Patents by Inventor Rafael Sampaio De Rezende
Rafael Sampaio De Rezende 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).
-
Publication number: 20230350951Abstract: A system includes: a training dataset including first objects of a first modality and second objects of a second modality different than the first modality, where the second objects include text that is descriptive of the first objects; a first matrix including first relevance values indicative of relevance between the first objects and the second objects, respectively; a second matrix including second relevance values indicative of relevance between the second objects and the first objects, respectively; and a training module configured to: assign ones of the second objects to bins based on distances between the ones of the objects and a query; determine a ranking measure based on a number of the ones of the second objects assigned to the bins; determine losses based on the ranking measure and the first and second matrices; determine a final loss based on the losses; train embedding functions based on the final loss.Type: ApplicationFiled: June 29, 2023Publication date: November 2, 2023Applicant: Naver CorporationInventors: Diane LARLUS, Jon ALMAZAN, Cesar DE SOUZA, Naila MURRAY, Rafael SAMPAIO DE REZENDE
-
Patent number: 11734352Abstract: A training system includes: a training dataset including first objects of a first modality and second objects of a second modality that are associated with the first objects, respectively; a first matrix including first relevance values indicative of relevance between the first objects and the second objects, respectively; a second matrix including second relevance values indicative of relevance between the second objects and the first objects, respectively; and a training module configured to: based on similarities between ones of the second objects, generate a third matrix by selectively adding first additional relevance values to the first matrix; based on the similarities between the ones of the second objects, generate a fourth matrix by selectively adding second additional relevance values to the second matrix; and store the third and fourth matrices in memory of a search module for cross-modal retrieval in response to receipt of search queries.Type: GrantFiled: February 14, 2020Date of Patent: August 22, 2023Assignee: NAVER CORPORATIONInventors: Diane Larlus, Jon Almazan, Cesar De Souza, Naila Murray, Rafael Sampaio De Rezende
-
Publication number: 20230196098Abstract: A training system includes: a neural network configured to, using trained parameters, generate a first encoding based on an input query and second encodings based on candidate responses for the input query; and a training module configured to: train the trained parameters using hyperparameters; and jointly optimize the hyperparameters using coordinate descent and line searching, the hyperparameters including: a first hyperparameter indicative of a first weight value to apply based on positive interactions of entries of a distance matrix based on encodings; a second hyperparameter indicative of a second weight value to apply based on negative interactions of entries of the distance matrix generated based on the first and second encodings; and a third hyperparameter corresponding to a dimension of the distance matrix generated based on the first and second encodings.Type: ApplicationFiled: September 20, 2022Publication date: June 22, 2023Applicant: NAVER CORPORATIONInventors: Rafael SAMPAIO DE REZENDE, Arnaud SORS, Sarah IBRAHIMI, Jean-Marc ANDREOLI
-
Publication number: 20230073843Abstract: An interaction module includes: a first text-image interaction module configured to generate a vector representation of a first text-image pair based on an encoded representation of a reference image and an encoded representation of a text modifier, the reference image and the text modifier received from a computing device. A second text-image interaction module is configured to generate a vector representation of a second text-image pair based on the encoded representation of the text modifier and an encoded representation of a candidate target image. A compatibility module is configured to compute, based on the vector representation of the first text-image pair and the vector representation of the second text-image pair, a compatibility score for a triplet including the reference image, the text modifier, and the candidate target image. A ranking module is configured to rank a set of candidate target images including the candidate target image by compatibility scores.Type: ApplicationFiled: June 23, 2022Publication date: March 9, 2023Applicant: NAVER CORPORATIONInventors: Rafael SAMPAIO DE REZENDE, Diane LARLUS, Ginger DELMAS, Gabriela CSURKA KHEDARI
-
Patent number: 11521072Abstract: A method of performing image retrieval includes: obtaining a query image; generating a global feature descriptor of the query image by inputting the query image into a convolutional neural network (CNN) and obtaining the global feature descriptor as an output of the CNN, where parameters of the CNN are learned during training of the CNN on a batch of training images using a listwise ranking loss function and optimizing a quantized mean average precision ranking evaluation metric; determining similarities between the query image and other images based on distances between the global feature descriptor of the query image and global feature descriptors of the other images, respectively; ranking the other images based on the similarities, respectively; and selecting a set of the other images based on the similarities between the query image and the other images.Type: GrantFiled: February 11, 2020Date of Patent: December 6, 2022Assignee: NAVER CORPORATIONInventors: Jérome Revaud, Jon Almazan, Cesar De Souza, Rafael Sampaio De Rezende
-
Publication number: 20210256068Abstract: A training system includes: a training dataset including first objects of a first modality and second objects of a second modality that are associated with the first objects, respectively; a first matrix including first relevance values indicative of relevance between the first objects and the second objects, respectively; a second matrix including second relevance values indicative of relevance between the second objects and the first objects, respectively; and a training module configured to: based on similarities between ones of the second objects, generate a third matrix by selectively adding first additional relevance values to the first matrix; based on the similarities between the ones of the second objects, generate a fourth matrix by selectively adding second additional relevance values to the second matrix; and store the third and fourth matrices in memory of a search module for cross-modal retrieval in response to receipt of search queries.Type: ApplicationFiled: February 14, 2020Publication date: August 19, 2021Applicant: Naver CorporationInventors: Diane Larlus, Jon Almazan, Cesar De Souza, Naila Murray, Rafael Sampaio De Rezende
-
Patent number: 11055569Abstract: A method for detecting a point of interest (POI) change in a pair of inputted POI images. A first processor of the method: generates triplets of training POI images using a base of training POI images and trains a convolutional neural network (CNN) of three-stream Siamese type based on the triplets of training POI images. A second processor of the method: computes, for each image of the pair of inputted POI images, a descriptor of that image using a stream of the CNN of three-stream Siamese type, computes a similarity score based on the descriptors of the images of the pair of inputted POI images using a similarity score function, and selectively detects the POI change based on the similarity score. A third processor of the method generates the base of training POI images to include an initial set of POI images and a set of synthetic POI images.Type: GrantFiled: September 19, 2019Date of Patent: July 6, 2021Assignee: NAVER CORPORATIONInventors: Jérôme Revaud, Rafael Sampaio De Rezende
-
Publication number: 20200342328Abstract: A method of performing image retrieval includes: obtaining a query image; generating a global feature descriptor of the query image by inputting the query image into a convolutional neural network (CNN) and obtaining the global feature descriptor as an output of the CNN, where parameters of the CNN are learned during training of the CNN on a batch of training images using a listwise ranking loss function and optimizing a quantized mean average precision ranking evaluation metric; determining similarities between the query image and other images based on distances between the global feature descriptor of the query image and global feature descriptors of the other images, respectively; ranking the other images based on the similarities, respectively; and selecting a set of the other images based on the similarities between the query image and the other images.Type: ApplicationFiled: February 11, 2020Publication date: October 29, 2020Applicant: NAVER CORPORATIONInventors: Jérome REVAUD, Jon ALMAZAN, Cesar DE SOUZA, Rafael SAMPAIO DE REZENDE
-
Publication number: 20200110966Abstract: A method for detecting a point of interest (POI) change in a pair of inputted POI images. A first processor of the method: generates triplets of training POI images using a base of training POI images and trains a convolutional neural network (CNN) of three-stream Siamese type based on the triplets of training POI images. A second processor of the method: computes, for each image of the pair of inputted POI images, a descriptor of that image using a stream of the CNN of three-stream Siamese type, computes a similarity score based on the descriptors of the images of the pair of inputted POI images using a similarity score function, and selectively detects the POI change based on the similarity score. A third processor of the method generates the base of training POI images to include an initial set of POI images and a set of synthetic POI images.Type: ApplicationFiled: September 19, 2019Publication date: April 9, 2020Applicant: Naver CorporationInventors: Jérôme Revaud, Rafael Sampaio De Rezende