Automatic generation of video narratives from shared UGC

Abstract

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 [Ursu, 2008a], 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.

Socially-aware multimedia authoring

“…They were especially keen with the approach of using an audio track as a master timeline to drive the story development. They also concurred with our approach of automatically selecting alternative shots from cameras available in parallel tracks and using rules that selected clips based on shot types [76].…”

“…An example of the selection criteria is the following: Once the automatic authoring process is complete, a new video compilation is created in which the selected song and people are featured. As reported elsewhere [76], such narrative constructs have been developed and tested together with professional video editors. Our assumption, based on the social theories, was that automatic methods -while useful -were not sufficient for creating personal memories of an event.…”

“…Our initial results showed a general enthusiasm from participants, which were validated in the first evaluation phase. The initial implementation, which was aligned with the personal effort guideline, made use of a narrative engine to automatically compile personalized stories based on the community media assets [76]. While the video compilations produced by the initial system were considered visually compelling, end-users missed the capability of personalizing those by adding their own 'imprint'.…”

WaaZam!

“…The Family Portals [14] and TA2 [43] projects designed shared spaces for drawing and interacting with board games. Nokia Research has several projects that support shared experiences through mobile storytelling [29], putting the child in the story [30], and scaffolding VMC sessions with activity prompts [10].…”

Sensor-Based Analysis of User Generated Video for Multi-camera Video Remixing

“…Most of this work is based on the analysis of video and/or audio content (thus being computationally demanding) for video captured by a single camera [2], and also for multi-camera setups [3][4][5]. In [6], a case study that compares manual and automatic video remix creation is presented.…”