• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.865-868
• /
• 2017

일반적으로 비디오로부터 캡션을 생성하는 작업은 입력 비디오로부터 특징을 추출해내는 과정과 추출한 특징을 이용하여 캡션을 생성해내는 과정을 포함한다. 본 논문에서는 효과적인 비디오 캡션 생성을 위한 심층 신경망 모델과 그 학습 방법을 소개한다. 본 논문에서는 입력 비디오를 표현하는 시각 특징 외에, 비디오를 효과적으로 표현하는 동적 의미 특징과 정적 의미 특징을 입력 특징으로 이용한다. 본 논문에서 입력 비디오의 시각 특징들은 C3D, ResNet과 같은 합성곱 신경망을 이용하여 추출하지만, 의미 특징은 본 논문에서 제안하는 의미 특징 추출 네트워크를 활용하여 추출한다. 그리고 이러한 특징들을 기반으로 비디오 캡션을 효과적으로 생성하기 위하여 선택적 주의집중 캡션 생성 네트워크를 제안한다. Youtube 동영상으로부터 수집된 MSVD 데이터 집합을 이용한 다양한 실험을 통해, 본 논문에서 제안한 모델의 성능과 효과를 확인할 수 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2155-2160
• /
• 2014

In this paper, we proposes a new document summarization method using the extracted semantic feature which the semantic feature is extracted by distributed parallel processing based Hadoop. The proposed method can well represent the inherent structure of documents using the semantic feature by the non-negative matrix factorization (NMF). In addition, it can summarize the big data document using Hadoop. The experimental results demonstrate that the proposed method can summarize the big data document which a single computer can not summarize those.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.3
• /
• pp.533-540
• /
• 2012

In this paper, we propose a document summarization method using the pseudo relevance feedback and the term weighting based on semantic features. The proposed method can minimize the user intervention to use the pseudo relevance feedback. It also can improve the quality of document summaries because the inherent semantic of the sentence set are well reflected by term weighting derived from semantic feature. In addition, it uses the semantic feature of term weighting and the expanded query to reduce the semantic gap between the user's requirement and the result of proposed method. The experimental results demonstrate that the proposed method achieves better performant than other methods without term weighting.

• Journal of Digital Contents Society
• /
• v.15 no.6
• /
• pp.701-710
• /
• 2014

The analysis on the characteristics of the signification system of Japanese feature-length animations that this essay centrally deals with eventually examines the characteristics of representation and communication in Japanese feature-length animations. In general, most animation works focusing on characters and stories contain the signification systems related to 'denotation' and connotation.' However, tendency of the aesthetic representation and communication that appears differently, depending on the characteristics of the signification system that each animation work pursues. From this point of view, Japanese feature-length animation emphasizes connotative signification system and aesthetic representation, unlike Disney animation that strongly shows the tendency that makes the audience directly immersed in the theme and message of the work conveyed further in the myths by pursuing denotative signification system. And, in the case of Japanese feature-length animation, the 'dissenting and arbitrary interpretation' of the theme, the message that the animation work intends to convey and myths pursued is bound to appear diversely, depending on the audience's experiences and cultural and social backgrounds.

• Journal of Internet Computing and Services
• /
• v.13 no.4
• /
• pp.1-10
• /
• 2012

In this paper, an optimal feature selection method considering sematic of features, which is preprocess of document classification is proposed. The feature selection is very important part on classification, which is composed of removing redundant features and selecting essential features. LSA (Latent Semantic Analysis) for considering meaning of the features is adopted. However, a supervised LSA which is suitable method for classification problems is used because the basic LSA is not specialized for feature selection. We also apply GA (Genetic Algorithm) to the features, which are obtained from supervised LSA to select better feature subset. Finally, we project documents onto new selected feature subset and classify them using specific classifier, SVM (Support Vector Machine). It is expected to get high performance and efficiency of classification by selecting optimal feature subset using the proposed hybrid method of supervised LSA and GA. Its efficiency is proved through experiments using internet news classification with low features.

• Annual Conference on Human and Language Technology
• /
• 1999.10e
• /
• pp.304-309
• /
• 1999

본 논문에서는 의미계층구조에 나타난 유사어 정보를 이용해서 단어 의미 중의성을 해결하고자 한다. 의미계층구조를 이용한 기존의 방법에서는 의미 벡터를 이용해서 단어 의미 중의성을 해결했다. 의미 벡터는 의미별 학습 자료에서 획득되는 것으로 유사어들의 공통적인 특징만을 이용하고, 유사어 개별 특징은 이용하지 않는다. 본 논문에서는 유사어 개별 특징을 이용하기 위해서 유사어 벡터를 이용해서 단어 의미 중의성을 해결한다. 유사어 벡터는 유사어별 학습 자료에서 획득되는 것으로, 유사어의 개별 정보를 가지고 있는 벡터이다. 세 개의 한국어 명사에 대한 실험 결과, 의미 벡터를 이용하는 것보다 유사어 벡터를 이용하는 경우에 평균 9.5%정도의 성능향상이 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.11
• /
• pp.2374-2381
• /
• 2012

This paper proposes a new enhancing snippet extraction method using fuzzy and semantic features. The proposed method creates a delegate of sentence by using semantic features. It extracts snippet using fuzzy association between a delegate sentence and sentence set which well represents query. In addition, the method uses pseudo relevance feedback to expand query which extracts snippet to be well reflected semantic user's intention. The experimental results demonstrate the proposed method can achieve better snippet extraction performance than the previous methods.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.11a
• /
• pp.1-3
• /
• 2005

통계 소프트웨어 R은 여러 가지 특징을 가진 도구이다. S라는 전산언어를 기반으로 하고 이에 수학함수와 통계함수, 그리고 그래픽함수들이 결합되어 편리한 계산 작업 환경을 제공하고 있다. R이 기반으로 하고 있는 S언어에는 문법적, 의미론적 특징이 잘 어울려 있다. S언어의 주요 특징 중 하나는 객체지향성이다. 본 연구에서는 R의 특징인 객체지향성과 그 의미에 대하여 살펴보게 된다.

• Journal of Advanced Navigation Technology
• /
• v.12 no.4
• /
• pp.372-377
• /
• 2008

This paper proposes a new query-based document summarization method using the semantic feature matrix and the semantic variable matrix. The proposed method doesn't need the training phase using training data comprising queries and query specific documents. And it exactly summarizes documents for the given query by using semantic features and semantic variables that is better at identifying sub-topics of document. Because the NMF have a great power to naturally extract semantic features representing the inherent structure of a document. The experimental results show that the proposed method achieves better performance than other methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.53-60
• /
• 2012

In this paper, we proposes a new document summarization method using the expanded query by wikipedia and the semantic feature representing inherent structure of document set. The proposed method can expand the query from user's initial query using the relevance feedback based on wikipedia in order to reflect the user require. It can well represent the inherent structure of documents using the semantic feature by the non-negative matrix factorization (NMF). In addition, it can reduce the semantic gap between the user require and the result of document summarization to extract the meaningful sentences using the expanded query and semantic features. The experimental results demonstrate that the proposed method achieves better performance than the other methods to summary document.