Xerox Corporation

Conduent Business Services, LLC

Other

Palo Alto Research Center Inc.

Zerox Corporation

Palo Alto Research Center Incorporate

Florent C Perronnin

Naila Murray

Albert Gordo Soldevila

Gabriela Csurka

Craig John Saunders

Jose Antonio Rodriguez-Serrano

Luca Marchesotti

Jose Antonio Rodriguez Serrano

Jorge Sanchez

Yan Liu

Jose A Rodriguez Serrano

Peter Paul

Robert Michael Lofthus

Kristine A German

Francois Ragnet

Claudio Cifarelli

Diane Larlus-Larrondo

Sandra Skaff

Albert Gordo

Beilei Xu

Rong Zhou

Robert Roy Price

Guillaume M Bouchard

Minh Binh Do

Herve Poirier

Adrien Gaidon

Thierry Armand Lehoux

Nicolas Guérin

Thomas Mensink

Raja Bala

Yonghui Zhao

Victor Ciriza

Frederic Roulland

Stéphane Clinchant

Cordelia Luise Schmid

Nicolas Guerin

Damien Cramet

Vincent Devin

Jakob Verbeek

José Antonio Rodriguez Serrano

Julian McAuley

Teofilo E De Campos

Diane Larlus

Sebastien Dabet

Hervé Poirier

Diane Larlus Larrondo

Jon Almazán Almazán

Teófilo E De Campos

Zeynep Akata

Jose Antonio Rodriquez Serrano

Yangmuzi Zhang

Mario Agustin Ricardo Jarmasz

Zaid Harchaoui

José Antonio Rodríguez-Serrano

José A Rodriguez Serrano

Usman Tariq

Milan Sulc

Josè Antonio Rodriguez Serrano

Jose-Antonio Rodriguez

A system and method enable semantic comparisons to be made between word images and concepts. Training word images and their concept labels are used to learn parameters of a neural network for embedding word images and concepts in a semantic subspace in which comparisons can be made between word images and concepts without the need for transcribing the text content of the word image. The training of the neural network aims to minimize a ranking loss over the training set where non relevant concepts for an image which are ranked more highly than relevant ones penalize the ranking loss.

Latent embeddings for word images and their semantics

In image classification, each class of a set of classes is embedded in an attribute space where each dimension of the attribute space corresponds to a class attribute. The embedding generates a class attribute vector for each class of the set of classes. A set of parameters of a prediction function operating in the attribute space respective to a set of training images annotated with classes of the set of classes is optimized such that the prediction function with the optimized set of parameters optimally predicts the annotated classes for the set of training images. The prediction function with the optimized set of parameters is applied to an input image to generate at least one class label for the input image. The image classification does not include applying a class attribute classifier to the input image.

Label-embedding view of attribute-based recognition

A method for extracting a representation from an image includes inputting an image to a pre-trained neural network. The gradient of a loss function is computed with respect to parameters of the neural network, for the image. A gradient representation is extracted for the image based on the computed gradients, which can be used, for example, for classification or retrieval.

Extracting gradient features from neural networks

A privacy-preserving multi-query parking management system and method. An image of a vehicle with respect to a specific part (e.g., license plate) can be captured when the vehicle enters via an entry point. An image signature can be computed by embedding the image into a descriptor space and the image signature can be stored in a database together with relevant metadata. An image of a vehicle with respect to the specific part can be captured when the vehicle exits via at least one exit point and an image signature can be computed. An entry-exit association with respect to the vehicle can be performed by searching for a most similar image signature in the database. Additionally, given a textual query (e.g., a license plate number), a signature can be computed by embedding the text into the same descriptor space.

Multi-query privacy-preserving parking management system and method

Authentication methods are disclosed for determining whether a person or object to be authenticated is a member of a set of authorized persons or objects. A query signature is acquired comprising a vector whose elements store values of an ordered set of features for the person or object to be authenticated. The query signature is compared with an aggregate signature comprising a vector whose elements store values of the ordered set of features for the set of authorized persons or objects. The individual signatures for the authorized persons or objects are not stored; only the aggregate signature. It is determined whether the person or object to be authenticated is a member of the set of authorized persons or objects based on the comparison. The comparing may comprise computing an inner product of the query signature and the aggregate signature, with the determining being based on the inner product.

One-to-many matching with application to efficient privacy-preserving re-identification

A method, system, and apparatus for vehicle occupancy detection comprises collecting image data of a vehicle, creating a first value according to a plurality of characteristics of a driver position of the vehicle, and then creating at least one other value according to a plurality of characteristics of at least one other candidate occupant position in the vehicle. The characteristics of the driver position of the vehicle and candidate occupant position of the vehicle are compared in order to determine the vehicle occupancy.

Vehicle occupancy detection using passenger to driver feature distance

Object clustering techniques are disclosed. A nonnegative sparse similarity matrix is constructed for a set of objects. Nonnegative factorization of the nonnegative sparse similarity matrix is performed. Objects of the set of objects are allocated to clusters based on factor matrices generated by the nonnegative factorization of the nonnegative sparse similarity matrix.

Clustering using non-negative matrix factorization on sparse graphs

An object detection method includes for each of a set of patches of an image, encoding features of the patch with a non-linear mapping function, and computing per-patch statistics based on the encoded features for approximating a window-level non-linear operation by a patch-level operation. Then, windows are extracted from the image, each window comprising a sub-set of the set of patches. Each of the windows is scored based on the computed patch statistics of the respective sub-set of patches. Objects, if any, can then be detected in the image, based on the window scores. The method and system allow the non-linear operations to be performed only at the patch level, reducing the computation time of the method, since there are generally many more windows than patches, while not impacting performance unduly, as compared to a system which performs non-linear operations at the window level.

Efficient object detection with patch-level window processing

A system and method for evaluating iconicity of an image are provided. In the method, at least one test image is received, each test image including an object in a selected class. Properties related to iconicity are computed for each test image. The properties may include one or more of: a) a direct measure of iconicity, which is computed with a direct iconicity prediction model which has been learned on a set of training images, each training image labeled with an iconicity score; b) one or more class-independent properties; and c) one or more class-dependent properties. A measure of iconicity of each of the test images is computed, based on the computed properties. By combining a set of complementary properties, an iconicity measure which shows good agreement with human evaluations of iconicity can be obtained.

System and method for predicting iconicity of an image

A system and method for comparing a text image with or without a wildcard character and a character string are provided. The method includes embedding a character string into a vectorial space by extracting a set of features from the character string and generating a character string representation based on the extracted features, such as a spatial pyramid bag of characters (SPBOC) representation. A text image is embedded into a vectorial space by extracting a set of features from the text image and generating a text image representation based on the text image extracted features. A similarity between the text image representation and the character string representation is computed, which includes computing a function of the text image representation and character string representation.

Method and system to perform text-to-image queries with wildcards

A method includes adapting the universal generative model of local descriptors to a first camera to obtain a first camera-dependent generative model. The same universal generative model is also adapted to a second camera to obtain a second camera-dependent generative model. From a first image captured by the first camera, a first image-level descriptor is extracted, using the first camera-dependent generative model. From a second image captured by the second camera, a second image-level descriptor is extracted using the second camera-dependent generative model. A similarity is computed between the first image-level descriptor and the second image-level descriptor. Information is output, based on the computed similarity. The adaptation allows differences between the image-level descriptors to be shifted towards deviations in image content, rather than the imaging conditions.

Adapted vocabularies for matching image signatures with fisher vectors

A system and method enable similarity measures to be computed between pairs of images and between a color name and an image in a common feature space. Reference image representations are generated by embedding color name descriptors for each reference image in the common feature space. Color name representations for different color names are generated by embedding synthesized color name descriptors in the common feature space. For a query including a color name, a similarity is computed between its color name representation and one or more of the reference image representations. For a query which includes a query image, a similarity is computed between a representation of the query image and one or more of reference image representations. The method also enables combined queries which include both a query image and a color name to be performed. One or more retrieved reference images, or information based thereon, is then output.

Discriminative embedding of local color names for object retrieval and classification

A method for diagnosis assistance exploits similarity between a new medical case and existing medical cases and experts when embedded in a common embedding space. Different types of queries are provided for, including a query-by-cases and a query-by-experts. These may be associated with different cost structures that encourage the requester to use the query-by-cases first and seek expert assistance if this proves unsuccessful. Depending on whether the query-by-cases or query-by-experts is requested, a subset of the existing cases or experts is identified based on the similarity of their representations, in the embedding space, with a representation of the new case in the embedding space. There may then be provision for communicating the new case to a selected one or more of the subset of experts for the expert to attempt to provide a diagnosis.

Social medical network for diagnosis assistance

In an image classification method, a feature vector representing an input image is generated by unsupervised operations including extracting local descriptors from patches distributed over the input image, and a classification value for the input image is generated by applying a neural network (NN) to the feature vector. Extracting the feature vector may include encoding the local descriptors extracted from each patch using a generative model, such as Fisher vector encoding, aggregating the encoded local descriptors to form a vector, projecting the vector into a space of lower dimensionality, for example using Principal Component Analysis (PCA), and normalizing the feature vector of lower dimensionality to produce the feature vector representing the input image. A set of mid-level features representing the input image may be generated as the output of an intermediate layer of the NN.

Fisher vectors meet neural networks: a hybrid visual classification architecture

A system and method for object instance localization in an image are disclosed. In the method, keypoints are detected in a target image and candidate regions are detected by matching the detected keypoints to keypoints detected in a set of reference images. Similarity measures between global descriptors computed for the located candidate regions and global descriptors for the reference images are computed and labels are assigned to at least some of the candidate regions based on the computed similarity measures. Performing the region detection based on keypoint matching while performing the labeling based on global descriptors improves object instance detection.

System and method for product identification

Growing community of inventors

Domène, France

Florent C Perronnin