Exploiting character networks for movie summarization

Movie summarization focuses on providing as much information as possible for shorter movie clips while still keeping the content of the original movie and presenting a faster way for the audience to understand the movie. In this paper, we propose a novel method to summarize a movie based on character network analysis and the appearance of protagonist and main characters in the movie. Experiments were carried out for 2 movies (Titanic (1997) and Frozen (2013)) to show that our method outperforms conventional approaches in terms of the movie summarization rate.     

Remembering Bogle Chandler: an exploration of new media's storytelling potential

Remembering Bogle Chandler is a digital narrative that incorporates photos, line drawings, text and sound playable using a graphical user interface (GUI). The work describes the characters and events surrounding the mysterious deaths of Gilbert Bogle and Margaret Chandler in Sydney on New Year's Day 1963. Users can retrieve and play 104 movie clips (photographic images, animations, text and sound) from the project's digital library. The GUI is both an image illustrating connections between movie clips and an instrument for controlling them.

Remembering Bogle Chandler tells an old story in a new way. In order to explore the novel qualities of the work, this article employs terminology and concepts from three essentialist theories of digital media that define the ways in which digital media differ from old or legacy media. To assess the impact of these properties on storytelling, the article also explores audience responses to the work.     

Movie story intensity representation through audiovisual tempo analysis

A comprehensive method for movie abstraction is developed in this research for applications in fast movie content exploring, indexing, browsing, and skimming, Most current approaches rely heavily on specific domain knowledge or models to identify and extract the determining scenes of a given movie; however, the segments extracted are often isolated, presenting a fragmented outline of the original. Our proposed method fuses simple audiovisual features, and measures the “tempos” of a movie directly, especially that of long-term ones. These tempos form a curve that catches the high-level semantics of a movie, indicating the events of interests named as “story intensity.” Through tempo, the proposed algorithm provides a natural way that segments a movie into manageable parts. As our experimental results demonstrate, the condensed skimming clips efficiently extract semantic content that contains the most interesting and informative parts of the original movie.

Ranking highlight level of movie clips: A template based adaptive kernel SVM method

This paper looks into a new direction in movie clips analysis – model based ranking of highlight level. A movie clip, containing a short story, is composed of several continuous shots, which is much simpler than the whole movie. As a result, clip based analysis provides a feasible way for movie analysis and interpretation. In this paper, clip-based ranking of highlight level is proposed, where the challenging problem in detecting and recognizing events within clips is not required. Due to the lack of publicly available datasets, we firstly construct a database of movie clips, where each clip is associated with manually derived highlight level as ground truth. From each clip a number of effective visual cues are then extracted. To bridge the gap between low-level features and highlight level semantics, a holistic method of highlight ranking model is introduced. According to the distance between testing clips and selected templates, appropriate kernel function of support vector machine (SVM) is adaptively selected. Promising results are reported in automatic ranking of movie highlight levels.     

The fashion blog as genre—between user-driven bricolage design and the reproduction of established fashion system

Abstract

Fashion as a phenomenon cannot be understood independently of the visual images and designed presentations that convey the content and forms of fashion. With the breakthrough of the digital media in the 2000s we were introduced to new ways of communicating and staging fashion where the blog in particular has established a new media culture for the distribution and exchange of potential fashion-based self-presentation forms and resulted in new design strategies. In this article, the fashion blog is presented as a specific genre that is characterised by remediating existing genre forms and combining them into new formats, where amateur bricolage approaches are combined with the reproduction of familiar features from the established fashion media. The article presents four types of fashion blogs, each representing a specific design strategy for presenting and interacting with fashion content. In closing, it is argued that the fashion blog as a phenomenon, on the one hand, has placed the ordinary fashion consumer centre stage as a producer of fashion content while also, on the other hand, helping to consolidate established hierarchical and communicative structures in the fashion system.     

融合视音频特征的影片摘要生成方法

提出了融合视音频特征的影片摘要生成算法。以特写人脸检测、紧张、激烈镜头检测作为选取重要视频片段的依据。针对影片语音端点难以检测的问题,利用影片字幕文件提取影片语音首尾时间以及语音内容,从而实现了影片语音端点的准确检测。实验证明,该方法生成的影片摘要具有较好的有效性。     

The system design for GALATEA,an interactive real-time computer graphics system for movie and video analysis

The extraction of information from movie film and videotape has always been a very tedious process. Yet the usefulness of these media in biomedical research, behavioral science, industrial testing, etc., is apparent. We are developing a system, GALATEA, for the rapid extraction of data from film or video using interactive graphics. The key aspects of GALATEA are: the user indicates what features are of interest using an x, y digitizing pen. These pen positions are the only data the system sees, so that full digital image encoding is avoided. The user can trace the features while the film runs (frame-by-frame analysis is not necessary). The user has constant feedback in the form of an animated, computer-generated movie (Kinegram), overlaid on the original film image and running synchronously with it. It is this kinetic feedback of the data entered that makes the system efficient. Structured programming, real-time programming techniques, data structures for time-dependent pictures and dynamical graphics ‘tools’ are covered. A detailed discussion is given of Slippage or soft degradation in real-time systems under fluctuating load conditions.     

Determination of emotional content of video clips by low-level audiovisual features

Affective analysis of video content has greatly increased the possibilities of the way we perceive and deal with media. Different kinds of strategies have been tried, but results are still opened to improvements. Most of the problems come from the lack of standardized test set and real affective models. In order to cope with these issues, in this paper we describe the results of our work on the determination of affective models for evaluation of video clips using audiovisual low-level features. The affective models were developed following two classes of psychological theories of affect: categorial and dimensional. The affective models were created from real data, acquired through a series of user experiments. They reflect the affective state of a viewer after watching a certain scene from a movie. We evaluate the detection of Pleasure, Arousal and Dominance coefficients as well as the detection rate of six affective categories. For this end, two Bayesian network topologies are used, a Hidden Markov Model and an Autoregressive Hidden Markov Model. The measurements were done using audio-only models, video-only models and fused models. Fusion is done using two different methods, a Decision Level Fusion and Feature Level Fusion. All tests were conducted using localized affective models, both categorial and dimensional. Results are presented in terms of detection rate and accuracy for affective families, affective dimensions and probabilistic networks. Arousal was the best detected dimension, followed by dominance and pleasure.     

Example-based video remixing

A video remix is generally created by arranging selected video clips and combining them with other media streams such as audio clips and video transition effects. This paper proposes a system for semi-automatically creating video remixes of good expressive quality. Given multiple original video clips, audio clips, and transition effects as the input, the proposed system generates a video remix by five processes: I) video clip sequence generation, II) audio clip selection, III) audio boundary extraction, IV) video segment extraction, and V) transition effect selection, based on the spatial and temporal structural patterns automatically learned from professionally created video remix examples. Experiments using movie trailers of action genre as video remix examples not only demonstrate that video remixing by professionals can be imitated based on examples but also reveal that the video clip sequence generation and audio clip selection are the most important processes to improve the perceived expressive quality of video remixes.     

Film clips retrieval using image queries

The emergence of entertainment industry motivates the explosive growth of automatically film trailer. Manually finding desired clips from these large amounts of films is time-consuming and tedious, which makes finding the moments of user major or special preference becomes an urgent problem. Moreover, the user subjectivity over a film makes no fixed trailer caters to all tastes. This paper addresses these problems by posing a query-related film clip extraction framework which optimizes selected frames not only meet the semantic meaning of the queries but also have visual similarity on appearance between the query and selected clips. The experimental results show that our query-related film clip retrieval method is particularly useful for film editing, e.g. automatically finding movie clips to arouse audiences’ interests on the film.

     

Do moods affect programmers’ debug performance?

There is much research that shows people’s mood can affect their activities. This paper argues that this also applies to programmers, especially their debugging. Literature-based framework is presented linking programming with various cognitive activities as well as linking cognitive activities with moods. Further, the effect of mood on debugging was tested in two experiments. In the first experiment, programmers (n = 72) saw short movie clips selected for their ability to provoke specific moods. Afterward, they completed a debugging test. Results showed the video clips had a significant effect on programmers’ debugging performance; especially, there was a significant difference after watching low- and high-arousal-evoking video clips. In the second experiment, programmers’ mood was manipulated by asking participants (n = 19) to dry run algorithms for at least 16 min. They performed some physical exercises before continuing dry running algorithms again. The results showed a significant increase in arousal and valence that coincided with an improvement in programmers’ task performance after the physical exercises. Together, this suggests that programmers’ moods influence some programming tasks such as debugging.     

Querying large models efficiently

ContextThe paradigm of Model-Driven Engineering (MDE) has emerged as a new area of software engineering that uses models to improve the productivity and reusability of software in order to achieve industrial standards. As models grow in size and complexity, the need of model persistence and model querying solutions arises to efficiently store large models and obtain information from them in an efficient, usable and safe way. Morsa is a model repository that uses a No-SQL database backend; it has been recently presented [1] and achieves scalable access to models and transparent integration with tools.ObjectiveOur goal was to develop a query language for Morsa, as the existing model querying approaches cannot take advantage of the design of the our repository.MethodThe method followed in this paper comprises the following steps: (i) analyze the problem of model querying and identify a set of dimensions that can be used to characterize querying approaches; (ii) study and evaluate a representative set of model querying approaches and (iii) use the experience gained to design, develop and evaluate a dedicated model querying approach for Morsa that performs better than the studied ones (plain EMF, EMF Query, MDT OCL, IncQuery and CDO OCL). A test case has been defined to evaluate and compare the different approaches.ResultsThe contributions of this work are: first, an efficient, usable querying approach called Morsa Query Language (MorsaQL) that extends Morsa with querying capabilities, as the existing querying approaches cannot take advantage of our repository, and second, a comparative study of the current model persistence and querying approaches.ConclusionThe experience of analyzing and evaluating the different querying approaches has been very useful, as it has helped us developing our own one, which has been proven to be the best choice for Morsa. Moreover, the results of this paper can guide the MDE developers on which querying approach to use, depending on their needs.     

多媒体技术研究:2017——记忆驱动的媒体学习与创意

目的 借鉴大脑的工作机理来发展人工智能是当前人工智能发展的重要方向之一。注意力与记忆在人的认知理解过程中扮演了重要的角色。由于"端到端"深度学习在识别分类等任务中表现了优异性能,因此如何在深度学习模型中引入注意力机制和外在记忆结构,以挖掘数据中感兴趣的信息和有效利用外来信息,是当前人工智能研究的热点。方法 本文以记忆和注意力等机制为中心,介绍了这些方面的3个代表性工作,包括神经图灵机、记忆网络和可微分神经计算机。在这个基础上,进一步介绍了利用记忆网络的研究工作,其分别是记忆驱动的自动问答、记忆驱动的电影视频问答和记忆驱动的创意（文本生成图像）,并对国内外关于记忆网络的研究进展进行了比较。结果 调研结果表明：1）在深度学习模型中引入注意力机制和外在记忆结构,是当前人工智能研究的热点;2）关于记忆网络的研究越来越多。国内外关于记忆网络的研究正在蓬勃发展,每年发表在机器学习与人工智能相关的各大顶级会议上的论文数量正在逐年攀升;3）关于记忆网络的研究越来越热。不仅每年发表的论文数量越来越多,且每年的增长趋势并没有放缓,2015年增长了9篇,2016年增长了4篇,2017年增长了9篇,2018年增长了14篇;4）基于记忆驱动的手段和方法十分通用。记忆网络已成功地运用于自动问答、视觉问答、物体检测、强化学习、文本生成图像等领域。结论 数据驱动的机器学习方法已成功运用于自然语言、多媒体、计算机视觉、语音等领域,数据驱动和知识引导将是人工智能未来发展的趋势之一。     

Investigating perceived emotions and affects of a scene,and the user satisfaction with motion effects in 4D movies

The primary objective of this study was to investigate the intensity of perceived affect and emotion of a scene in relation to individual empathy ability and the rotation angle of a seat's motion caused by 4D movie motion effect. The secondary objective was to identify the causal factors that affected satisfaction with a motion effect. Although 4D movies have received increasing attention from the users of audiovisual content, user-centered research related to motion effects has rarely been conducted. Thirty-six participants who were grouped according to their empathy ability, viewed 10 4D movie clips and answered 2 questions related to 1) the perceived affect and emotion felt from the scenes and 2) satisfaction with the motion effects. The participants who had a high empathy ability indicated a stronger perceived affect and emotion during a scene than the participants who had a low empathy ability. A motion effect elicited different perceived emotions and affects between the two groups. The perceived temporal appropriateness, physical appropriateness, understandability, and disturbance of a motion effect affected the participants' satisfaction. This is a pioneering research related to the motion effects of 4D movie; therefore, these results could be helpful in providing insight for 4D effect designers of contents industry.     

Artist Space

Abstract

This paper addresses the process of patterning reconfigurable video narrative using architectural theory, through a case-study of practice-based research on the interactive, reconfigurable small-screen movie Gormenghast Explore. It focuses on the topography of cinematic narrative as architectural construction, refashioning Kevin Lynch's urban categories and Christian Norberg-Schulz's concept of place to support a design ontology for dramatic fictive narrativity. This architectural framework provides an effective representation for both navigable narrative content and 3D environment and interface.     

A Novel Approach Based on Multi-View Content Analysis and Semi-Supervised Enrichment for Movie Recommendation

Although many existing movie recommender systems have investigated recommendation based on information such as clicks and tags, much less efforts have been made to explore the multimedia content of movies, which has potential information for the elicitation of the user’s visual and musical preferences.In this paper, we explore the content from three media types (image, text, audio) and propose a novel multi-view semi-supervised movie recommendation method, which represents each media type as a view space for movies.The three views of movies are integrated to predict the rating values under the multi-view framework.Furthermore, our method considers the casual users who rate limited movies.The algorithm enriches the user profile with a semi-supervised way when there are only few rating histories.Experiments indicate that the multimedia content analysis reveals the user’s profile in a more comprehensive way.Different media types can be a complement to each other for movie recommendation.And the experimental results validate that our semi-supervised method can effectively enrich the user profile for recommendation with limited rating history.     

Motion in images is essential to cause motion sickness symptoms,but not to increase postural sway

ObjectiveIt is generally assumed that motion in motion images is responsible for increased postural sway as well as for visually induced motion sickness (VIMS). However, this has not yet been tested. To that end, we studied postural sway and VIMS induced by motion and still images.Method15 Participants were exposed to motion- and still images in separate sessions. Motion images consisted of video clips taken from a first person shooter game. Still images consisted of stills taken every 10 s from these same clips. Before, during, and after exposure, VIMS was rated and postural sway was measured. Sway path length, standard deviation and short- and long-term scaling components of the centre of pressure were calculated as measures of postural sway.ResultsVIMS scores obtained during and after exposure to motion images were significantly higher compared to scores obtained before, and directly after exposure to still images. The sway path length, standard deviation in anteroposterior direction and short-term scaling components in mediolateral and anteroposterior direction increased significantly during exposure to motion and still images.ConclusionIn this experiment motion- and still images caused different levels of VIMS, but comparable increases in postural sway. We assume VIMS was caused by a mismatch between visual and vestibular motion cues. The increase in sway during exposure to still images can be explained by visual effects present in still images. The lack of vection in the motion images may explain why sway was not larger when viewing these motion images as compared to viewing the still images.     

Civil liability for misuse of online communication through websites: an analytical study of UAE law

ABSTRACT

This paper takes the UAE legal system as case in point to illustrate certain challenges posed for jurists by the spread of the Internet. Since it enables large-scale participatory multimedia content production, the Internet is surrounded by regulatory safeguards for ensuring its public accountability. In the UAE, the National Media Council holds responsibility for licensing media outlets, including online ones, and for overseeing content published therein. Together, legal disciplines on content, regulatory accountability frameworks and the collaborative nature of Internet content production form the context in which existing regimes, such as for civil liability (tort), call for interpretive adaptation. This is what this paper undertakes, with respect to civil liability claims for misuse of online communication through websites. A close analytical study of UAE law helps clarify how civil liability is established and apportioned between the National Media Council (vicarious liability), media outlets and individual users, alongside other findings.