• Journal of Korea Multimedia Society
• /
• v.10 no.8
• /
• pp.967-980
• /
• 2007

Video objects of interest play an important role in representing the video content and are useful for improving the performance of video retrieval and compression. The objects of interest may be a main object in describing contents of a video shot or a core object that a video producer wants to represent in the video shot. We know that any object attracting one's eye much in the video shot may not be an object of interest and a non-moving object may be an object of interest as well as a moving one. However it is not easy to define an object of interest clearly, because procedural description of human interest is difficult. In this paper, a set of four filtering conditions for extracting moving objects of interest is suggested, which is defined by considering variation of location, size, and moving pattern of moving objects in a video shot. Non-moving objects of interest are also defined as another set of four extracting conditions that are related to saliency of color/texture, location, size, and occurrence frequency of static objects in a video shot. On a test with 50 video shots, the segmentation method based on the two sets of conditions could extract the moving and non-moving objects of interest chosen manually on accuracy of 84%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.181-184
• /
• 2005

기존의 비디오 분할 방법은 밝기의 변화가 큰 영상이나 움직임이 큰 영상에 대해서는 정확한 분할이 이루어지지 않았다. 본 논문은 움직임 정보를 이용하여 움직임이 큰 영상에서 좀 더 정확하게 비디오를 분할할 수 있는 방법을 제안한다. 이를 위해 블록 정합 알고리즘을 이용하여 얻어진 움직임 벡터로부터 움직임 유사도를 찾는 방법을 제안한다. 또 연속된 프레임에서 픽셀의 차이 값을 계산할 때 motion blur 로 생기는 오차를 각 블록의 움직임 크기로 보상하여 좀 더 정확한 픽셀의 차이 값을 계산하는 방법을 제안한다. 이렇게 얻어진 두 가지 정보를 이용하여 discontinuity value 를 계산한다. 움직임이 많은 액션 영화 3 편에 대해 실험한 결과 제안한 방법이 기존의 움직임 유사도와 픽셀 차이 값을 구하여 샷 경계 검출을 하는 방법보다 좀 더 정확한 샷 경계 검출을 하고 있다는 것을 보여준다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.531-534
• /
• 2012

기존의 히스토그램을 이용한 샷 전환 탐지 방법은 연속적인 두 프레임의 전체 또는 대응되는 동일한 크기의 소 영역의 히스토그램을 사용하며, 객체의 이동이나, 프레임의 밝기 변화에 취약한 문제점이 있다. 본 논문에서는 이 문제점들을 해결하기 위하여 연속적인 두 프레임(현재와 참조 프레임)을 소영역으로 분할한 후, 현재 프레임의 소 영역과 두 프레임사이에서 발생할 수 있는 객체의 이동을 고려한 참조 프레임에서의 소 영역의 비교, 그리고 참조 프레임의 소 영역에서 얻은 화소 밝기 히스토그램에 밝기 변화를 보상한 후, 현재 프레임의 소 영역에서 얻은 화소 밝기 히스토그램과 비교하는 방법을 제안한다. 제안한 방법은 영화와 뉴스 같은 비디오 데이터에 좋은 결과를 보였다.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.35-43
• /
• 2021

Recently, there has been a growing interest in zero-shot cross-lingual transfer, which leverages cross-lingual language models (CLLMs) to perform downstream tasks that are not trained in a specific language. In this paper, we point out the limitations of the data-centric aspect of quality estimation (QE), and perform zero-shot cross-lingual transfer even in environments where it is difficult to construct QE data. Few studies have dealt with zero-shots in QE, and after fine-tuning the English-German QE dataset, we perform zero-shot transfer leveraging CLLMs. We conduct comparative analysis between various CLLMs. We also perform zero-shot transfer on language pairs with different sized resources and analyze results based on the linguistic characteristics of each language. Experimental results showed the highest performance in multilingual BART and multillingual BERT, and we induced QE to be performed even when QE learning for a specific language pair was not performed at all.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.54-56
• /
• 2000

데이터 마이닝 작업에서 사용되는 데이터의 크기는 그 특성상 대규모를 이루고 있다. 이러한 대규모의 데이터로부터 규칙을 추출하는 작업은 많은 배용이 소모된다. 또한 급변하는 데이터는 이미 발견된 마이닝 패턴에 대하여 현저한 패턴은 약한 패턴으로, 반면 약한 패턴은 현저한 패턴으로 변화시키는 요인이 되고 있다. 이러한 동적 환경에서는 기존의 데이터베이스 특정시간의 스냅 샷 형태의 데이터를 이용하였던 마이닝 방법으로는 적당하지 못하다. 따라서 이 논문에서는 동적인 환경에서 적용할 수 있는 점진적 마이닝 방법을 제시하고, 점진적 마이닝 작업이 효과적으로 수행 가능한 능동시스템 모델을 제시한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.263-267
• /
• 2009

With the increase of weight and influence of TV drama, Many researchers began to publish papers on TV drama. However, Those papers were mainly about social meaning of TV drama and viewing motives and attitudes of TV audience. However, only a few limited papers were about television image production techniques. The purpose of this thesis is to analyse the relationship between TV genre and image production technique with the data of top 100 of TNS Media Korea from the year 2004 to 2008. This paper found out that history drama uses more closeup, longshot, tracking and less waist shot than other genres, with shorter shot duration and longer scene duration.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.11_12
• /
• pp.587-597
• /
• 2005

Flash memory based embedded computing systems are becoming increasingly prevalent.These systems typically have to provide an instant start-up time. However, we observe that mounting a file system toy flash memory takes 1 to 25 seconds mainly depending on the flash capacity. Since the flash chip capacity is doubled in every year, this mounting time will soon become the most dominant reason of the delay of system start-up time Therefore, in this paper, we present instant mounting techniques for flash file systems by storing the In-memory file system metadata to flash memory when unmounting the file system and reloading the stored metadata quickly when mounting the file system. These metadata snapshot techniques are specifically developed for NOR- and NAND-type flash memories, while at the same time, overcoming their physical constraints. The proposed techniques check the validity of the stored snapshot and use the proposed fast trash recovery techniques when the snapshot is Invalid. Based on the experimental results, the proposed techniques can reduce the flash mounting time by about two orders of magnitude over the existing de facto standard flash file system, JFFS2.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.159-167
• /
• 2009

With the increase of weight and influence of TV drama, many researchers began to publish papers on TV drama. However, those papers were mainly focused on social meaning and viewing motives and attitudes of TV audience. However, only a few papers researched about television image production techniques, such as 'Relationship between TV ratings and image production techniques', 'Transition process of TV drama's image production techniques', and 'Comparison of TV and film image production techniques'. According to the recent research on the relationship between TV ratings and image production techniques, TV rating is inverse proportionate to multiple camerawork and shot average duration with a very close relationship. The purpose of this thesis is to analyse the relationship between TV genre and image production technique with the data of top 100 of TNS Media Korea from the year 2004 to 2008. This paper found out that history drama uses more closeup, longshot, tracking and less waist shot than other genres, with shorter shot duration and longer scene duration.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.399-403
• /
• 2023

본 논문에서는 다중 문서 기반의 대화 시스템을 통한 효율적인 정보 검색과 응답 생성에 중점을 둡니다. 대규모 데이터 집합에서 정확한 문서를 선택하는 데 필요한 검색의 중요성을 강조하며, 현재 검색 방법의 한계와 문제점을 지적합니다. 또한 더 자연스러운 답변을 생성하기 위해 대규모 언어 모델을 사용하게 되면서 fine-tuning 시에 발생하는 제약과 낭비를 모델의 제로샷 생성 능력을 활용하여 개선하려는 방안을 제안하며, 모델의 크기와 자원의 효율성에 대한 고려사항을 논의합니다. 우리의 접근 방식은 대규모 언어 모델을 프롬프트와 함께 다중 문서로 학습 없이 정보를 검색하고 응답을 생성하는 방향으로 접근하여 대화 시스템의 효율성과 유용성을 향상시킬 수 있음을 제시합니다.

• The Journal of the Korea Contents Association
• /
• v.6 no.8
• /
• pp.184-191
• /
• 2006

The purpose of this case study is to understand the characteristics and implication of videojournalist's image expression techniques in the television news programs, comparing with television camera reporter's image expression techniques. Texts chosen in this thesis are 120 programs of KBS2TV 'News Time' which had been on air from July to December in 2005. Shot size, camerawork, shot duration and camera angle of the images were analysed, which had been extracted through the processes of thematic classification. The results of the analysis of thematic classification shows us that videojournalist covered mainly social, economic and cultural news items, almost completely alienated in the fields of hard news as political and health-scientific news items which were very sensitive and influential on the life of the entire people of the nation. The results of the analysis on the characteristics of image expression reveals that videojournalist used one-shot more often than the camera reporter, showing us videojournalist's preference of close news gathering, and videojournalist used following and zooming much more often than camera reporter, showing us videojoumalist's preference of mobile and dynamic cameraworks, and videojournalist used low angles more often than camera reporter, also showing us videojoumalist's preference of candid camera style news gathering.