Institution
Naver Corporation
Company•Seongnam-si, South Korea•
About: Naver Corporation is a company organization based out in Seongnam-si, South Korea. It is known for research contribution in the topics: Terminal (electronics) & Computer science. The organization has 4038 authors who have published 4294 publications receiving 35045 citations. The organization is also known as: NAVER Corporation & NAVER.
Papers published on a yearly basis
Papers
More filters
••
Harbin Institute of Technology1, ETH Zurich2, Yonsei University3, Hong Kong Polytechnic University4, Xidian University5, University of Girona6, Toyota Technological Institute7, Baidu8, Ulsan National Institute of Science and Technology9, KAIST10, Amazon.com11, University of Illinois at Urbana–Champaign12, Naver Corporation13, Korea University14, The Catholic University of America15, Guangdong University of Technology16, Sun Yat-sen University17, Dalian Maritime University18, College of Engineering, Trivandrum19
TL;DR: The NTIRE 2020 challenge on perceptual extreme super-resolution as mentioned in this paper focused on super-resolving an input image with a magnification factor ×16 based on a set of prior examples of low and corresponding high resolution images.
Abstract: This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor ×16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.
47 citations
••
13 May 2019
TL;DR: A refined version of GAN, named RAGANBT, aiming to alleviate the data sparsity problem in collaborative filtering (CF), eventually improving recommendation accuracy significantly and providing existing CF models with great improvement in accuracy under various situations.
Abstract: Generative Adversarial Networks (GAN) have not only achieved a big success in various generation tasks such as images, but also boosted the accuracy of classification tasks by generating additional labeled data, which is called data augmentation. In this paper, we propose a Rating Augmentation framework with GAN, named RAGAN, aiming to alleviate the data sparsity problem in collaborative filtering (CF), eventually improving recommendation accuracy significantly. We identify a unique challenge that arises when applying GAN to CF for rating augmentation: naive RAGAN tends to generate values biased towards high ratings. Then, we propose a refined version of RAGAN, named RAGANBT, which addresses this challenge successfully. Via our extensive experiments, we validate that our RAGANBT is really effective to solve the data sparsity problem, thereby providing existing CF models with great improvement in accuracy under various situations such as basic top-N recommendation, long-tail item recommendation, and recommendation to cold-start users.
46 citations
•
TL;DR: The authors compare various ways to integrate pretrained BERT model with NMT model and study the impact of the monolingual data used for BERT training on the final translation quality.
Abstract: Exploiting large pretrained models for various NMT tasks have gained a lot of visibility recently. In this work we study how BERT pretrained models could be exploited for supervised Neural Machine Translation. We compare various ways to integrate pretrained BERT model with NMT model and study the impact of the monolingual data used for BERT training on the final translation quality. We use WMT-14 English-German, IWSLT15 English-German and IWSLT14 English-Russian datasets for these experiments. In addition to standard task test set evaluation, we perform evaluation on out-of-domain test sets and noise injected test sets, in order to assess how BERT pretrained representations affect model robustness.
46 citations
••
23 Aug 2020TL;DR: A tightly coupled single pipeline model that allows feature rectification and boundary localization of arbitrary-shaped text regions and demonstrates state-of-the-art performance in publicly available straight and curved benchmark dataset is constructed.
Abstract: A scene text spotter is composed of text detection and recognition modules. Many studies have been conducted to unify these modules into an end-to-end trainable model to achieve better performance. A typical architecture places detection and recognition modules into separate branches, and a RoI pooling is commonly used to let the branches share a visual feature. However, there still exists a chance of establishing a more complimentary connection between the modules when adopting recognizer that uses attention-based decoder and detector that represents spatial information of the character regions. This is possible since the two modules share a common sub-task which is to find the location of the character regions. Based on the insight, we construct a tightly coupled single pipeline model. This architecture is formed by utilizing detection outputs in the recognizer and propagating the recognition loss through the detection stage. The use of character score map helps the recognizer attend better to the character center points, and the recognition loss propagation to the detector module enhances the localization of the character regions. Also, a strengthened sharing stage allows feature rectification and boundary localization of arbitrary-shaped text regions. Extensive experiments demonstrate state-of-the-art performance in publicly available straight and curved benchmark dataset.
46 citations
•
18 Aug 2005TL;DR: In this article, a character service method and system having a game item function is described, and a method is provided for generating a character by a character generating system including a gamvatar provider, game server, and avatar.
Abstract: Disclosed is a character service method and system having a game item function. In one embodiment, a method is provided for generating a character by a character generating system including a gamvatar provider, a gamvatar controller, and a game server. The method includes providing an avatar to a user accessing the character generating system online, checking whether the user desires to combine a game item function with the avatar before progressing a game when the user acquires the game item function, combining the game item function with a corresponding layer of the avatar when the user desires to combine the game item function with the avatar, and d) generating the combined gamvatar.
45 citations
Authors
Showing all 4041 results
Name | H-index | Papers | Citations |
---|---|---|---|
Andrea Vedaldi | 89 | 305 | 63305 |
Sunghun Kim | 51 | 115 | 12994 |
Eric Gaussier | 41 | 231 | 8203 |
Un Ju Jung | 39 | 98 | 5696 |
Hyun-Soo Kim | 37 | 421 | 5650 |
Gabriela Csurka | 37 | 145 | 10959 |
Nojun Kwak | 34 | 234 | 6026 |
Young-Jin Park | 31 | 257 | 3759 |
Sung Joo Kim | 31 | 196 | 3078 |
Jae-Hoon Kim | 30 | 323 | 5847 |
Jung-Ryul Lee | 29 | 222 | 3322 |
Joon Son Chung | 28 | 73 | 4900 |
Ok-Hwan Lee | 27 | 163 | 2896 |
Diane Larlus | 27 | 69 | 4722 |
Jung Goo Lee | 26 | 142 | 1917 |