Overview of VideoCLEF 2008: Automatic Generation of Topic-Based Feeds for Dual Language Audio-Visual Content

Abstract

The VideoCLEF track, introduced in 2008, aims to develop and evaluate tasks related to analysis of and access to multilingual multimedia content. In its first year, VideoCLEF piloted the Vid2RSS task, whose main subtask was the classification of dual language video (Dutchlanguage television content featuring English-speaking experts and studio guests). The task offered two additional discretionary subtasks: feed translation and automatic keyframe extraction. Task participants were supplied with Dutch archival metadata, Dutch speech transcripts, English speech transcripts and 10 thematic category labels, which they were required to assign to the test set videos. The videos were grouped by class label into topic-based RSS-feeds, displaying title, description and keyframe for each video.Five groups participated in the 2008 VideoCLEF track. Participants were required to collect their own training data; both Wikipedia and general web content were used. Groups deployed various classifiers (SVM, Naive Bayes and k-NN) or treated the problem as an information retrieval task. Both the Dutch speech transcripts and the archival metadata performed well as sources of indexing features, but no group succeeded in exploiting combinations of feature sources to significantly enhance performance. A small scale fluency/adequacy evaluation of the translation task output revealed the translation to be of sufficient quality to make it valuable to a non-Dutch speaking English speaker. For keyframe extraction, the strategy chosen was to select the keyframe from the shot with the most representative speech transcript content. The automatically selected shots were shown, with a small user study, to be competitive with manually selected shots. Future years of VideoCLEF will aim to expand the corpus and the class label list, as well as to extend the track to additional tasks.

Automatic Summarization

“…For video applications, presenting a keyframe may provide the user with an additional hint as to the content of the result. A further dimension to the selection of the appropriate form of surrogates is the background knowledge of the user, which has been observed to have an impact on the types of surrogates that are preferred [158,268].…”

Overview of VideoCLEF 2009: New Perspectives on Speech-Based Multimedia Content Enrichment

“…The results confirm the viability of techniques that approach the Subject Classification Task as an information retrieval task. Such techniques proved useful in VideoCLEF 2008 [6] and also provide the best results in 2009 where the size of the collection and the label set increased. Also, consistent with VideoCLEF 2008 observations, performance is better when archival metadata is used in addition to speech recognition transcripts.…”

“…The videos were annotated with the ground truth with the support of the Anvil 6 Video Annotation Research Tool [5]. Anvil makes it possible to generate frame-accurate video annotations in a graphic interface.…”

“…Since these subject labels are currently in use to archive and retrieve video in the setting of a large archive, we are confident in their usefulness for search and browsing in real-world information retrieval scenarios. The Subject Classification Task was introduced during the VideoCLEF 2008 pilot [6]. In 2009, the number of videos in the collection was increased from 50 to 418 and the number of subject labels increased from 10 to 46.…”

“…The track was piloted last year as VideoCLEF 2008 [6]. The VideoCLEF track is successor to the Cross-Language Speech Retrieval (CL-SR) track, which ran at CLEF from 2005 to 2007 [7].…”