Naver Corporation

Rafael Sampaio De Rezende

Diane Larlus

Cesar De Souza

Naila Murray

Jon Almazan

Jérome Revaud

Gabriela Csurka Khedari

Jérôme Revaud

Ginger Delmas

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.

Data compatibility for text-enhanced visual retrieval

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.

Cross-modal search systems and methods

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.

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.

Training a convolutional neural network for image retrieval with a listwise ranking loss function

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.

Growing community of inventors

Grenoble, France

Rafael Sampaio De Rezende