309 patents
Page 10 of 16
Utility
Training and using a convolutional neural network for person re-identification
5 Oct 21
A method for re-identification of a subject in an image by pre-training a convolutional neural network to recognize individuals within a closed set of possible identifications and further pre-training the convolutional neural network using classification loss; training the pre-trained convolutional neural network by sequentially processing a plurality of triplet of images, each triplet containing a query image degraded by adding random noise to a region of the query image, a positive image corresponding to an image of a same subject as in the query image, and a negative image corresponding to an image of a different subject as in the query image by (a) ranking the triplets by the triplet loss computed, (b) selecting a subset of triplets among the plurality of triplets, and (c) retraining the pre-trained convolutional neural network on each of the triplets of the subset of triplets.
Jon Almazan, Bojana Gajic, Naila Murray, Diane Larlus-Larrondo
Filed: 6 Nov 19
Utility
Method And System For Generating And Executing Client/Server Applications
30 Sep 21
There is provided an improvement for developing an application between an application server and one of multiple client devices where the application server is disposed remotely of the one of multiple client devices.
Jose Miguel PEREZ ALVAREZ, Adrian MOS
Filed: 13 Jun 21
Utility
Unsupervised Aspect-based Multi-document Abstractive Summarization
30 Sep 21
A multi-document summarization system includes: an encoding module configured to receive multiple documents associated with a subject and to, using a first model, generate vector representations for sentences, respectively, of the documents; a grouping module configured to group first and second ones of the sentences associated with first and second aspects into first and second groups, respectively; a group representation module configured to generate a first vector representation based on the first ones of the sentences and a second vector representation based on the second ones of the sentences; a summary module configured to: using a second model: generate a first sentence regarding the first aspect based on the first vector representation; and generate a second sentence regarding the second aspect based on the second vector representation; and store a summary including the first and second sentences in memory in association with the subject.
Hady ELSAHAR, Maximin COAVOUX, Matthias GALLE
Filed: 27 Mar 20
Utility
Methods, systems, and computer readable media for providing word learning
28 Sep 21
A method performed using at least one processor to facilitate word learning, the method including selecting a plurality of words to be learned; generating a learning word pool including the plurality of words to be learned; selecting a determined number of words from the learning word pool; generating a learning list including the determined number of words; displaying a first word included in the learning list; receiving a selection of whether to maintain the displayed first word in the learning list or replace the displayed first word with an alternate word; excluding the displayed first word from the learning list in response to the selection to replace the displayed first word; and adding the alternate word to the learning list in response to the excluding.
Ryan Kim, Dong-Hoon Han, Jonghwan Kim
Filed: 2 Oct 17
Utility
Content providing server, content providing terminal, and content providing method
21 Sep 21
Provided are a content providing server, a content providing terminal, a content providing method.
Byung Gyou Choi, Chan Su Suh, Song Hyun Park, Sung Hyun Lee
Filed: 7 Jun 18
Utility
Training and Using an Ensemble of Complimentary Convolutional Neural Networks for Cross-domain Retrieval of Fashion Item Images
9 Sep 21
A method and system generate an ensemble image representation for cross-domain retrieval of a fashion item image from a database by using a three-stream Siamese triplet loss trained convolutional neural network to generate a first retrieval descriptor corresponding to an inputted query image; using an average precision loss trained convolutional neural network to generate a second retrieval descriptor corresponding to the inputted query image; concatenating both the first retrieval descriptor and the second retrieval descriptor; and I2-normalizing the concatenated result to generate the ensemble image representation.
Naila Murray, Michal Kucer
Filed: 4 Mar 20
Utility
Cartoon statistical reading data method and apparatus
31 Aug 21
Provided is a method of providing statistical data related to cartoon data provided to a cartoon data display apparatus, the method including: obtaining, by a controller, first cartoon reading information by analyzing a cartoon reading pattern of a first user when the first user reads first cartoon data; generating, by the controller, first statistical data from the obtained first cartoon reading information; and providing, by a communication unit, the generated first statistical data to an external apparatus in communication with the controller.
Hyo Kim, Hyun Chul Lee, Ji Han Kim, Dai Hyun Lim, Byoung Kwan Kim, Myeong Seok Yang
Filed: 8 Aug 17
Utility
Method and System for Generating a Schematic Map
26 Aug 21
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: 26 Oct 20
Utility
System and method for generating pedestrian tours
24 Aug 21
Generating a pedestrian tour includes: receiving a query from a user device via a network, the query indicative of a request for a pedestrian tour and including a location and preferences including a target length for the pedestrian tour; obtaining a graph of a geographical area around the location of the user device, the graph including nodes indicative of path crossings and arcs indicative of paths connecting pairs of the nodes; determining scores for the arcs based on characteristics of the arcs, respectively, and the preferences; selecting connecting ones of the arcs based on the scores of the connecting ones of the arcs, lengths of the selected connecting ones of the arcs, and the target length; adding the selected connecting ones of the arcs to the pedestrian tour to initialize the pedestrian tour; and transmitting the pedestrian tour to the user device via the network for display.
Sofia Michel, Stéphane Clinchant, Christophe Legras, Jutta Willamowski
Filed: 21 Nov 19
Utility
Method and System for Providing Information to a User Relating to a Point-of-interest
19 Aug 21
In methods and systems for providing information to a user relating to a point-of-interest (POI), a query is received via a communication network.
Salah AÏT-MOKHTAR, Caroline BRUN, Agnes SANDOR
Filed: 13 Feb 20
Utility
Cross-modal Search Systems and Methods
19 Aug 21
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.
Diane Larlus, Jon Almazan, Cesar De Souza, Naila Murray, Rafael Sampaio De Rezende
Filed: 14 Feb 20
Utility
Latent Question Reformulation and Information Accumulation for Multi-hop Machine Reading
19 Aug 21
A question answering system includes: a first encoder module configured to receive a question, the question including a first plurality of words, and encode the question into a first vector representation; a second encoder module configured to encode a document into a second vector representation, the document including a second plurality of words; a first reading module configured to generate a third vector representation based on the first and second vector representations; a first reformulation module configured to generate a first reformulated vector representation based on the first vector representation; a second reading module configured to generate a fifth vector representation based on the second vector representation and the first reformulated vector representation; a second reformulation module configured to generate a second reformulated vector representation based on first reformulated vector representation; and an answer module configured to determine an answer to the question based on the second reformulated vector representation.
Quentin GRAIL, Julien PEREZ, Eric Jacques Guy GAUSSIER
Filed: 9 Sep 20
Utility
Video-providing method and video-providing system
17 Aug 21
A video-providing system includes a first grouping unit configured to generate a first group that is a collection of one or more video files; a second group unit configured to group at least a portion of video files from the video files included in the first group; and a providing unit configured to provide video files selected from the video files included in the second group unit.
Yu-Sik Kim
Filed: 17 May 16
Utility
Content Providing Server, Content Providing Terminal, and Content Providing Method
5 Aug 21
An operation method of a user terminal for providing a video slide service includes uploading a UGC video to a server; receiving, from the server, scene meta-information for each playback section of the UGC video; generating a video slide file on the basis of the received scene meta-information for each playback section; classifying, according to categories, a plurality of pieces of page information configuring the video slide file; and generating a storybook corresponding to the UGC video on the basis of a plurality of page groups classified according to the categories.
Byung Gyou CHOI, Sung Hyun LEE, Sang Yoon LEE, Jun Oh KIM
Filed: 21 Apr 21
Utility
Electronic Device for Providing Visual Localization Based on Outdoor Three-dimension Map Information and Operating Method Thereof
5 Aug 21
Electronic devices and/or operating methods of the electronic device to provide visual localization based on outdoor three-dimensional (3D) map information may be provided.
Deokhwa KIM, Donghwan LEE
Filed: 3 Feb 21
Utility
Method, System, and Non-transitory Computer Readable Recording Medium for Precise User Tracking
5 Aug 21
A user tracking method includes collecting cookies in a log according to a user action on the Internet and collecting chain information by Internet communication as third information different from the cookie, and grouping cookies based on the chain information.
Youngjin KIM, Moweon LEE
Filed: 5 Feb 21
Utility
Content Providing Server, Content Providing Terminal, and Content Providing Method
5 Aug 21
A method for operating a user terminal providing a video slide service includes uploading a UGC video to a server; receiving, from the server, scene metadata information for each reproduction section corresponding to the UGC video; generating a video slide file based on the scene metadata information for each reproduction section; displaying an item corresponding to the video slide file; and displaying a page screen composed of representative image information and subtitle information, for each reproduction section of the UGC video in response to a user selection on the item.
Byung Gyou CHOI, Sung Hyun LEE, Sang Yoon LEE, Jun Oh KIM
Filed: 21 Apr 21
Utility
Automatic Scroll Control Method for Synchronizing Positions of Original Text and Translation, Computer Program and Terminal Device
22 Jul 21
An automatic scroll control method for synchronizing positions of an original text and a translation includes displaying, by a processor of a terminal device, the original text on a first display and displaying the translation corresponding to the original text on a second display; and when the original text or the translation is scrolled by a drag operation of a user, synchronizing the display positions of the original text and the translation with each other.
Yeongje KIM, Hanno LEE, Byungsoo KIM, Jihyun HWANG, Jung Hee BAEK, Jinah PARK, Eunbi JOE, Hyoung Jung KIM
Filed: 15 Jan 21
Utility
Method and system for generating and executing client/server applications
20 Jul 21
There is provided an improvement for developing an application between an application server and one of multiple client devices where the application server is disposed remotely of the one of multiple client devices.
Jose Miguel Perez Alvarez, Adrian Mos
Filed: 15 May 20
Utility
Apparatus, method, and computer-readable recording medium for compactedly displaying popup content
13 Jul 21
An apparatus for compactedly displaying popup content includes a processor configured to execute computer program modules; and a non-transitory computer-readable recording medium configured to store executable computer program modules.
Hyo Kim, Ji Ho Choi, Yun Seok Lee, Sung Mann Cho
Filed: 6 Jun 16