Abstract: Computer vision systems and methods for machine learning using image hallucinations are provided. The system generates image hallucinations that are subsequently used to train a deep neural network to match image patches. In this scenario, the synthesized changes serve in the learning of feature-embedding that captures how a patch of an image might look like from a different vantage point. In addition, a curricular learning framework is provided which is used to automatically train the neural network to progressively learn more invariant representations.

Abstract: Machine learning systems and methods for evaluating sampling bias in deep active classification are provided. The system generates an acquisition function based on an uncertainty based query strategy. The system utilizes the Least Confidence and the Entropy uncertainty based query strategies. The system acquires at least one data sample from the input data based on the acquisition function. The input data can include, but is not limited to, large datasets widely utilized for text classification. The system labels the data sample via an oracle and generates a training dataset with the labeled data sample. The system generates a sequence of training datasets by sampling b queries from the input data, each of size K. The system evaluates an efficiency and bias of sample datasets obtained by different query strategies. The system also trains a network with the generated training dataset(s).

Abstract: Computer vision systems and methods for localizing image forgery are provided. The system generates a constrained convolution via a plurality of learned rich filters. The system trains a convolutional neural network with the constrained convolution and a plurality of images of a dataset to learn a low level representation of each image among the plurality of images. The low level representation is indicative of a statistical signature of at least one source camera model of each image. The system can determine a splicing manipulation localization by the trained convolutional neural network.

Abstract: A system for improved localization of image forgery. The system generates a variational information bottleneck objective function and works with input image patches to implement an encoder-decoder architecture. The encoder-decoder architecture controls an information flow between the input image patches and a representation layer. The system utilizes information bottleneck to learn useful residual noise patterns and ignore semantic content present in each input image patch. The system trains a neural network to learn a representation indicative of a statistical fingerprint of a source camera model from each input image patch while excluding semantic content thereof. The system can determine a splicing manipulation localization by the trained neural network.

Abstract: A system for generating a permutation invariant representation of a graph is provided. The system assembles a dataset including a graph having a plurality of nodes and a number of features per node and generates a first matrix and a second matrix based on the plurality of nodes and the number of features per node. The system determines a set of node embeddings by a graph convolutional network based on the first matrix and the second matrix and determines a permutation invariant representation of the graph by a permutation invariant mapping based on the set of node embeddings. The system determines a universal attribute of the graph by a fully connected network based on the permutation invariant representation of the graph.

Abstract: Systems and methods for machine learning of voice and other attributes are provided. The system receives input data, isolates predetermined sounds from isolated speech of a speaker of interest, summarizes the features to generate variables that describe the speaker, and generates a predictive model for detecting a desired feature of a person Also provided are systems and methods for detecting one or more attributes of a speaker based on analysis of audio samples or other types of digitally-stored information (e.g, videos, photos, etc.).

Abstract: Systems and methods for machine learning of voice and other attributes are provided. The system receives input data, isolates predetermined sounds from isolated speech of a speaker of interest, summarizes the features to generate variables that describe the speaker, and generates a predictive model for detecting a desired feature of a person Also provided are systems and methods for detecting one or more attributes of a speaker based on analysis of audio samples or other types of digitally-stored information (e.g, videos, photos, etc.).

Abstract: Computer vision systems and methods for optimized computer vision using deep neural networks and Lipschitz analysis are provided. The system receives signals or data related to visual imagery, such as data from a camera, and feed-forwards the signals/data through the multiple layers of a convolutional neural network (CNN). At one or more layers of the CNN, the system determines at least one Bessel bound of that layer. The system then determines a Lipschitz bound based on the one or more Bessel bounds. The system then applies the Lipschitz bound to the signals. Once the Lipschitz bound is applied, the system can feed-forward the signals to other processes of the layer or to a further layer.

Abstract: Computer vision systems and methods for machine learning using a set packing framework are provided. A minimum weight set packing (“MWSP”) framework is parameterized by a set of possible hypotheses, each of which is associated with a real valued cost that describes the sensibility of the belief that the members of the hypothesis correspond to a common cause. Using MWSP, the system then selects the lowest total cost set of hypotheses, such that no two selected hypotheses share a common observation. Observations that are not included in any selected hypothesis, define the set of false observations can be thought of as false observations/noise. The system can be utilized to support one or more trained computer models in performing computer vision on input data in order to generate output data.

Abstract: Computer vision systems and methods for optimized computer vision using deep neural networks and Lipschitz analysis are provided. The system receives signals or data related to visual imagery, such as data from a camera, and feed-forwards the signals/data through the multiple layers of a convolutional neural network (CNN). At one or more layers of the CNN, the system determines at least one Bessel bound of that layer. The system then determines a Lipschitz bound based on the one or more Bessel bounds. The system then applies the Lipschitz bound to the signals. Once the Lipschitz bound is applied, the system can feed-forward the signals to other processes of the layer or to a further layer.

Abstract: Systems and methods for unsupervised representation learning by sorting sequences are provided. An unsupervised representation learning approach is provided which uses videos without semantic labels. The temporal coherence as a supervisory signal can be leveraged by formulating representation learning as a sequence sorting task. A plurality of temporally shuffled frames (i.e., in non-chronological order) can be used as inputs and a convolutional neural network can be trained to sort the shuffled sequences and to facilitate machine learning of features by the convolutional neural network. Features are extracted from all frame pairs and aggregated to predict the correct sequence order. As sorting shuffled image sequence requires an understanding of the statistical temporal structure of images, training with such a proxy task can allow a computer to learn rich and generalizable visual representations from digital images.

Abstract: Computer vision systems and methods for machine learning using image hallucinations are provided. The system generates image hallucinations that are subsequently used to train a deep neural network to match image patches. In this scenario, the synthesized changes serve in the learning of feature-embedding that captures how a patch of an image might look like from a different vantage point. In addition, a curricular learning framework is provided which is used to automatically train the neural network to progressively learn more invariant representations.

Abstract: A method of evaluating the driving behavior in a vehicle. The method includes determining values of a plurality of parameters of the operation of a first vehicle in a first road segment, determining values of the plurality of parameters for one or more second vehicles in a second road segment having similar properties to those of the first road segment, comparing the determined values of the first vehicle and the one or more second vehicles and providing an evaluation of the driving behavior of the first vehicle, responsive to the comparison.

Abstract: A method of evaluating the driving behavior in a vehicle. The method includes determining values of a plurality of parameters of the operation of a first vehicle in a first road segment, determining values of the plurality of parameters for one or more second vehicles in a second road segment having similar properties to those of the first road segment, comparing the determined values of the first vehicle and the one or more second vehicles and providing an evaluation of the driving behavior of the first vehicle, responsive to the comparison.

Abstract: Systems and methods for detection and localization of image and document forgery. The method can include the step of receiving a dataset having a plurality of authentic images and a plurality of manipulated images. The method can also include the step of benchmarking a plurality of image forgery algorithms using the dataset. The method can further include the step of generating a plurality of receiver operating characteristic (ROC) curves for each of the plurality of image forgery algorithms. The method also includes the step of calculating a plurality of area under curve metrics for each of the plurality of ROC curves. The method further includes the step of training a neural network for image forgery based on the plurality of area under curve metrics.

Abstract: Systems and methods for optical character resolution (OCR) at low resolutions are provided. The system receives a dataset and extracts document images from the dataset. The system then segments and extracts a plurality of text lines from the document images. The system then processes the plurality of text lines using a Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) module to perform line OCR. Finally, the system generates a plurality of text strings corresponding to the plurality of text lines.

Abstract: A method of evaluating the driving behavior in a vehicle. The method includes determining values of a plurality of parameters of the operation of a first vehicle in a first road segment, determining values of the plurality of parameters for one or more second vehicles in a second road segment having similar properties to those of the first road segment, comparing the determined values of the first vehicle and the one or more second vehicles and providing an evaluation of the driving behavior of the first vehicle, responsive to the comparison.

Abstract: A method of evaluating the driving behavior in a vehicle. The method includes determining values of a plurality of parameters of the operation of a first vehicle in a first road segment, determining values of the plurality of parameters for one or more second vehicles in a second road segment having similar properties to those of the first road segment, comparing the determined values of the first vehicle and the one or more second vehicles and providing an evaluation of the driving behavior of the first vehicle, responsive to the comparison.

Abstract: Systems and methods for computerized fraud detection using machine learning and network analysis are provided. The system includes a fraud detection computer system that executes a machine learning, network detection engine/module for detecting and visualizing insurance fraud using network analysis techniques. The system electronically obtains raw insurance claims data from a data source such as an insurance claims database, resolves entities and events that exist in the raw claims data, and automatically detects and identify relationships between such entities and events using machine learning and network analysis, thereby creating one or more networks for visualization. The networks are then scored, and the entire network visualization, including associated scores, are displayed to the user in a convenient, easy-to-navigate fraud analytics user interface on the user's local computer system.

Abstract: A system and method for conducting on-site asset investigations for insurance underwriting are provided. The system allows a user to conduct an investigation into an asset to be insured while at the asset's location, using a mobile software application executing on a mobile computing device such as smart phone, tablet computer, etc. The mobile application allows the user to acquire information relating to the asset as well as to take photographs of the vehicle or other personal property to be insured, using the mobile computing device. The acquired information is transmitted to an underwriting computer server in communication with the mobile device, which processes the information and generates an underwriting report for the asset.