Abstract: Methods and apparatus to detect anomalies in video data are disclosed. An example apparatus disclosed herein generates a reconstructed feature vector corresponding to an input feature vector representative of a video segment, the reconstructed feature vector based on a transformation applied to the input feature vector and an inverse of the transformation applied to an output of the transformation, the input feature vector and the reconstructed feature vector including features associated with a plurality of dimensions including a time dimension. The disclosed example apparatus also generates an error vector based on a difference between the input feature vector and the reconstructed feature vector. The disclosed example apparatus further generates an anomaly map based on sums of elements of the error vector across at least the time dimension, the anomaly map corresponding to the video segment.

Abstract: Systems, apparatus, articles of manufacture, and methods to detect anomalies in three-dimensional (3D) images are disclosed. Example apparatus disclosed herein generate a first two-dimensional (2D) anomaly map corresponding to a first 2D image slice of a 3D image, the first 2D image slice corresponding to a first axis of the 3D image. Disclosed example apparatus also generate a second 2D anomaly map corresponding to a second 2D image slice of the 3D image, the second 2D image slice corresponding to a second axis of the 3D image. Disclosed example apparatus further generate a 3D anomaly volume based on the first 2D anomaly map and the second 2D anomaly detection, the 3D anomaly volume corresponding to the 3D image.

Abstract: Methods, systems, articles of manufacture, apparatus and methods are disclosed to generate flow and audio multi-modal output. An example apparatus includes interface circuitry, machine-readable instructions, and at least one processor circuit programmed by the machine-readable instructions to train an unsupervised image model to generate flow tensors based on a reference frame and a driver frame, the flow tensors representing at least one of rotation information or translation information. The example apparatus also includes at least one processor circuit programmed by the machine-readable instructions to train a denoising diffusion probabilistic model (DDPM) based on (a) the flow tensors, (b) audio distributions and (c) prompt signals, the trained DDPM to temporally align the flow tensors with the audio distributions.

Abstract: Techniques are disclosed for using neural network architectures to estimate predictive uncertainty measures, which quantify how much trust should be placed in the deep neural network (DNN) results. The techniques include measuring reliable uncertainty scores for a neural network, which are widely used in perception and decision-making tasks in automated driving. The uncertainty measurements are made with respect to both model uncertainty and data uncertainty, and may implement Bayesian neural networks or other types of neural networks.

Abstract: Embodiments of the present disclosure are directed toward probabilistic in-memory computing configurations and arrangements, and configurations of probabilistic bit devices (p-bits) for probabilistic in-memory computing. concept with emerging. A probabilistic in-memory computing device includes an array of p-bits, where each p-bit is disposed at or near horizontal and vertical wires. Each p-bit is a time-varying resistor that has a time-varying resistance, which follows a desired probability distribution. The time-varying resistance of each p-bit represents a weight in a weight matrix of a stochastic neural network. During operation, an input voltage is applied to the horizontal wires to control the current through each p-bit. The currents are accumulated in the vertical wires thereby performing respective multiply-and-accumulative (MAC) operations. Other embodiments may be described and/or claimed.

Abstract: Features extracted from one or more layers of a trained deep neural network (DNN) are used to detect out-of-distribution (OOD) data, such as anomalies. An OOD detection process includes transforming a feature output from a layer of the DNN from a relatively high-dimensional feature space to a lower-dimensional space, and then performing a reverse transformation back to the higher-dimensional feature space, resulting in a reconstructed feature. A feature reconstruction error is calculated based on a difference between the reconstructed feature and the original feature output from the DNN. The OOD detection process may further include calculating a score based on the feature reconstruction error and generating a visual representation of the feature reconstruction error.

Abstract: Vehicle navigation control systems in autonomous driving rely on accurate predictions of objects within the vicinity of the vehicle to appropriately control the vehicle safely through its surrounding environment. Accordingly this disclosure provides methods and devices which implement mechanisms for obtaining contextual variables of the vehicle's environment for use in determining the accuracy of predictions of objects within the vehicle's environment.

Abstract: Embodiments of the present disclosure are directed toward probabilistic in-memory computing configurations and arrangements, and configurations of probabilistic bit devices (p-bits) for probabilistic in-memory computing. concept with emerging. A probabilistic in-memory computing device includes an array of p-bits, where each p-bit is disposed at or near horizontal and vertical wires. Each p-bit is a time-varying resistor that has a time-varying resistance, which follows a desired probability distribution. The time-varying resistance of each p-bit represents a weight in a weight matrix of a stochastic neural network. During operation, an input voltage is applied to the horizontal wires to control the current through each p-bit. The currents are accumulated in the vertical wires thereby performing respective multiply-and-accumulative (MAC) operations. Other embodiments may be described and/or claimed.

Abstract: Methods, systems, and apparatus to obtain well-calibrated uncertainty in probabilistic deep neural networks are disclosed. An example apparatus includes a loss function determiner to determine a differentiable accuracy versus uncertainty loss function for a machine learning model, a training controller to train the machine learning model, the training including performing an uncertainty calibration of the machine learning model using the loss function, and a post-hoc calibrator to optimize the loss function using temperature scaling to improve the uncertainty calibration of the trained machine learning model under distributional shift.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to facilitate continuous learning. An example apparatus includes a trainer to train a first Bayesian neural network (BNN) and a second BNN, the first BNN associated with a first weight distribution and the second BNN associated with a second weight distribution. The example apparatus includes a weight determiner to determine a first sampling weight associated with the first BNN and a second sampling weight associated with the second BNN. The example apparatus includes a network sampler to sample at least one of the first weight distribution or the second weight distribution based on a pseudo-random number, the first sampling weight, and the second sampling weight. The example apparatus includes an inference controller to generate an ensemble weight distribution based on the sample.

Abstract: Techniques are disclosed for using neural network architectures to estimate predictive uncertainty measures, which quantify how much trust should be placed in the deep neural network (DNN) results. The techniques include measuring reliable uncertainty scores for a neural network, which are widely used in perception and decision-making tasks in automated driving. The uncertainty measurements are made with respect to both model uncertainty and data uncertainty, and may implement Bayesian neural networks or other types of neural networks.

Abstract: In one example a management system for an autonomous vehicle, comprises a first image sensor to collect first image data in a first geographic region proximate the autonomous vehicle and a second image sensor to collect second image data in a second geographic region proximate the first geographic region and a controller communicatively coupled to the first image sensor and the second image sensor and comprising processing circuitry to collect the first image data from the first image sensor and second image data from the second image sensor, generate a first reliability index for the first image sensor and a second reliability index for the second image sensor, and determine a correlation between the first image data and the second image data. Other examples may be described.

Abstract: Vehicle navigation control systems in autonomous driving rely on accurate predictions of objects within the vicinity of the vehicle to appropriately control the vehicle safely through its surrounding environment. Accordingly this disclosure provides methods and devices which implement mechanisms for obtaining contextual variables of the vehicle's environment for use in determining the accuracy of predictions of objects within the vehicle's environment.

Abstract: Techniques are provided for detection and location of active display regions in videos with static borders. A methodology implementing the techniques according to an embodiment includes extracting features from rows and columns of pixels of a video frame. The features are based on horizontal gradient runs (HGRs) and vertical gradient runs (VGRs). The method also includes detecting one or more static regions of the frame, based on a comparison of differences between the features of the current video frame and features extracted from a previous video frame. The method further includes detecting one or more boundaries of the static regions based on a location of a maximum value of one of the features within the static region, if the maximum value is greater than a boundary detection threshold value. Determination of the active region in the current video frame is based on exclusion of the detected static regions.

Abstract: In one example a management system for an autonomous vehicle, comprises a first image sensor to collect first image data in a first geographic region proximate the autonomous vehicle and a second image sensor to collect second image data in a second geographic region proximate the first geographic region and a controller communicatively coupled to the first image sensor and the second image sensor and comprising processing circuitry to collect the first image data from the first image sensor and second image data from the second image sensor, generate a first reliability index for the first image sensor and a second reliability index for the second image sensor, and determine a correlation between the first image data and the second image data. Other examples may be described.

Abstract: Techniques are provided for detection and location of active display regions in videos with static borders. A methodology implementing the techniques according to an embodiment includes extracting features from rows and columns of pixels of a video frame. The features are based on horizontal gradient runs (HGRs) and vertical gradient runs (VGRs). The method also includes detecting one or more static regions of the frame, based on a comparison of differences between the features of the current video frame and features extracted from a previous video frame. The method further includes detecting one or more boundaries of the static regions based on a location of a maximum value of one of the features within the static region, if the maximum value is greater than a boundary detection threshold value. Determination of the active region in the current video frame is based on exclusion of the detected static regions.

Abstract: In some embodiments, color and contrast enhancement video processing may be done in one shot instead of adjusting one of color and contrast enhancement, then the other, and then going back to the first one to readjust because of the second adjustment. In some embodiments, global lightness adjustment, local contrast enhancement, and saturation enhancement may be done at the same time and in parallel. Lightness adjustment improves visibility of details for generally dark or generally light images without changing intended lighting conditions in the original shot, and is used to enhance the range of color/saturation enhancement. Local contrast enhancement done in parallel improves visual definition of objects and textures and thus local contrast and perceived sharpness.

Abstract: Apparatus, systems and methods for adaptively reducing blocking artifacts in block-coded video are disclosed. In one implementation, a system includes processing logic at least capable of deblock filtering at least a portion of a line of video data based, at least in part, on edge information and texture information to generate at least a portion of a line of deblocked video data, and an image data output device responsive to the processing logic.

Abstract: In some embodiments, color and contrast enhancement video processing may be done in one shot instead of adjusting one of color and contrast enhancement, then the other, and then going back to the first one to readjust because of the second adjustment. In some embodiments, global lightness adjustment, local contrast enhancement, and saturation enhancement may be done at the same time and in parallel. Lightness adjustment improves visibility of details for generally dark or generally light images without changing intended lighting conditions in the original shot, and is used to enhance the range of color/saturation enhancement. Local contrast enhancement done in parallel improves visual definition of objects and textures and thus local contrast and perceived sharpness.

Abstract: In some embodiments, color and contrast enhancement video processing may be done in one shot instead of adjusting one of color and contrast enhancement, then the other, and then going back to the first one to readjust because of the second adjustment. In some embodiments, global lightness adjustment, local contrast enhancement, and saturation enhancement may be done at the same time and in parallel. Lightness adjustment improves visibility of details for generally dark or generally light images without changing intended lighting conditions in the original shot, and is used to enhance the range of color/saturation enhancement. Local contrast enhancement done in parallel improves visual definition of objects and textures and thus local contrast and perceived sharpness.