176 patents
Utility
Neural Ranking Model for Generating Sparse Representations for Information Retrieval
28 Dec 23
A ranker for a neural information retrieval model comprises a document encoder having a pretrained language model layer and configured to receive one or more documents and generate a sparse representation for each of the documents predicting term importance of the document over a vocabulary.
Stéphane CLINCHANT, Carlos LASSANCE
Filed: 5 May 23
Utility
Method, Device, and Non-transitory Computer-readable Recording Medium to Provide Conversational Content In Role-playing Format
28 Dec 23
A conversation learning service method includes registering audio uttered by a first learning participant as pronunciation content in an accent that represents the first learning participant's country of origin, ethnicity, or region; and providing a conversational text including at least two sentences in a role-playing format using the pronunciation content corresponding to the sentence.
Sua LEE, Somi KIM, Jonghwan KIM, Hye Seung SEO, Dongwoon KIM, JeeHye SUNG, Yanchen ZHOU, Longri JIN
Filed: 21 Jun 23
Utility
Method and System for Generating a Schematic Map
7 Dec 23
A method for automatically generating, in real-time, for display on a display, a simplified network layout from an initial network layout including one or more lines each connecting a plurality of nodes.
Gianluca MONACI, Frédéric ROULLAND, Adrien BRUYAT, Christelle LOIODICE
Filed: 16 Aug 23
Utility
Distilling Information for Crowd-aware Robot Navigation
9 Nov 23
A navigating device includes: a camera configured to capture images within a field of view, the field of view depicting a scene including humans; a feature module configured to generate feature vectors based on the scene of humans in the images and to specify latent vectors that summarize movement of the humans in the scene based only on the camera images, the feature vectors summarizing the movement of the humans in the scene, and the latent vectors capturing a latent representation of trajectories in the scene of humans; a policy module configured to generate actions to be taken by the navigating device to navigate the scene of humans based on the feature vectors; and a propulsion control module configured to control one or more propulsion devices of the navigating device based on the actions to be taken generated by the policy module to navigate the scene of humans
Gianluca MONACI, Michel Aractingi, Tomi Silander
Filed: 9 Feb 23
Utility
Method, Computer Device, and Non-transitory Computer-readable Recording Medium for Providing Optimal Path Using Expert Knowledge
2 Nov 23
A method for providing an optimal path through a computer network includes predicting a subsequent action of a target user through an optimal path prediction model that is trained in a form of a graph representing a user action trajectory of a session unit and recommending a path of the predicted action as an optimal path.
Young-Bum KIM, Gun Su LEE, Dongchan KIM, Sun KIM, Jinmyung WON, Hongyeon YU, Chanhee LEE
Filed: 7 Nov 22
Utility
Cross-modal Search Systems and Methods
2 Nov 23
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.
Diane LARLUS, Jon ALMAZAN, Cesar DE SOUZA, Naila MURRAY, Rafael SAMPAIO DE REZENDE
Filed: 29 Jun 23
Utility
Method, Computer Device, and Non-transitory Computer-readable Recording Medium for Providing Optimal Path
2 Nov 23
A method for providing an optimal path to achieve a user goal includes collecting user historical session data that includes a user action trajectory based on a session unit; and generating a model for optimal path prediction by representing the user historical session data as a path in a form of a graph and by learning the path.
Young-Bum KIM, Gun Su LEE, Dongchan KIM, Sun KIM, Jinmyung WON, Hongyeon YU, Chanhee LEE
Filed: 10 Nov 22
Utility
Self-attention-based Confidence Estimation of Language Models
19 Oct 23
A confidence estimation system includes: a neural network including at least one an attention module including N heads configured to: generate attention matrices based on interactions between tokens for words in an input sequence of words, the input sequence of words including a word that is obscured; and determine the word that is obscured in the input sequence; and a confidence module configured to determine a confidence value indicative of a probability of the neural network correctly determining the word that is obscured, the confidence module determining the confidence value of the word that is obscured using a convolutional neural network that projects the attention matrices generated by the attention module over a multi-dimensional space, the attention matrices recording interactions between the tokens in the input sequence of words without information regarding the tokens for the words and the word that is obscured.
Julien PEREZ, Denys Proux, Michael Niemaz
Filed: 14 Apr 22
Utility
System and Method Using Pyramidal and Uniqueness Matching Priors for Identifying Correspondences Between Images
28 Sep 23
A computer-implemented method includes: obtaining a pair of images depicting a same scene, the pair of images including a first image with a first pixel grid and a second image with a second pixel grid, the first pixel grid different than the second pixel grid; by a neural network module having a first set of parameters: generating a first feature map based on the first image; and generating a second feature map based on the second image; determining a first correlation volume based on the first and second feature maps; iteratively determining a second correlation volume based on the first correlation volume; determining a loss for the first and second feature maps based on the second correlation volume; generating a second set of the parameters based on minimizing a loss function using the loss; and updating the neural network module to include the second set of parameters.
Jérome REVAUD, Vincent LEROY, Philippe WEINZAEPFEL, Boris CHIDLOVSKII
Filed: 30 Jan 23
Utility
Content Playing Method and System
17 Aug 23
A content playing method includes obtaining a first media playlist for video on demand (VOD)-type first content via a server in accordance with a request from a player; changing the obtained first media playlist from VOD-type to live-type; providing the changed first media playlist to the player; obtaining a second media playlist for second content via the server, before the completion of the playing of the first content using the changed first media playlist in the player; and generating a third media playlist by connecting the changed first media playlist and the second media playlist.
Jonghyeok LEE, Hyo Won HWANG, Woo-sik BYUN, SungTaek CHO, SungHo KIM, Joon-kee CHANG
Filed: 17 Apr 23
Utility
Method and System for Evaluating Performance of Image Tagging Model
10 Aug 23
A method for comparing and evaluating performance of an image tagging model includes receiving a verification data set including a plurality of verification images and a plurality of correct values associated with the plurality of verification images, receiving a first image tagging model and a second image tagging model, calculating a first performance score for the first image tagging model using the verification data set, and calculating a second performance score for the second image tagging model using the verification data set, in which each of the correct values is associated with at least one verification class of a verification class set.
Hyung Do KIM, Jaehoon JUNG, Hyunyang SEO
Filed: 6 Feb 23
Utility
Model Globalization for Long Document Summarization
3 Aug 23
A summarization system includes: K embedding modules configured to: receive K blocks of text, respectively, of a document to be summarized; and generate K first representations based on the K blocks of text, respectively, where K is an integer greater than 2; a first propagation module configured to generate second representations based on the K first representations; a second propagation module configured to generate third representations based on the second representations; an output module configured to select ones of the K blocks based on the third representations; and a summary module configured to generate a summary of the document from text of the selected ones of the K blocks.
Julien Perez, Quentin Grail, Eric Jacques Guy Gaussier
Filed: 3 Feb 22
Utility
Reset Systems and Methods for Continuous Adaptation without Forgetting
3 Aug 23
An autonomous system includes: a first semantic segmentation model trained based on a training dataset including images and labels for the images, the first semantic segmentation model configured to generate a first segmentation map based on an image from a camera; a second semantic segmentation model of the same type of semantic segmentation model as the first semantic segmentation model, the second semantic segmentation model configured to generate a second segmentation map based on the image from the camera; an adaptation module configured to selectively adjust one or more first parameters of the second semantic segmentation model; and a reset module configured to: determine a first total number of unique classifications included in the first segmentation map; determine a second total number of unique classifications included in the first segmentation map; and selectively reset the first parameters to previous parameters, respectively, based on the first and second total numbers.
Riccardo VOLPI, Diane LARLUS, Gabriela CSURKA KHEDARI
Filed: 31 Jan 22
Utility
Action Recognition Using Implicit Pose Representations
6 Jul 23
A computer-implemented method of recognition of actions performed by individuals includes: by one or more processors, obtaining images including at least a portion of an individual by the one or more processors, based on the images, generating implicit representations of poses of the individual in the images; and by the one or more processors, determining an action performed by the individual and captured in the images by classifying the implicit representations of the poses of the individual.
Philippe WEINZAEPFEL, Gregory Rogez
Filed: 13 Mar 23
Utility
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters
6 Jul 23
Methods and systems for unsupervised training for a neural multilingual sequence-to-sequence (seq2seq) model.
Alexandre BÉRARD, Laurent BESACIER, Matthias GALLÉ, Ahmet ÜSTÜN
Filed: 9 Sep 22
Utility
Neural Ranking Model for Generating Sparse Representations for Information Retrieval
6 Jul 23
A neural model for representing an input sequence over a vocabulary in a ranker of a neural information retrieval model.
Stéphane Clinchant, Thibault Formal, Carlos Lassance, Benjamin PIwowarski
Filed: 1 Jun 22
Utility
Method and System for Meta-learning of Neural Combinatorial Optimization Heuristics
6 Jul 23
Methods and systems for training a neural combinatorial optimization (NCO) model having a processor and memory for performing a task having a target distribution.
Jean-Marc ANDREOLI, Sofia MICHEL, Sahil MANCHANDA
Filed: 15 Nov 22
Utility
End-to-end Neural Text-to-speech Model with Prosody Control
6 Jul 23
Methods and systems for generating an end-to-end neural text-to-speech (TTS) model to process an input text to generate speech representations.
Ioan CALAPODESCU, Inyoung KIM, Laurent BESACIER, Siddique LATIF
Filed: 23 Sep 22
Utility
Method, System, and Computer-readable Recording Medium for Implementing Fast-switching Mode Between Channels In Multi-live Transmission Environment
6 Jul 23
A method, a system, and a computer-readable recording medium implement a fast-switching mode between channels in a multi-live transmission environment.
Joon-kee CHANG, Sung Ho KIM, Hyesung NO, Yun Ho JUNG, Jinhoon KIM, Yeong Jin JEONG, Jeongki KIM, In Cheol KANG, Jonghyeok LEE, Jae Chul AHN, Sung Taek CHO
Filed: 9 Mar 23
Utility
Fairness Utility Trade-off In Ranking As a Geometric Projection Problem
25 May 23
A ranking system includes: an exposure module configured to, in response to receiving an input from a computing device via a network, determine, based on an anisotropic intensity value and using a Dynamic Bayesian Network (DBM) exposure model, an exposure value for ranking items for output via the computing device, where the anisotropic intensity value corresponds to a tradeoff between utility to users and fairness to item producers; a ranking module configured to generate a ranking of the items based on the exposure value; and a response module configured to transmit a response including the ranking of the items to the computing device via the network.
Till KLETTI, Jean-Michel RENDERS
Filed: 19 Nov 21