Nec Corporation

Nec Laboratories America, Inc.

Nec C Orporation

Alexandru Niculescu-Mizil

Eric Cosatto

Hans Peter Graf

Renqiang Min

Farley Lai

Felix Wu

Xavier Fontaine

Asim Kadav

Iain Melvin

Shuchu Han

Koray Kavukcuoglu

Mohammad Ehsan Abbasnejad

Diane Oyen

Abhishek Kumar

Honglu Zhou

Deep Patel

Systems and methods for optimizing multi-camera multi-entity artificial intelligence tracking systems. Visual and location information of entities from video feeds received from multiple cameras can be obtained by employing an entity detection model and re-identification model. Likelihood scores that entity detections belong to an entity track can be predicted from the visual and location information. The entity detections predicted into entity tracks can be processed by employing combinatorial optimization of the likelihood scores by identifying assumptions from the likelihood scores, entity detections, and the entity tracks, filtering the assumptions with unsatisfiable problems to obtain a filtered assumptions set, and optimizing an answer set by utilizing the filtered assumptions set and the likelihood scores to maximize an overall score and obtain optimized entity tracks. Multiple entities can be monitored by utilizing the optimized entity tracks.

Optimizing multi-camera multi-entity artificial intelligence tracking systems

Methods and systems for detecting and correcting anomalies include detecting an anomaly in a cyber-physical system, based on a classification of time series information from sensors that monitor the cyber-physical system as being anomalous. A similarity graph is determined for each of the sensors, based on the time series information. A subset of the sensors that are related to the classification is selected, based on a spectral embedding of the similarity graphs. A corrective action is performed responsive to the detected anomaly, prioritized according to the selected subset.

Sensor contribution ranking

A method for using a multi-hop reasoning framework to perform multi-step compositional long-term reasoning is presented. The method includes extracting feature maps and frame-level representations from a video stream by using a convolutional neural network (CNN), performing object representation learning and detection, linking objects through time via tracking to generate object tracks and image feature tracks, feeding the object tracks and the image feature tracks to a multi-hop transformer that hops over frames in the video stream while concurrently attending to one or more of the objects in the video stream until the multi-hop transformer arrives at a correct answer, and employing video representation learning and recognition from the objects and image context to locate a target object within the video stream.

Multi-hop transformer for spatio-temporal reasoning and localization

Systems and methods for solving queries on image data are provided. The system includes a processor device coupled to a memory device. The system includes a detector manager with a detector application programming interface (API) to allow external detectors to be inserted into the system by exposing capabilities of the external detectors and providing a predetermined way to execute the external detectors. An ontology manager exposes knowledge bases regarding ontologies to a reasoning engine. A query parser transforms a natural query into query directed acyclic graph (DAG). The system includes a reasoning engine that uses the query DAG, the ontology manager and the detector API to plan an execution list of detectors. The reasoning engine uses the query DAG, a scene representation DAG produced by the external detectors and the ontology manager to answer the natural query.

Multi-detector probabilistic reasoning for natural language queries

Methods and systems for detecting and correcting anomalies include predicting normal behavior of a monitored system based on training data that includes only sensor data collected during normal behavior of the monitored system. The predicted normal behavior is compared to recent sensor data to determine that the monitored system is behaving abnormally. A corrective action is performed responsive to the abnormal behavior to correct the abnormal behavior.

Reconstruction-based anomaly detection

A false alarm reduction system and method are provided for reducing false alarms in an automatic defect detection system. The false alarm reduction system includes a defect detection system, generating a list of image boxes marking detected potential defects in an input image. The false alarm reduction system further includes a feature extractor, transforming each of the image boxes in the list into a respective set of numerical features. The false alarm reduction system also includes a classifier, computing as a classification outcome for the each of the image boxes whether the detected potential defect is a true defect or a false alarm responsive to the respective set of numerical features for each of the image boxes.

False alarm reduction system for automatic manufacturing quality control

A method is provided for model training to detect defective products. The method includes sampling training images of a product to (i) extract image portions therefrom made of a center patch and its context and (ii) black-out the center patch. The method further includes performing unsupervised back-propagation training of a Contextual Auto-Encoder (CAE) model using (i) the image portions with the blacked-out center patch as an input and, (ii) the center patch as a target output and, (iii) an image-based loss function, to obtain a trained CAE model. The method also includes sampling positive and negative center-patch-sized portions from the training images. The method additionally includes normalizing, using the trained CAE model, the positive and negative center-patch-sized portions. The method further includes performing supervised training of a classifier model using the normalized positive and negative center-patch-sized portions to obtain a trained supervised classifier model for detecting the defective products.

Anomaly detection with predictive normalization

A false alarm reduction system is provided that includes a processor cropping each input image at randomly chosen positions to form cropped images of a same size at different scales in different contexts. The system further includes a CONDA-GMM, having a first and a second conditional deep autoencoder for respectively (i) taking each cropped image without a respective center block as input for measuring a discrepancy between a reconstructed and a target center block, and (ii) taking an entirety of cropped images with the target center block. The CONDA-GMM constructs density estimates based on reconstruction error features and low-dimensional embedding representations derived from image encodings. The processor determines an anomaly existence based on a prediction of a likelihood of the anomaly existing in a framework of a CGMM, given the context being a representation of the cropped image with the center block removed and having a discrepancy above a threshold.

Unsupervised image-based anomaly detection using multi-scale context-dependent deep autoencoding gaussian mixture model

Systems and methods for detecting and correcting defective products include capturing at least one image of a product with at least one image sensor to generate an original image of the product. An encoder encodes portions of an image extracted from the original image to generate feature space vectors. A decoder decodes the feature space vectors to reconstruct the portions of the image into reconstructed portions by predicting defect-free structural features in each of the portions according to hidden layers trained to predict defect-free products. Each of the reconstructed portions are merged into a reconstructed image of a defect-free representation of the product. The reconstructed image is communicated to a contrastor to detect anomalies indicating defects in the product.

Reconstructor and contrastor for anomaly detection

Systems and methods for diagnosing a patient condition include a medical imaging device for generating an anatomical image. A reconstructor reconstructs the anatomical image by reconstructing portions of the anatomical image to be a healthy representation of the portions and merging the portions into the anatomical image to generate a reconstructed image. A contrastor contrasts the anatomical image with the reconstructed image to generate an anomaly map indicating locations of difference between the anatomical image and the reconstructed image. An anomaly tagging device tags the locations of difference as anomalies corresponding to anatomical abnormalities in the anatomical image, and a display displays the anatomical image with tags corresponding to the anatomical abnormalities.

Reconstructor and contrastor for medical anomaly detection

Systems and methods for assigning labels to an object are provided. A set of labels is assigned to at least one object. A label filter is applied to the set of labels and to the object and labels that are irrelevant to the object are identified by the label filter. The irrelevant labels are then eliminated from further consideration and a subset of labels are created. Labels from the subset of labels that are relevant to the object are then determined and assigned to the object. The elimination of the irrelevant labels increases the speed of the labeling process. A determination of which of the objects are relevant to a user may then be performed to create user-oriented content.

Label filters for large scale multi-label classification

Methods and systems for displaying dependencies within data and illustrating differences between a plurality of data sets are disclosed. In accordance with one such method, a plurality of data sets are received for the generation of a plurality of dependency networks in accordance with a graphical modeling scheme. The method further includes receiving a selection of a value of a parameter that adjusts a number of differences between the dependency networks in accordance with the graphical modeling scheme. In addition, at least one version of the dependency networks is generated based on the selected value of the parameter. Further, the one or more versions of the dependency networks is output to permit a user to analyze distinctions between the dependency networks.

Methods and systems for dependency network analysis using a multitask learning graphical lasso objective function

Disclosed are methods and structures of Multiple Kernel learning framed as a standard binary classification problem with additional constraints that ensure the positive definiteness of the learned kernel. Advantageously, the disclosed methods and structures permit the use of binary classification technologies to develop better performing, and more scalable Multiple Kernel Learning methods that are conceptually simpler.

Growing community of inventors

Plainsboro, NJ, United States of America

Alexandru Niculescu-Mizil