• Title, Summary, Keyword: Title sequence

Search Result 24, Processing Time 0.032 seconds

Automatic Document Title Generation with RNN and Reinforcement Learning (RNN과 강화 학습을 이용한 자동 문서 제목 생성)

  • Cho, Sung-Min;Kim, Wooseng
    • Journal of Information Technology Applications and Management
    • /
    • v.27 no.1
    • /
    • pp.49-58
    • /
    • 2020
  • Lately, a large amount of textual data have been poured out of the Internet and the technology to refine them is needed. Most of these data are long text and often have no title. Therefore, in this paper, we propose a technique to combine the sequence-to-sequence model of RNN and the REINFORCE algorithm to generate the title of the long text automatically. In addition, the TextRank algorithm was applied to extract a summarized text to minimize information loss in order to protect the shortcomings of the sequence-to-sequence model in which an information is lost when long texts are used. Through the experiment, the techniques proposed in this study are shown to be superior to the existing ones.

Kinetic Typography in Korean Film, 2012 (Study on the movie opening title sequence expression studies using kinetic typography) (키네틱 타이포그래피를 활용한 영화 오프닝타이틀 시퀀스 표현연구(2012 흥행작 중심으로))

  • Bang, Yoon-Kyeong
    • Cartoon and Animation Studies
    • /
    • /
    • pp.227-248
    • /
    • 2013
  • With the advancement of computers, opening title sequences in movies are continuously improving. Initially, titles and opening credits were created using what is called the optical method, whereby text was photographed on separate film and then copied onto the movies film negative. In contemporary movie making, however, the title sequence may be seamlessly integrated into the beginning of the movie by an insertion method that not only allows for more diverse technical expression, including the use of both 2D and 3D graphics, but also for its emergence as an independent art form. As such a title sequence, in as little as 50 seconds or up to 10 minutes, is able to convey the films concept while also suggesting more implicit intricacies of plot and thereby eliciting greater interest in the movie. Moreover, according to the directors intent and for a variety of purposes, the title sequence, while maintaining its autonomy, is inseparable from the movie as an organic whole; therefore, it is possible to create works that are highly original in nature. The purpose of this study is to analyze the kinetic typography that appears in title sequences of ten films produced by the Korean entertainment industry in 2012. Production techniques are analyzed in a variety of ways in order to predict the future direction of opening title sequences, as well as present aesthetic and technical models for their creation.

Title Generation Model for which Sequence-to-Sequence RNNs with Attention and Copying Mechanisms are used (주의집중 및 복사 작용을 가진 Sequence-to-Sequence 순환신경망을 이용한 제목 생성 모델)

  • Lee, Hyeon-gu;Kim, Harksoo
    • Journal of KIISE
    • /
    • v.44 no.7
    • /
    • pp.674-679
    • /
    • 2017
  • In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.

A Research on Motion Graphic by Opening Title Sequence of Korea Movie (한국영화 오프닝타이틀 시퀀스를 통한 모션그래픽에 관한 연구)

  • Choi, Ji-Hye;Kim, Chee-Yong
    • Journal of Korea Multimedia Society
    • /
    • v.13 no.4
    • /
    • pp.618-625
    • /
    • 2010
  • Receiving information and transmitting it is the most basic and important thing in numan society. And modern communication is not only transmitting objective information but also a visual communication which shows feeling of each emotions and image-motive. Introduction of Motion graphic which was grown by new media changed opening title sequence to a more expanded genre. The purpose of this research is to announce the new value of opening title sequence. Motion graphic will be used continually as an important way to communicate and also a guideline which could transmit exact informations and emotions to viewers with creative expressions.

A Study of my Fashion Film : A Remediation of the <007 Skyfall Title Sequence> (<007 Skyfall 타이틀 시퀀스>를 재매개화한 패션 필름 연구 : 본인 작품을 중심으로)

  • Kim, Loyou;Kim, Soyoung
    • Proceedings of the Korea Contents Association Conference
    • /
    • /
    • pp.103-104
    • /
    • 2019
  • <007 Skyfall Title Sequence Hommage Film>(2015)(이하 본인작품)은 원작 <007 Skyfall Title Sequence>(2012)(이하 원작)을 패션 필름(fashion film)이라는 새로운 형식의 접근과 재매개화(remediation)를 시도한 본인의 작품이다. 본 연구자는 이 작품에서 오마주(hommage)와 패스티쉬(pastiche)기법을 통해 연작 형태의 007 타이틀 시퀀스 제작방식을 그대로 가져오면서도 패션 필름으로 재목적성을 시도하고자 했다. 본 연구는 형식의 변화 과정에서 나타난 오리지널리티의 왜곡(distortion)과 전환(transformations)으로 인해 '원본에 대한 고유성을 침해하는가, 혹은 오마주나 패스티쉬 기법으로 재생산되어 새로운 창작물로서의 가치를 지니는가'에 대한 문제 제기로부터 출발하였다.

  • PDF

Materiality for Producing the Title Sequence of Film (영화 타이틀시퀀스 제작을 위한 물질성)

  • Shin, Seung-Yun;Kim, Mi-Jin;Mun, Yo-Han
    • The Journal of the Korea Contents Association
    • /
    • v.13 no.10
    • /
    • pp.160-169
    • /
    • 2013
  • The materials used in the title sequence connotes a style & a content of film comprehensively. Therefore, the effect of emotional expression can be changed according to what materials are selected. Thus, the materials of which 42 title sequences are collected for the last 10 years are classified, and the category of materiality & material degree are defined with the semiotic rectangle. To investigate intensity of the material degree, the survey was done. As a result of the survey, the intensity was classified into 3 levels of material degree. The category of materiality used according to the genre of film was analyzed. As a result of the analysis, the materiality was selected according to the content regardless of genre, but there's any difference in the material degree. The intense material degree was used in a thriller and an SF mystery genre, and the medium one was used in the general genre, but, above all, drama and action genre. The weak one was used in a variety of genre, but specifically horror, SF mystery genre. It is significant that this study suggested the expression method in accordance with selection of materials in producing a title sequence to visualize film symbolically.

A Study on the Tendencies of the Motion Graphic Expressions in the Title sequence (타이틀 시퀀스에서 모션그래픽의 표현경향에 관한 연구)

  • Jung, Hee-Jin;Na, Jun-Ki
    • Proceedings of the Korea Contents Association Conference
    • /
    • /
    • pp.195-199
    • /
    • 2006
  • In the field of video design, motion graphics tends to be realized to deliver a certain message properly incorporating basic motion graphics components such as space, form of expression, and time, and has continued to be used as a powerful communication tool. Many cases proved that title sequences were produced as a result of combination of a variety of quick images and effects with appropriately chosen sounds to meet the demands of audience. This study indicated that motion graphics began to be widely used as a more powerful video communication tool for title sequences and also applied for M-NET, DMB, CABLE TV, IPTV, and others.

  • PDF

Restoring Omitted Sentence Constituents in Encyclopedia Documents Using Structural SVM (Structural SVM을 이용한 백과사전 문서 내 생략 문장성분 복원)

  • Hwang, Min-Kook;Kim, Youngtae;Ra, Dongyul;Lim, Soojong;Kim, Hyunki
    • Journal of Intelligence and Information Systems
    • /
    • v.21 no.2
    • /
    • pp.131-150
    • /
    • 2015
  • Omission of noun phrases for obligatory cases is a common phenomenon in sentences of Korean and Japanese, which is not observed in English. When an argument of a predicate can be filled with a noun phrase co-referential with the title, the argument is more easily omitted in Encyclopedia texts. The omitted noun phrase is called a zero anaphor or zero pronoun. Encyclopedias like Wikipedia are major source for information extraction by intelligent application systems such as information retrieval and question answering systems. However, omission of noun phrases makes the quality of information extraction poor. This paper deals with the problem of developing a system that can restore omitted noun phrases in encyclopedia documents. The problem that our system deals with is almost similar to zero anaphora resolution which is one of the important problems in natural language processing. A noun phrase existing in the text that can be used for restoration is called an antecedent. An antecedent must be co-referential with the zero anaphor. While the candidates for the antecedent are only noun phrases in the same text in case of zero anaphora resolution, the title is also a candidate in our problem. In our system, the first stage is in charge of detecting the zero anaphor. In the second stage, antecedent search is carried out by considering the candidates. If antecedent search fails, an attempt made, in the third stage, to use the title as the antecedent. The main characteristic of our system is to make use of a structural SVM for finding the antecedent. The noun phrases in the text that appear before the position of zero anaphor comprise the search space. The main technique used in the methods proposed in previous research works is to perform binary classification for all the noun phrases in the search space. The noun phrase classified to be an antecedent with highest confidence is selected as the antecedent. However, we propose in this paper that antecedent search is viewed as the problem of assigning the antecedent indicator labels to a sequence of noun phrases. In other words, sequence labeling is employed in antecedent search in the text. We are the first to suggest this idea. To perform sequence labeling, we suggest to use a structural SVM which receives a sequence of noun phrases as input and returns the sequence of labels as output. An output label takes one of two values: one indicating that the corresponding noun phrase is the antecedent and the other indicating that it is not. The structural SVM we used is based on the modified Pegasos algorithm which exploits a subgradient descent methodology used for optimization problems. To train and test our system we selected a set of Wikipedia texts and constructed the annotated corpus in which gold-standard answers are provided such as zero anaphors and their possible antecedents. Training examples are prepared using the annotated corpus and used to train the SVMs and test the system. For zero anaphor detection, sentences are parsed by a syntactic analyzer and subject or object cases omitted are identified. Thus performance of our system is dependent on that of the syntactic analyzer, which is a limitation of our system. When an antecedent is not found in the text, our system tries to use the title to restore the zero anaphor. This is based on binary classification using the regular SVM. The experiment showed that our system's performance is F1 = 68.58%. This means that state-of-the-art system can be developed with our technique. It is expected that future work that enables the system to utilize semantic information can lead to a significant performance improvement.

A Study on Omission and Suggestive Expressions in Motion Graphics (모션그래픽에서 생략과 암시적 표현에 관한 연구)

  • Youm, Dong-Cheol
    • Cartoon and Animation Studies
    • /
    • /
    • pp.251-265
    • /
    • 2009
  • Motion Graphics are a great effective vehicle for precise communication between customers in various media and formats. The important thing in the expression of Motion Graphics is to deliver messages clearly. Some current Motion Graphics which are focused on only attracting attention or sensational expressions more than narrative are evaluated lower. This study aims to utilize easy and positive Motion Graphics to deliver messages by applying their utility to production of Motion Graphics, omitting time spent on delivering effective messages and analyzing their suggestive expression methods because of the nature of producing Motion Graphics. This thesis is to study several theoretical backgrounds of omission and implicated expressions mentioned in the similar studies from the view of Motion Graphics, and to search applied examples and functional things using the expression methods in some film title sequence. Excellent Motion Graphics use planned omission and implicated methods rather than to use entire narratives or complicated descriptions. Especially, a film title sequence should focus on symbolic visual expressions. They are necessary to attract the audience's interest. To overcome the limitation of time and space deliver a huge amount of information quickly and powerfully, Motion Graphics should properly use omission of image and time and suggestive expressions through symbols and metaphors. Then they will have a role to level up their current values and discussions.

  • PDF

Patome: Database of Patented Bio-sequences

  • Kim, SeonKyu;Lee, ByungWook
    • Genomics & Informatics
    • /
    • v.3 no.3
    • /
    • pp.94-97
    • /
    • 2005
  • We have built a database server called Patome which contains the annotation information for patented bio-sequences from the Korean Intellectual Property Office (KIPO). The aims of the Patome are to annotate Korean patent bio-sequences and to provide information on patent relationship of public database entries. The patent sequences were annotated with Reference Sequence (RefSeq) or NCBI's nr database. The raw patent data and the annotated data were stored in the database. Annotation information can be used to determine whether a particular RefSeq ID or NCBI's nr ID is related to Korean patent. Patome infrastructure consists of three components­the database itself, a sequence data loader, and an online database query interface. The database can be queried using submission number, organism, title, applicant name, or accession number. Patome can be accessed at http://www.patome.net. The information will be updated every two months.