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
••
26 Mar 2020TL;DR: This paper proposed a metric learning objective for open-set speaker recognition, where ideal embeddings should be able to condense information into a compact utterance-level representation that has small intra-speaker and large inter-Speaker distance.
Abstract: The objective of this paper is 'open-set' speaker recognition of unseen speakers, where ideal embeddings should be able to condense information into a compact utterance-level representation that has small intra-speaker and large inter-speaker distance.
A popular belief in speaker recognition is that networks trained with classification objectives outperform metric learning methods. In this paper, we present an extensive evaluation of most popular loss functions for speaker recognition on the VoxCeleb dataset. We demonstrate that the vanilla triplet loss shows competitive performance compared to classification-based losses, and those trained with our proposed metric learning objective outperform state-of-the-art methods.
199 citations
•
25 Feb 2005TL;DR: In this paper, a method for generating a search result list by reflecting importance information in processing the search result lists corresponding to a predetermined keyword input from a user terminal by a search engine and a system thereof is presented.
Abstract: The present invention relates to a method for providing a search result list by a search engine and a system thereof, and more particularly, to a method for generating a search result list by reflecting importance information in processing the search result list corresponding to a predetermined keyword input from a user terminal by a search engine and a system thereof. According to the present invention, there is an effect that is possible to provide method and system for providing a search result list, capable of providing a search result list on the basis of importance information in which accuracy and information on the registration date of a corresponding content are reflected.
199 citations
••
01 Oct 2019TL;DR: Wang et al. as mentioned in this paper proposed a wavelet corrected transfer based on whitening and coloring transforms (WCT2) that allows features to preserve their structural information and statistical properties of VGG feature space during stylization.
Abstract: Recent style transfer models have provided promising artistic results. However, given a photograph as a reference style, existing methods are limited by spatial distortions or unrealistic artifacts, which should not happen in real photographs. We introduce a theoretically sound correction to the network architecture that remarkably enhances photorealism and faithfully transfers the style. The key ingredient of our method is wavelet transforms that naturally fits in deep networks. We propose a wavelet corrected transfer based on whitening and coloring transforms (WCT2) that allows features to preserve their structural information and statistical properties of VGG feature space during stylization. This is the first and the only end-to-end model that can stylize a 1024x1024 resolution image in 4.7 seconds, giving a pleasing and photorealistic quality without any post-processing. Last but not least, our model provides a stable video stylization without temporal constraints. Our code, generated images, pre-trained models and supplementary documents are all available at https://github.com/ClovaAI/WCT2.
197 citations
•
04 Jun 2016TL;DR: In this article, a multimodal residual network (MRN) was proposed to learn the joint representation from visual and language information, which achieved state-of-the-art results on the Visual QA dataset for both Open-Ended and Multiple-Choice tasks.
Abstract: Deep neural networks continue to advance the state-of-the-art of image recognition tasks with various methods. However, applications of these methods to multimodality remain limited. We present Multimodal Residual Networks (MRN) for the multimodal residual learning of visual question-answering, which extends the idea of the deep residual learning. Unlike the deep residual learning, MRN effectively learns the joint representation from visual and language information. The main idea is to use element-wise multiplication for the joint residual mappings exploiting the residual learning of the attentional models in recent studies. Various alternative models introduced by multimodality are explored based on our study. We achieve the state-of-the-art results on the Visual QA dataset for both Open-Ended and Multiple-Choice tasks. Moreover, we introduce a novel method to visualize the attention effect of the joint representations for each learning block using back-propagation algorithm, even though the visual features are collapsed without spatial information.
196 citations
•
14 Oct 2016TL;DR: The authors proposed low-rank bilinear pooling using Hadamard product for multimodal learning, which outperforms compact bilinearly pooling in visual question-answering tasks.
Abstract: Bilinear models provide rich representations compared with linear models. They have been applied in various visual tasks, such as object recognition, segmentation, and visual question-answering, to get state-of-the-art performances taking advantage of the expanded representations. However, bilinear representations tend to be high-dimensional, limiting the applicability to computationally complex tasks. We propose low-rank bilinear pooling using Hadamard product for an efficient attention mechanism of multimodal learning. We show that our model outperforms compact bilinear pooling in visual question-answering tasks with the state-of-the-art results on the VQA dataset, having a better parsimonious property.
191 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 |