In accordance with one embodiment of the present disclosure, method includes obtaining multi-level environment data corresponding to a plurality of driving environment levels, encoding the multi-level environment data at each level, extracting features from the multi-level environment data at each encoded level, fusing the extracted features from each encoded level with a spatial-temporal attention framework to generate a fused information embedding, and decoding the fused information embedding to predict driving environment information at one or more driving environment levels.

In one embodiment, a set of feature vectors can be derived from any biometric data, and then using a deep neural network (DNN) on those one-way homomorphic encryptions (i.e., each biometrics' feature vector) can determine matches or execute searches on encrypted data. Each biometrics' feature vector can then be stored and/or used in conjunction with respective classifications, for use in subsequent comparisons without fear of compromising the original biometric data. In various embodiments, the original biometric data is discarded responsive to generating the encrypted values. In another embodiment, the homomorphic encryption enables computations and comparisons on cypher text without decryption. This improves security over conventional approaches. Searching biometrics in the clear on any system, represents a significant security vulnerability. In various examples described herein, only the one-way encrypted biometric data is available on a given device. Various embodiments restrict execution to occur on encrypted biometrics for any matching or searching.

A processing system including at least one processor may obtain a personal identifier comprising a plurality of characters and generate a first embedding of the personal identifier in accordance with an embedding model. The processing system may then identify one or more embeddings of other personal identifiers that are within a threshold distance of the first embedding and generate an alert in response to the identifying of the one or more embeddings of the other personal identifiers that are within the threshold distance.

Techniques for improving image processing related to item deliveries are described. In an example, a computer system receives an image showing a drop-off of an item, the item associated with a delivery to a delivery location. The computer system inputs the image to a first artificial intelligence (AI) model. The computer system receives first data comprising an indication of whether the drop-off is correct from the first AI model. The computer system causes a presentation of the indication at a device associated with the delivery of the item to the delivery location.

Methods and apparatus for predicting an association between input data in a first modality and data in a second modality using a statistical model trained to represent interactions between data having a plurality of modalities including the first modality and the second modality, the statistical model comprising a plurality of encoders and decoders, each of which is trained to process data for one of the plurality of modalities, and a joint-modality representation coupling the plurality of encoders and decoders. The method comprises selecting, based on the first modality and the second modality, an encoder/decoder pair or a pair of encoders, from among the plurality of encoders and decoders, and processing the input data with the joint-modality representation and the selected encoder/decoder pair or pair of encoders to predict the association between the input data and the data in the second modality.

A framework is provided for associating dense images with topics. The framework is trained utilizing images, each having multiple regions, multiple visual characteristics and multiple keyword tags associated therewith. For each region of each image, visual features are computed from the visual characteristics utilizing a convolutional neural network, and an image feature vector is generated from the visual features. The keyword tags are utilized to generate a weighted word vector for each image by calculating a weighted average of word vector representations representing keyword tags associated with the image. The image feature vector and the weighted word vector are aligned in a common embedding space and a heat map is computed for the image. Once trained, the framework can be utilized to automatically tag images and rank the relevance of images with respect to queried keywords based upon associated heat maps.

Systems, methods, and non-transitory computer-readable media are disclosed for extracting material properties from a single digital image portraying one or more materials by utilizing a neural network encoder, a neural network material classifier, and one or more neural network material property decoders. In particular, in one or more embodiments, the disclosed systems and methods train the neural network encoder, the neural network material classifier, and one or more neural network material property decoders to accurately extract material properties from a single digital image portraying one or more materials. Furthermore, in one or more embodiments, the disclosed systems and methods train and utilize a rendering layer to generate model images from the extracted material properties.

Methods, systems, and computer program products for enabling distance-based algorithms on data encrypted using a 2DNF homomorphic encryption scheme with inefficient decryption are provided herein. A computer-implemented method includes generating multiple versions of a data point, wherein each of the multiple versions of the data point comprises a distinct value corresponding to a distinct Euclidean space; encrypting each of the multiple versions of the data point; storing the multiple encrypted versions of the data point across multiple databases; and executing one or more distance-based algorithms on the multiple encrypted versions of the data point by using a finite decryption table across the multiple databases, wherein the finite decryption table stores a set of plaintext-ciphertext mappings between (i) multiple plaintext values and (ii) multiple encrypted ciphertext values corresponding to the multiple plaintext values.

Methods and apparatus for predicting an association between input data in a first modality and data in a second modality using a statistical model trained to represent interactions between data having a plurality of modalities including the first modality and the second modality, the statistical model comprising a plurality of encoders and decoders, each of which is trained to process data for one of the plurality of modalities, and a joint-modality representation coupling the plurality of encoders and decoders. The method comprises selecting, based on the first modality and the second modality, an encoder/decoder pair or a pair of encoders, from among the plurality of encoders and decoders, and processing the input data with the joint-modality representation and the selected encoder/decoder pair or pair of encoders to predict the association between the input data and the data in the second modality.

The present disclosure relates generally to machine learning. More particularly, the present disclosure relates to systems and methods that regularize neural networks by decorrelating neurons or other parameters of the neural networks during training of the neural networks promoting these parameter to innovate over one another.