Provided is a method of verifying an authenticity of declaration information. The method includes: acquiring a machine-detected radiation image obtained by scanning a container loaded with an article; acquiring a declaration information for declaring the article in the container; performing an identification on an image information of the article in the machine-detected radiation image to obtain an image feature corresponding to the machine-detected radiation image; performing an identification on a text information of the article in the declaration information to obtain a text feature corresponding to the declaration information; screening a declaration category of the article in the container by taking the image feature as an input information and the text feature as an external introduction feature; and determining that the declaration information is in doubt when a declaration category of at least one article in the container does not belong to a declaration category in the declaration information.

A method for identifying a component part includes receiving a digital image of an object and textual information about the object and accessing images of component parts and textual information about the component parts. The method further includes applying the digital image to a first classifier trained on the images of the component parts to classify the object as a first of the component parts and applying the textual information about the object to a second classifier trained on the textual information about the component parts to recognize the textual information as information about the first of the component parts or a second of the component parts. The method further includes identifying the object as a component part that is the first of the component parts or the second of the component parts and accessing a data record with information about the component part.

The present teaching relates to system, method, medium for in-situ perception in an autonomous driving vehicle. A plurality of types of sensor data acquired continuously by a plurality of types of sensors deployed on the vehicle are first received, where the plurality of types of sensor data provide information about surrounding of the vehicle. Based on at least one model, one or more items are tracked from a first of the plurality of types of sensor data acquired by one or more of a first type of the plurality of types of sensors, wherein the one or more items appear in the surrounding of the vehicle. At least some of the one or more items are then automatically labeled on-the-fly via either cross modality validation or cross temporal validation of the one or more items and are used to locally adapt, on-the-fly, the at least one model in the vehicle.

An intelligent automatic license plate recognition (IALPR) system implements technical solutions that improve the accuracy of automatic license plate recognition. The IALPR analyzes an image of a vehicle proximate to a toll collection point using optical character recognition (OCR), and determines candidate license plate identifications based, at least in part, on the corresponding OCR confidence level. The IALPR can also perform fingerprinting for candidate license plate images and matching analysis with a knowledge base, resulting in additional confidence levels. The IALPR can also perform behavioral analysis on the candidate license plate identifications, including trip context analysis, historical behavioral analysis, or other analytics. The IALPR can generate an overall confidence level for the candidate license plate identifications responsive to the OCR and vehicle fingerprint confidence levels and the behavioral analysis. This enhanced analysis helps the IALPR reduce the number of incorrect license plate identifications and reduce the need for human review.

An object recognition device 4 includes: a data reception unit 5 that creates observation data of respective sensors 1, 2 in accordance with sensor's detection data of an object in the surroundings of a host vehicle; an association processing unit 6 which, based on an association reference value, generates association data denoting a correspondence between the observation data and object data of a previous process cycle; and an updating processing unit 7 which, based on the association data, updates a state vector included in the object data of the previous process cycle, and updates the object data by including latest association data being the observation data having corresponded to the object data most recently, wherein the association processing unit 6 generates the association reference value using preferentially the latest association data of the same sensor as that of the observation data of a current process cycle.

A method and electronic device for recognizing a product are provided. The method includes obtaining first feature information and second feature information from an image related to a product, obtaining fusion feature information based on the first feature information and the second feature information by using a main encoder model that reflects a correlation between feature information of different modalities, matching the fusion feature information against a database of the product, and providing information about the product, based on a result of the matching.

Systems and methods for multimodal classification include a plurality of expert modules, each expert module configured to receive data corresponding to one of a plurality of input modalities and extract associated features, a plurality of class prediction modules, each class prediction module configured to receive extracted features from a corresponding one of the expert modules and predict an associated class, a gate expert configured to receive the extracted features from the plurality of expert modules and output a set of weights for the input modalities, and a fusion module configured to generate a weighted prediction based on the class predictions and the set of weights. Various embodiments include one or more of an image expert, a video expert, an audio expert, class prediction modules, a gate expert, and a co-learning framework.

Various embodiments described herein relate to techniques for forecasting with state transitions and confidence factors. In this regard, a system is configured to segment data associated with one or more assets to determine a set of classifications for one or more attributes related to the one or more assets. The system is also configured to generate a state machine associated with a Markov chain model based on the set of classifications for the data. Furthermore, the system is configured to perform a machine learning process associated with the state machine to determine one or more behavior changes associated with the one or more attributes related to the one or more assets. The system is also configured to predict, based on the one or more behavior changes associated with the one or more attributes related to the one or more assets, a change in demand data for the one or more assets during a future interval of time.

A joint multimodal fusion computer model architecture is provided that receives prediction output data from a machine learning (ML) computer model set comprising a plurality of different subsets of ML computer models operating on input data of different modalities and generating different prediction outputs. Prediction outputs are fused by executing an uncertainty and correlation weighted (UCW) joint multimodal fusion operation on the prediction outputs to generate a fused output providing multimodal prediction output data. The UCW joint multimodal fusion operation applies different weights to different ones of prediction outputs from the different subsets of ML computer models operating on input data of different modalities. The different weights are determined based on an estimation of uncertainty in each of the different subsets of ML computer models and an estimate of a correlation between different modalities.

This document describes Kurtosis based pruning for sensor-fusion systems. Kurtosis based pruning minimizes a total quantity of comparisons performed when fusing together large sets of data. Multiple candidate radar tracks may possibly align with one of multiple candidate visual tracks. For each candidate vision track, a weight or other evidence of matching is assigned to each candidate radar track. An inverse of matching errors between each candidate vision and each candidate radar track contributes to this evidence, which may be normalized to produce, for each candidate vision track, a distribution associated with all candidate radar tracks. A Kurtosis or shape of this distribution is calculated. Based on the Kurtosis values, some candidate radar tracks are selected for matching and other remaining candidate radar tracks are pruned. The Kurtosis aids in determining how many candidates to retain and how many to prune. In this way, Kurtosis based pruning can prevent combinatorial explosions due to large-scale matching.