• 비교문화연구
• /
• 제36권
• /
• pp.271-291
• /
• 2014

In this paper, we maintain that case makers '에e' and '에게ege', and '에서eseo' and '에게서egeseo' are not two separate morphemes but are simply allomorphs of the same morphemes respectively. When '에e' and '에게ege' are used as a dative marker, they show exactly the same semantic function and are in complementary distribution in relation to the semantic features of their preceding noun; that is, if the preceding noun is an animate noun, '에게ege' is used and '에e' is used if not. Also, '에게서egeseo' and '에서eseo' as ablative and locative case makers show exactly the same semantic function and show complementary distribution depending on whether the preceding noun is animate or non-animate. Therefore, we assume that these markers are semantically conditioned allomorphs.

• 한국전자통신학회논문지
• /
• 제8권3호
• /
• pp.409-414
• /
• 2013

이미지와 같은 멀티미디어 정보들의 증가로 저수준의 시각 정보에서 고수준의 의미 정보를 추출하는 방법에 대한 연구가 이루어지고 있으며, 이러한 정보를 자동으로 생성하는 다양한 기술들이 연구되고 있다. 그러나 이러한 기술들은 대부분 한 장의 이미지와 이미지 사이의 의미 정보를 추출하므로 이미지내에 여러 객체가 같이 있는 경우 의미 정보를 추출하기 어렵다. 본 논문에서는 이미지내의 객체들을 시각적 특징 정보들을 추출하여 트레이닝 이미지를 DB에 저장하고 유사도를 측정하여 각 객체의 특징들을 정의한다. 이미지내의 각 객체 특징들은 온톨로지로 이용하여 위치 관계와 연관 관계를 추론엔진을 통해 의미 정보를 추론한다. 이로써 이미지내 객체들 사이의 의미 정보 추론이 가능하고, 좀 더 복잡하고 다양한 고수준의 의미 정보를 추론하는 방법을 제안한다.

• 한국멀티미디어학회논문지
• /
• 제11권2호
• /
• pp.143-152
• /
• 2008

비디오 데이터에 대한 의미적 검출을 위해 이벤트 표현에 대한 많은 방법론이 연구되고 있지만, 아직도 저차원 특징을 이용한 내용기반 검출과 각 데이터에 주석을 정의한 주석기반 검출 방법이 대부분이다. 본 논문은 기존의 방법보다 의미적인 검색을 위해 객체 움직임 단위 생성과 이를 통한 이벤트 검출 기법을 제안한다. 첫째, 이벤트 단위로 움직임을 분류한다. 둘째, 분류된 객체 움직임에 대한 의미적 단위를 정의하고 이를 이벤트 검출에 이용하기 위해 저차원 특징과 매핑 가능한 규칙을 생성한다. 이를 통해 비디오 샷 단위의 의미적 이벤트 검출을 가능하게 한다. 제안된 내용의 유용성 평가를 위해 우리는 비디오 영상 이벤트 검출을 실험한 결과 약 80%의 정확률을 얻었다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제35권5호
• /
• pp.306-312
• /
• 2008

목적 지향성 대화에서 화자의 의도는 화행과 개념열 쌍으로 구성되는 의미 구조로 근사화될 수 있다. 그러므로 지능형 대화 시스템을 구현하기 위해서는 의미 구조를 올바르게 파악하는 것이 매우 중요하다. 본 논문에서는 능동학습(active learning) 방법을 이용하여 효율적으로 의미 구조를 분석하는 모델을 제안한다. 제안 모델은 언어 분석에 따른 부담을 덜기위하여 형태소 자질들과 이전 의미 구조만을 입력 자질로 사용한다. 그리고 정확률 향상을 위하여 자연어 처리 분야에서 높은 성능을 보이고 있는 CRFs(Conditional Random Fields)를 기본 통계 모델로 사용한다. 일정 관리 영역에서 제안 모델을 실험한 결과는 기존 모델들과 비교하여 1/3 정도의 훈련데이타를 사용하고도 비슷한 정확률(화행 92.4%, 개념열 89.8%)을 나타내고 있음을 알 수 있었다.

• 한국의상디자인학회지
• /
• 제18권1호
• /
• pp.135-147
• /
• 2016

The purpose of this research is to study the semantic characteristics of outdoor brand names by analyzing 94 brand names in domestic market, so as to propose ways to develop strategic brand names. The results are as follows. When it comes to outdoor brand products, the emphasis is placed on their functional features. Thus, the majority of outdoor brands surveyed in this Study were using strategic descriptive brand names which clearly denote the properties and effects of the relevant products to leave lasting impressions on consumers'minds. In other words, the outdoor brands surveyed herein were using brands which inform consumers of the specific business and product categories, express the concept of the brands, and provide them with information on the features and benefits of the products such as high quality, high-class, and luxurious lifestyle. In conclusion, the components of outdoor brand names are crucial elements which symbolize the concepts, functions or features of the relevant brands. In order to develop brand names consisting of components which build brand powers and enhance brand images, it is imparetive to develop more unique and characteristic brand names.

• 한국정보통신학회논문지
• /
• 제17권2호
• /
• pp.347-354
• /
• 2013

본 논문은 확장된 용어를 기반으로 용어의 가중치를 재산정하여 문서군집의 성능을 향상시키는 방법을 제안한다. 제안된 방법은 의미특징을 이용하여 군집문서의 중요 용어를 추출하고, 워드넷을 이용하여 용어를 확장함으로서 문서의 주제를 잘 나타낼 수 있다. 또한 확장된 용어를 기반으로 하여 용어의 가중치를 재산정함으로써 문서군집의 성능을 높일 수 있다. 실험결과 제안방법을 적용한 문서군집방법이 적용하지 않은 문서군집 방법에 비해서 좋은 성능을 보인다.

• Journal of Information Processing Systems
• /
• 제9권3호
• /
• pp.349-364
• /
• 2013

The big challenge in current content-based image retrieval systems is to reduce the semantic gap between the low level-features and high-level concepts. In this paper, we have proposed a novel framework for efficient image retrieval to improve the retrieval results significantly as a means to addressing this problem. In our proposed method, we first extracted a strong set of image features by using the dual-tree rotated complex wavelet filters (DT-RCWF) and dual tree-complex wavelet transform (DT-CWT) jointly, which obtains features in 12 different directions. Second, we presented a relevance feedback (RF) framework for efficient image retrieval by employing a support vector machine (SVM), which learns the semantic relationship among images using the knowledge, based on the user interaction. Extensive experiments show that there is a significant improvement in retrieval performance with the proposed method using SVMRF compared with the retrieval performance without RF. The proposed method improves retrieval performance from 78.5% to 92.29% on the texture database in terms of retrieval accuracy and from 57.20% to 94.2% on the Corel image database, in terms of precision in a much lower number of iterations.

• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.685-694
• /
• 2022

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.

• 한국멀티미디어학회논문지
• /
• 제22권9호
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

• 한국CDE학회논문집
• /
• 제9권2호
• /
• pp.167-174
• /
• 2004

As the networks connect the world, enterprises tend to move manufacturing activities into virtual spaces. Since different applications use different data terminology, it becomes a problem to interoperate, interchange, and manage electronic data among different systems. According to RTI, approximately one billion dollar has been being spent yearly for product data exchange and interoperability. As commercial CAD systems have brought in the concept of design feature for the sake of interoperability, terminologies of design feature need to be harmonized. In order to define design feature terminology for integration, knowledge about feature definitions of different CAD systems should be considered. STEP (Standard for the Exchange of Product model data) have attempted to solve this problem, but it defines only syntactic data representation so that semantic data integration is unattainable. In this paper, we utilize the ontology concept to build a data model of design feature which can be a semantic standard of feature definitions of CAD systems. Using feature ontology, we implement an integrated virtual database and a simple system which searches and edits design features in a semantic way. This paper proposes a methodology for integrating modeling features of CAD systems.