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
••
TL;DR: The Korea Institute for Advanced Study Value-Added Galaxy Catalog (KIAS VAGC) as mentioned in this paper is a catalog of galaxies based on the Large Scale Structure (LSS) sample of New York University Value-addition Galaxy Catalog Data Release 7.
Abstract: We present the Korea Institute for Advanced Study Value-Added Galaxy Catalog (KIAS VAGC), a catalog of galaxies based on the Large Scale Structure (LSS) sample of New York University Value-Added Galaxy Catalog (NYU VAGC) Data Release 7. Our catalog supplements redshifts of 10,497 galaxies with 10 < rP ≤ 17.6 (1455 with 10 < rP ≤ 14.5) to the NYU VAGC LSS sample. Redshifts from various existing catalogs such as the Updated Zwicky Catalog, the IRAS Point Source Catalog Redshift Survey, the Third Reference Catalogue of Bright Galaxies, and the Two Degree Field Galaxy Redshift Survey have been put into the NYU VAGC photometric catalog. Our supplementation significantly improves spectroscopic completeness: the area covered by the spectroscopic sample with completeness higher than 95% increases from 2.119 to 1.737 sr. Our catalog also provides morphological types of all galaxies that are determined by the automated morphology classification scheme of Park & Choi (2005), and related parameters, together with fundamental photometry parameters supplied by the NYU VAGC. Our catalog contains matches to objects in the Max Planck for Astronomy (MPA) & Johns Hopkins University (JHU) spectrum measurements (Data Release 7). This new catalog, the KIAS VAGC, is complementary to the NYU VAGC and MPA-JHU catalog.
110 citations
••
University of Pretoria1, University of California, Berkeley2, University of Porto3, Leibniz University of Hanover4, African Institute for Mathematical Sciences5, University of Electronic Science and Technology of China6, Council of Scientific and Industrial Research7, University of Waterloo8, Georgia Institute of Technology9, Google10, Carnegie Mellon University11, Lancaster University12, Stellenbosch University13, Naver Corporation14, Technische Universität München15, Jacobs University Bremen16, Pompeu Fabra University17, Florida State University18
TL;DR: The feasibility and scalability of participatory research is demonstrated with a case study on MT for African languages, which leads to a collection of novel translation datasets, MT benchmarks for over 30 languages, with human evaluations for a third of them, and enables participants without formal training to make a unique scientific contribution.
Abstract: Research in NLP lacks geographic diversity, and the question of how NLP can be scaled to low-resourced languages has not yet been adequately solved. "Low-resourced"-ness is a complex problem going beyond data availability and reflects systemic problems in society. In this paper, we focus on the task of Machine Translation (MT), that plays a crucial role for information accessibility and communication worldwide. Despite immense improvements in MT over the past decade, MT is centered around a few high-resourced languages. As MT researchers cannot solve the problem of low-resourcedness alone, we propose participatory research as a means to involve all necessary agents required in the MT development process. We demonstrate the feasibility and scalability of participatory research with a case study on MT for African languages. Its implementation leads to a collection of novel translation datasets, MT benchmarks for over 30 languages, with human evaluations for a third of them, and enables participants without formal training to make a unique scientific contribution. Benchmarks, models, data, code, and evaluation results are released under https://github.com/masakhane-io/masakhane-mt.
109 citations
••
02 Jul 2020TL;DR: This work proposes an automatic audio-visual diarisation method for YouTube videos that consists of active speaker detection using audio- visual methods and speaker verification using self-enrolled speaker models, and integrates this method into a semi-automatic dataset creation pipeline.
Abstract: The goal of this paper is speaker diarisation of videos collected 'in the wild'. We make three key contributions. First, we propose an automatic audio-visual diarisation method for YouTube videos. Our method consists of active speaker detection using audio-visual methods and speaker verification using self-enrolled speaker models. Second, we integrate our method into a semi-automatic dataset creation pipeline which significantly reduces the number of hours required to annotate videos with diarisation labels. Finally, we use this pipeline to create a large-scale diarisation dataset called VoxConverse, collected from 'in the wild' videos, which we will release publicly to the research community. Our dataset consists of overlapping speech, a large and diverse speaker pool, and challenging background conditions.
109 citations
•
24 Oct 2006TL;DR: In this article, a method and system for providing product information, which can retrieve an advertising shopping mall that has suggested a bidding price for an upper display area, and can sort product information of the retrieved advertising shopping malls according to a predetermined standard, and display the sorted product information in the upper display areas and also can sort information according to various types of standards, such as a popularity, a sales volume, and the like, when sorting and displaying product information on a product search result page.
Abstract: A method and system for providing product information, which can retrieve an advertising shopping mall that has suggested a bidding price for an upper display area, and can sort product information of the retrieved advertising shopping mall according to a predetermined standard, and display the sorted product information in the upper display area and also can sort product information according to various types of standards, such as a popularity, a sales volume, and the like, and display the sorted product information in a remaining area excluding the upper display area, when sorting and displaying product information on a product search result page.
109 citations
••
17 Jul 2019TL;DR: In this article, an adversarial attack is used to discover adversarial samples supporting a decision boundary, and the proposed algorithm trains a student classifier based on the adversarial examples supporting the decision boundary.
Abstract: Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good technique for knowledge distillation is still an open problem. In this paper, we provide a new perspective based on a decision boundary, which is one of the most important component of a classifier. The generalization performance of a classifier is closely related to the adequacy of its decision boundary, so a good classifier bears a good decision boundary. Therefore, transferring information closely related to the decision boundary can be a good attempt for knowledge distillation. To realize this goal, we utilize an adversarial attack to discover samples supporting a decision boundary. Based on this idea, to transfer more accurate information about the decision boundary, the proposed algorithm trains a student classifier based on the adversarial samples supporting the decision boundary. Experiments show that the proposed method indeed improves knowledge distillation and achieves the state-of-the-arts performance.
108 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 |