Patents by Inventor Boris Chidlovskii

Boris Chidlovskii has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10289909
    Abstract: A method and apparatus for classifying an image. In one example, the method may include receiving one or more images associated with a source domain and one or more images associated with a target domain, identifying one or more source domain features based on the one or more images associated with the source domain, identifying one or more target domain features based on the one or more images associated with the target domain, training a conditional maximum mean discrepancy (CMMD) engine based on a difference between the one or more source domain features and the one or more target domain features, applying the CMMD engine to the one or more images associated with the target domain to generate one or more labels for each unlabeled target image of the one or more images associated with the target domain and classifying each one of the one or more images in the target domain using the one or more labels.
    Type: Grant
    Filed: March 6, 2017
    Date of Patent: May 14, 2019
    Assignee: Xerox Corporation
    Inventors: Fabien Baradel, Boris Chidlovskii, Gabriela Csurka
  • Publication number: 20180347999
    Abstract: Method and apparatus for generating realistic samples of public transportation usage to improve the operability of a public transportation system. Constraints can be expressed as a group of origin-destination-time triples. A trip (or trips) can then be assigned to each triple among the group of origin-destination-time triples while ignoring capacity constraints. A Metropolis-Hasting class sampling technique can then be applied with respect to the trip beginning with the origin-destination-time triples to generate a realistic sample of public transportation usage based on the aforementioned constraints in the form of target probability distributions and/or target probability densities, thereby improving the public transportation system by taking into account the generated realistic sample of public transportation usage.
    Type: Application
    Filed: May 30, 2017
    Publication date: December 6, 2018
    Inventor: Boris Chidlovskii
  • Patent number: 10089640
    Abstract: Methods and systems for interpretable user behavior profiling in off-street parking applications. To render user profiles easy to interpret by decision makers, the semi-automatic discovery and tagging of user profiles can be implemented. Transaction data from one or more (and geographically close) off-street parking installations can be implemented. An analysis of spatio-temporal behavioral patterns can be implemented based on representation of any parking episode by a set of heterogeneous features, the use of clustering methods for automatic pattern discovery, an assessment of obtained clusters, semi-automatic identification/tagging of space-temporal patterns, and a user-friendly interpretation of obtained patterns.
    Type: Grant
    Filed: February 26, 2015
    Date of Patent: October 2, 2018
    Assignee: CONDUENT BUSINESS SERVICES, LLC
    Inventors: Cesar Roberto de Souza, Boris Chidlovskii, Frederic Roulland, Luis Rafael Ulloa Paredes
  • Publication number: 20180253627
    Abstract: A method and apparatus for classifying an image. In one example, the method may include receiving one or more images associated with a source domain and one or more images associated with a target domain, identifying one or more source domain features based on the one or more images associated with the source domain, identifying one or more target domain features based on the one or more images associated with the target domain, training a conditional maximum mean discrepancy (CMMD) engine based on a difference between the one or more source domain features and the one or more target domain features, applying the CMMD engine to the one or more images associated with the target domain to generate one or more labels for each unlabeled target image of the one or more images associated with the target domain and classifying each one of the one or more images in the target domain using the one or more labels.
    Type: Application
    Filed: March 6, 2017
    Publication date: September 6, 2018
    Inventors: Fabien Baradel, Boris Chidlovskii, Gabriela Csurka
  • Patent number: 9989372
    Abstract: A method and system are disclosed for re-ranking trips from a journey planner using real traveler preferences. A trip request is received that includes an origin, a destination and a departure time. An associated journey planner retrieves a list of candidate trips that correspond to the request. A ranking function, ascertained from actual trips that match the trip request and from which are determined real-world traveler preferences, is applied to the list of candidate trips output by the journey planner, thereby re-ranking the list of candidate trips to reflect real-world traveler's experiences.
    Type: Grant
    Filed: November 5, 2014
    Date of Patent: June 5, 2018
    Assignee: Conduent Business Services, LLC
    Inventor: Boris Chidlovskii
  • Patent number: 9946767
    Abstract: A method and system are disclosed for generating a list of trips on an associated transportation network, the list ranked in accordance with time-dependent modeling of passenger preferences. User preferences of choosing a specific public transportation service or change point are modeled by a set of latent variables. Any actual trip on the network is converted into a set of pairwise preferences implicitly made by the passenger during the trip. Sequences of services matrices and change points matrices from the retrieved set of trips and non-negative factorization of the services and change points matrices is performed to smooth the matrices. The set of pairwise preferences are used to learn a ranking function and the output of a journey planner is re-ranked using the ranking function.
    Type: Grant
    Filed: January 19, 2016
    Date of Patent: April 17, 2018
    Assignee: Conduent Business Services, LLC
    Inventor: Boris Chidlovskii
  • Patent number: 9916542
    Abstract: A machine learning method operates on training instances from a plurality of domains including one or more source domains and a target domain. Each training instance is represented by values for a set of features. Domain adaptation is performed using stacked marginalized denoising autoencoding (mSDA) operating on the training instances to generate a stack of domain adaptation transform layers. Each iteration of the domain adaptation includes corrupting the training instances in accord with feature corruption probabilities that are non-uniform over at least one of the set of features and the domains. A classifier is learned on the training instances transformed using the stack of domain adaptation transform layers. Thereafter, a label prediction is generated for an input instance from the target domain represented by values for the set of features by applying the classifier to the input instance transformed using the stack of domain adaptation transform domains.
    Type: Grant
    Filed: February 2, 2016
    Date of Patent: March 13, 2018
    Assignee: XEROX CORPORATION
    Inventors: Boris Chidlovskii, Gabriela Csurka, Stéphane Clinchant
  • Publication number: 20180024968
    Abstract: A method for domain adaptation of samples includes receiving training samples from a plurality of domains, the plurality of domains including at least one source domain and a target domain, each training sample including values for a set of features. A domain predictor is learned on at least some of the training samples from the plurality of domains and respective domain labels. Domain adaptation is performed on the training samples using marginalized denoising autoencoding. This generates a domain adaptation transform layer (or layers) that transforms the training samples to a common adapted feature space. The domain adaptation employs the domain predictor to bias the domain adaptation towards one of the plurality of domains. Domain adapted training samples and their class labels can be used to train a classifier for prediction of class labels for unlabeled target samples that have been domain adapted with the domain adaptation transform layer(s).
    Type: Application
    Filed: July 22, 2016
    Publication date: January 25, 2018
    Applicant: Xerox Corporation
    Inventors: Stéphane Clinchant, Gabriela Csurka, Boris Chidlovskii
  • Publication number: 20170330112
    Abstract: A method for estimating travel demand in a transportation network includes receiving a dataset of trips. The trips were taken in the transportation network and are each represented by an origin-destination pair and a departure time. A trip can include a sequence of legs. Each trip is described by a vector of modalities. For trips that include the sequence of legs, boarding and alighting stops are estimated. An empirical trip distribution is generated for each modality for given origin-destination stops. The empirical trip distribution is fitted to a specific family of probability distributions. At least one of the generating the empirical trip distribution for a given modality and the fitting the empirical trip distribution to the probability distributions is performed with a processor.
    Type: Application
    Filed: May 11, 2016
    Publication date: November 16, 2017
    Applicant: Conduent Business Services, LLC
    Inventor: Boris Chidlovskii
  • Publication number: 20170220951
    Abstract: Training instances from a target domain are represented by feature vectors storing values for a set of features, and are labeled by labels from a set of labels. Both a noise marginalizing transform and a weighting of one or more source domain classifiers are simultaneously learned by minimizing the expectation of a loss function that is dependent on the feature vectors corrupted with noise represented by a noise probability density function, the labels, and the one or more source domain classifiers operating on the feature vectors corrupted with the noise. An input instance from the target domain is labeled with a label from the set of labels by operations including applying the learned noise marginalizing transform to an input feature vector representing the input instance and applying the one or more source domain classifiers weighted by the learned weighting to the input feature vector representing the input instance.
    Type: Application
    Filed: February 2, 2016
    Publication date: August 3, 2017
    Applicant: Xerox Corporation
    Inventors: Boris Chidlovskii, Gabriela Csurka, Stéphane Clinchant
  • Publication number: 20170220897
    Abstract: A machine learning method operates on training instances from a plurality of domains including one or more source domains and a target domain. Each training instance is represented by values for a set of features. Domain adaptation is performed using stacked marginalized denoising autoencoding (mSDA) operating on the training instances to generate a stack of domain adaptation transform layers. Each iteration of the domain adaptation includes corrupting the training instances in accord with feature corruption probabilities that are non-uniform over at least one of the set of features and the domains. A classifier is learned on the training instances transformed using the stack of domain adaptation transform layers. Thereafter, a label prediction is generated for an input instance from the target domain represented by values for the set of features by applying the classifier to the input instance transformed using the stack of domain adaptation transform domains.
    Type: Application
    Filed: February 2, 2016
    Publication date: August 3, 2017
    Applicant: Xerox Corporation
    Inventors: Boris Chidlovskii, Gabriela Csurka, Stéphane Clinchant
  • Patent number: 9715695
    Abstract: Methods and systems for estimating airport usage demand. Airport parking traffic usage data and flight-time table data can be compiled with respect to an airport (or more than one airport). The airport parking traffic usage data and flight-time table data can be analyzed using an efficient time matching approach (e.g., a time segment matching algorithm). An efficient method to match passengers and flights is introduced. Passenger behavior can be estimated with respect to the airport based on the airport parking traffic usage data and flight-time table data.
    Type: Grant
    Filed: June 1, 2015
    Date of Patent: July 25, 2017
    Assignee: Conduent Business Services, LLC
    Inventors: Cesar Roberto de Souza, Luis Rafael Ulloa Paredes, Boris Chidlovskii, Victor Ciriza
  • Publication number: 20170206201
    Abstract: A method and system are disclosed for generating a list of trips on an associated transportation network, the list ranked in accordance with time-dependent modeling of passenger preferences. User preferences of choosing a specific public transportation service or change point are modeled by a set of latent variables. Any actual trip on the network is converted into a set of pairwise preferences implicitly made by the passenger during the trip. Sequences of services matrices and change points matrices from the retrieved set of trips and non-negative factorization of the services and change points matrices is performed to smooth the matrices. The set of pairwise preferences are used to learn a ranking function and the output of a journey planner is re-ranked using the ranking function.
    Type: Application
    Filed: January 19, 2016
    Publication date: July 20, 2017
    Applicant: Xerox Corporation
    Inventor: Boris Chidlovskii
  • Patent number: 9710729
    Abstract: In camera-based object labeling, boost classifier ƒT(x)=?r=1M?rhr(x) is trained to classify an image represented by feature vector x using a target domain training set DT of labeled feature vectors representing images acquired by the same camera and a plurality of source domain training sets DS1, . . . , DSN acquired by other cameras. The training applies an adaptive boosting (AdaBoost) algorithm to generate base classifiers hr(x) and weights ?r. The rth iteration of the AdaBoost algorithm trains candidate base classifiers hrk(x) each trained on a training set DT?DSk, and selects hr(x) from previously trained candidate base classifiers. The target domain training set DT may be expanded based on a prior estimate of the labels distribution for the target domain. The object labeling system may be a vehicle identification system, a machine vision article inspection system, or so forth.
    Type: Grant
    Filed: September 4, 2014
    Date of Patent: July 18, 2017
    Assignee: XEROX CORPORATION
    Inventors: Boris Chidlovskii, Gabriela Csurka
  • Publication number: 20170161633
    Abstract: A classification method includes receiving a collection of samples, each sample comprising a multidimensional feature representation. A class label prediction for each sample in the collection is generated with one or more pretrained classifiers. For at least one iteration, each multidimensional feature representation is augmented with a respective class label prediction to form an augmented representation, a set of corrupted samples is generated from the augmented representations, and a transformation that minimizes a reconstruction error for the set of corrupted samples is learned. An adapted class label prediction for at least one of the samples in the collection is generated using the learned transformation and information is output, based on the adapted class label prediction. The method is useful in predicting labels for target samples where there is no access to source domain samples that are used to train the classifier and no access to target domain training data.
    Type: Application
    Filed: December 7, 2015
    Publication date: June 8, 2017
    Applicant: Xerox Corporation
    Inventors: Stéphane Clinchant, Gabriela Csurka, Boris Chidlovskii
  • Publication number: 20170147944
    Abstract: A domain-adapted classification system and method are disclosed. The method includes mapping an input set of representations to generate an output set of representations, using a learned transformation. The input set of representations includes a set of target samples from a target domain. The input set also includes, for each of a plurality of source domains, a class representation for each of a plurality of classes. The class representations are representative of a respective set of source samples from the respective source domain labeled with a respective class. The output set of representations includes an adapted representation of each of the target samples and an adapted class representation for each of the classes for each of the source domains. A class label is predicted for at least one of the target samples based on the output set of representations and information based on the predicted class label is output.
    Type: Application
    Filed: November 24, 2015
    Publication date: May 25, 2017
    Applicant: Xerox Corporation
    Inventors: Gabriela Csurka, Boris Chidlovskii, Stéphane Clinchant
  • Publication number: 20170132544
    Abstract: Methods, systems, and processor-readable media for the stochastic optimization of public transport schedules. A real-world collection of transit instances can be derived from a transport system and fed as input to a two-stage stochastic program. A schedule offset can be relaxed in the two-stage stochastic program to allow the two-stage stochastic program to operate according to the real-world collection of transit instances. An optimized transport schedule can then be derived from the two-stage stochastic program for use by the transport system based on the schedule offset and the real-world collection of transit instances.
    Type: Application
    Filed: November 10, 2015
    Publication date: May 11, 2017
    Inventors: Sofia Zaourar Michel, Boris Chidlovskii
  • Patent number: 9600826
    Abstract: A tag recommendation for an item to be tagged is generated by: selecting a set of candidate neighboring items in an electronic social network based on context of items in the electronic social network respective to an owner of the item to be tagged; selecting a set of nearest neighboring items from the set of candidate neighboring items based on distances of the candidate neighboring items from the item to be tagged as measured by an item comparison metric; and selecting at least one tag recommendation based on tags of the items of the set of nearest neighboring items. The item comparison metric may comprise a Mahalanobis distance metric trained on the set of candidate neighboring items to correlate the trained Mahalanobis distance between pairs of items of the set of candidate neighboring items with an overlap metric indicative of overlap of the tag sets of the two items.
    Type: Grant
    Filed: February 28, 2011
    Date of Patent: March 21, 2017
    Assignee: XEROX CORPORATION
    Inventors: Mohamed Aymen Benzarti, Boris Chidlovskii, Nishant Vijayakumar
  • Patent number: 9519912
    Abstract: In demand prediction, a history of demand for a resource is modeled to generate a baseline model of the demand, and demand for the resource at a prediction time is predicted by evaluating a regression function of depth k operating on an input data set including at least the demand for the resource at the prediction time output by the baseline model and measured demand for the resource measured at k times prior to the prediction time. The resource may be off-street parking, and the input data set may further include weather data. The regression function may comprise a support vector regression (SVR) function that is trained on the history of demand for the resource. The baseline model suitably comprises a Fourier model of the history of demand for the resource.
    Type: Grant
    Filed: September 20, 2013
    Date of Patent: December 13, 2016
    Assignee: XEROX CORPORATION
    Inventors: Boris Chidlovskii, Mohammad Ghufran
  • Patent number: 9519060
    Abstract: A system and method for classifying vehicles from laser scan data by receiving laser scan data corresponding to multiple vehicles from a laser scanner; extracting vehicle shapes corresponding to the multiple vehicles based on the laser scan data; aligning the vehicle shapes; and generating vehicle profiles based on the aligned vehicle shapes. The system and method can further include aligning the vehicle shapes using sequence kernels, such as global alignment kernels, and constraining the sequence kernels based on determined weights.
    Type: Grant
    Filed: May 27, 2014
    Date of Patent: December 13, 2016
    Assignee: Xerox Corporation
    Inventors: Boris Chidlovskii, Gabriela Csurka, Jose Antonio Rodriguez Serrano