Abstract: Method and apparatus for image processing. A plurality of positive text exemplars is processed to generate a set of normal features using a trained model. A plurality of negative text exemplars is processed to generate a set of anomaly features using the trained model. A query image depicting an object is received. A query image feature for the query image is generated using the trained model. An anomaly score for the query image is generated based at least in part on determining one or more distances between the query image feature and one or more normal features of the set of normal features, and determining one or more distances between the query image feature and one or more anomaly features of the set of anomaly features.

Abstract: A chatbot system includes a computer hardware system for implementing a chatbot and a hardware processor configured to initiate the following executable operations. A user prompt associated with a user and directed to the chatbot is received from a client device. An interactive voice response (IVR) tree associated with the user prompt is identified. The user prompt and the IVR tree are encoded into an encoded input. The encoded input is consumed by a trained neural model, and the neural model generates, using the encoded input, business process information. The trained neural model generates, using the business process information, an answer, and the answer is provided to the client device.

Abstract: Detecting data anomalies by receiving a query image, determining a query image viewpoint according to a trained neural radiance field model, generating a 2D reference image according to the neural radiance field model, determining a difference between the query image and the reference image, and highlighting the difference in a presentation of the query image.

Abstract: An example system includes a processor to automatically extract text and images from a document. The processor can automatically generate text bags including a number of nearest texts for each of the extracted images. The processor can then train a multi-modal model based on the automatically generated text bags using a CLIP-MIL loss that computes, for each of the extracted images, a correlation between each of the different texts in the texts bags using a CLIP feature space at each gradient step of the gradient descent-based multiple instance learning (MIL) algorithm.

Abstract: An example system includes a processor that can randomly mask tokens using different masks to generate different subsets of masked tokens. The processor can process the different sets of masked tokens via a pretrained masked auto-encoder (MAE) encoder to output intermediate representations. The processor can process the intermediate representations via a pretrained MAE decoder to output reconstructed images. The processor can further compare input image with the output reconstructed images to generate an anomaly score.

Abstract: Training a machine learning model for domain generalized operation includes processing, using computer hardware, a first plurality of images belonging to a first domain through a first network. A second plurality of images belonging to a second domain is processed using the computer hardware through a second network. A compound error metric is generated using the computer hardware from a plurality of plurality of error metrics derived from results generated from the processing of the first network and the processing of the second network. Weights of the first network are updated using the computer hardware based on the compound error metric. Weights of the second network are updated using the computer hardware using a moving average technique that is dependent on the weights of the first network as updated.

Abstract: Method and apparatus for image processing. A plurality of positive text exemplars is processed to generate a set of normal features using a trained model. A plurality of negative text exemplars is processed to generate a set of anomaly features using the trained model. A query image depicting an object is received. A query image feature for the query image is generated using the trained model. An anomaly score for the query image is generated based at least in part on determining one or more distances between the query image feature and one or more normal features of the set of normal features, and determining one or more distances between the query image feature and one or more anomaly features of the set of anomaly features.

Abstract: Detecting data anomalies by receiving a query image, determining a query image viewpoint according to a trained neural radiance field model, generating a 2D reference image according to the neural radiance field model, determining a difference between the query image and the reference image, and highlighting the difference in a presentation of the query image.

Abstract: An example system includes a processor to automatically extract text and images from a document. The processor can automatically generate text bags including a number of nearest texts for each of the extracted images. The processor can then train a multi-modal model based on the automatically generated text bags using a CLIP-MIL loss that computes, for each of the extracted images, a correlation between each of the different texts in the texts bags using a CLIP feature space at each gradient step of the gradient descent-based multiple instance learning (MIL) algorithm.

Abstract: An example system includes a processor that can randomly mask tokens using different masks to generate different subsets of masked tokens. The processor can process the different sets of masked tokens via a pretrained masked auto-encoder (MAE) encoder to output intermediate representations. The processor can process the intermediate representations via a pretrained MAE decoder to output reconstructed images. The processor can further compare input image with the output reconstructed images to generate an anomaly score.

Abstract: An example system includes a processor to receive, a randomly generated alpha-map, a pair of training images, and a pair of training texts associated with the pair of training images. The processor is to generate a blended image based on the randomly generated alpha-map and the pair of training images. The processor is to train a visual language grounding model to separate the blended image into a pair of heatmaps identifying portions of the blended image corresponding to each of the training images using a separation loss.

Abstract: An example a system includes a processor to receive a model that is a neural network and a number of training images. The processor can train the model using a bridge transform that converts the training images into a set of transformed images within a bridge domain. The model is trained using a contrastive loss to generate representations based on the transformed images.

Abstract: An example system includes a processor to receive, a randomly generated alpha-map, a pair of training images, and a pair of training texts associated with the pair of training images. The processor is to generate a blended image based on the randomly generated alpha-map and the pair of training images. The processor is to train a visual language grounding model to separate the blended image into a pair of heatmaps identifying portions of the blended image corresponding to each of the training images using a separation loss.

Abstract: A method for multiple sensor calibration and tracking, the method including identifying a non-permanent object in a first field of detection (FOD) of a sensor, wherein the sensor is one of a plurality of sensors positioned in various locations at a site, each sensor has a corresponding FOD; tracking the identified object by single-sensor tracking in the first FOD; predicting appearance of the object, and based on the predictions initiating single-sensor tracking in at least one other FOD where it is predicted that the object will appear; and outputting data captured from the tracked FODs.

Abstract: A method for multiple sensor calibration and tracking, the method including identifying a non-permanent object in a first field of detection (FOD) of a sensor, wherein the sensor is one of a plurality of sensors positioned in various locations at a site, each sensor has a corresponding FOD; tracking the identified object by single-sensor tracking in the first FOD; predicting appearance of the object, and based on the predictions initiating single-sensor tracking in at least one other FOD where it is predicted that the object will appear; and outputting data captured from the tracked FODs.

Abstract: A method of controlling output of a neural network, the method including receiving or training the neural network; wherein the neural network is an application executed on a computer that receives input from sensors and provides an output comprising predictions and/or decisions based on the input, identifying a region of the neural network that contains information of interest, finding within the identified region a specific node or group of nodes that contains specific information of interest; and applying a manipulation application external to the neural network to operate on and alter the output of the specific node or group of nodes within the neural network; wherein the altered output of the specific node affects the output of the neural network without altering the input of the neural network.