in order to compute cross-covariance across channels to generate attention feature maps.