Rodrigo Laiola Guimarães

Automatic generation of video narratives from shared UGC

This paper introduces an evaluated approach to the automatic generation of video narratives from user generated content gathered in a shared repository. In the context of social events, end-users record video material with their personal cameras and upload the content to a common repository. Video narrative techniques, implemented using Narrative Structure Language (NSL) and ShapeShifting Media, are employed to automatically generate movies recounting the event. Such movies are personalized according to the preferences expressed by each individual end-user, for each individual viewing. This paper describes our prototype narrative system, MyVideos, deployed as a web application, and reports on its evaluation for one specific use case: assembling stories of a school concert by parents, relatives and friends. The evaluations carried out through focus groups, interviews and field trials, in the Netherlands and UK, provided validating results and further insights into this approach.

Composer: Authoring Tool for iTV Programs

This paper presents Composer, an authoring tool to help creating interactive TV programs for the Brazilian Terrestrial Digital TV System. In Composer, several abstractions are defined creating different document views (structural, temporal, layout and textual). One of these views, the temporal view, preserves as much as possible the timeline paradigm, so popular in TV program editing. Using this view, authoring can be done by placing media objects on a time axis, however, preserving the relative relationships among them. Moreover, non-deterministic time events, like viewer interactions and content adaptations, can also be represented in the temporal view. In addition, the occurrence of these unpredictable events can be simulated, and the resulting TV program played, from any starting point. Besides other facilities provided by its four views, Composer also supports third-party views created as add-ons, and live program editing.

Interactive video stories from user generated content: a school concert use case

This paper describes a web-based narrative system able to generate video compilations, framed as event stories, from a shared repository of video recordings of the event itself and possibly of related events. For this, it employs narrative techniques informed by TV documentary. The generated stories are dynamically personalised, in that the system is able to adapt them to the choices and preferences expressed by the active viewers during narration. The system has been prototyped for the case of school concerts. User evaluations indicate that experiences founded on story navigation rather than sharing individual media assets is a rewarding one and point to further areas of development in interactive storytelling in the context of user generated content.

Let me comment on your video: supporting personalized end-user comments within third-party online videos

Long before the first transmission in color of a World Cup in 1970, people used to gather around the few existing radio and TV sets to watch together and talk about their favorite programs. Decades later, not only the technology has significantly changed but also peoples consumption and commenting habits. Nowadays, one can easily watch an online video on demand and share comments with others asynchronously. However, current video commenting facilities do not take into account the temporal nature of videos. Viewers can only add comments that will then appear statically underneath the video. Motivated by a survey research on current media watching and commenting practices, we report on our findings from the evaluation of an online video commenting system that allows users to add synchronized comments to third-party videos. Our results indicate that users appreciate the functionalities of our system and find it better to comment when compared to existing tools. Ultimately, we hope that our work can bring insights to be considered in the design of next generation online video commenting tools.

Just-in-time personalized video presentations

Using high-quality video cameras on mobile devices, it is relatively easy to capture a significant volume of video content for community events such as local concerts or sporting events. A more difficult problem is selecting and sequencing individual media fragments that meet the personal interests of a viewer of such content. In this paper, we consider an infrastructure that supports the just-in-time delivery of personalized content. Based on user profiles and interests, tailored video mash-ups can be created at view-time and then further tailored to user interests via simple end-user interaction. Unlike other mash-up research, our system focuses on client-side compilation based on personal (rather than aggregate) interests. This paper concentrates on a discussion of language and infrastructure issues required to support just-in-time video composition and delivery. Using a high school concert as an example, we provide a set of requirements for dynamic content delivery. We then provide an architecture and infrastructure that meets these requirements. We conclude with a technical and user analysis of the just-in-time personalized video approach.

A visual approach for modeling spatiotemporal relations

Textual programming languages have proven to be difficult to learn and to use effectively for many people. For this sake, visual tools can be useful to abstract the complexity of such textual languages, minimizing the specification efforts. In this paper we present a visual approach for high level specification of spatiotemporal relations. In order to accomplish this task, our visual representation provides an intuitive way to specify complex synchronization events amongst media. Finally, to validate our work, the visual specification is mapped to NCL (Nested Context Language), the standard declarative language of the Brazilian Terrestrial Digital TV System.

Adding dynamic visual manipulations to declarative multimedia documents

The objective of this work is to define a document model extension that enables complex spatial and temporal interactions within multimedia documents. As an example we describe an authoring interface of a photo sharing system that can be used to capture stories in an open, declarative format. The document model extension defines visual transformations for synchronized navigation driven by dynamic associated content. Due to the open declarative format, the presentation content can be targeted to individuals, while maintaining the underlying data model. The impact of this work is reflected in its recent standardization in the W3C SMIL language. Multimedia players, as Ambulant and the RealPlayer, support the extension described in this paper.

Socially-aware multimedia authoring: Past, present, and future

Creating compelling multimedia productions is a nontrivial task. This is as true for creating professional content as it is for nonprofessional editors. During the past 20 years, authoring networked content has been a part of the research agenda of the multimedia community. Unfortunately, authoring has been seen as an initial enterprise that occurs before ‘real’ content processing takes place. This limits the options open to authors and to viewers of rich multimedia content for creating and receiving focused, highly personal media presentations. This article reflects on the history of multimedia authoring. We focus on the particular task of supporting socially-aware multimedia, in which the relationships within particular social groups among authors and viewers can be exploited to create highly personal media experiences. We provide an overview of the requirements and characteristics of socially-aware multimedia authoring within the context of exploiting community content. We continue with a short historical perspective on authoring support for these types of situations. We then present an overview of a current system for supporting socially-aware multimedia authoring within the community content. We conclude with a discussion of the issues that we feel can provide a fruitful basis for future multimedia authoring support. We argue that providing support for socially-aware multimedia authoring can have a profound impact on the nature and architecture of the entire multimedia information processing pipeline.

Exploring the Use of Massive Open Online Courses for Teaching Students with Intellectual Disability

In this paper, we report on a qualitative study that investigates the impact of using a popular Massive Open Online Course (MOOC) to complement the vocational training of students with intellectual disability (ID). We have been investigating this problem for several months in partnership with a Brazilian NGO (Non-Governmental Organization) for people with ID. Our methodology integrates different aspects of human-computer interaction (i.e., requirement gathering sessions and observation of real subjects). Potential users were involved since the beginning of this research, starting with focus groups and interviews with experts, followed by the observation of a traditional vocational training session, and then the assessment of a popular MOOC in the classroom. In this paper, we discuss the process and present our preliminary results, providing some indications on how MOOCs could better support instructors and students with ID.

Dynamic Adjustment of Subtitles Using Audio Fingerprints

Anyone who ever downloaded subtitle files from the Internet has faced problems synchronizing them with the associated media files. Even with the efforts of communities on reviewing user-contributed subtitles and with mechanisms in movie players to automate the discovery of subtitles for a given media, users still face lip synchronization issues. In this work we conduct a study on several subtitle files associated with popular movies and TV series and analyze their differences. Based on that, we propose a two-phase subtitle synchronization method that annotates subtitles with audio fingerprints, which serve as synchronization anchors to the media player. Preliminary results obtained with our prototype suggest that our technique is effective and has minimal impact on the extension of subtitle formats and on media playback performance.