Classification of dual language audio-visual content: Introduction to the VideoCLEF 2008 pilot benchmark evaluation task
Larson, Martha and Newman, Eamonn and Jones, Gareth J.F. (2008) Classification of dual language audio-visual content: Introduction to the VideoCLEF 2008 pilot benchmark evaluation task. In: the Workshop on Searching Spontaneous Conversational Speech at Thirty-First Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2008), July 2008, Singapore.
Full text available as:
VideoCLEF is a new track for the CLEF 2008 campaign. This
track aims to develop and evaluate tasks in analyzing multilingual video content. A pilot of a Vid2RSS task involving assigning thematic class labels to video kicks off the VideoCLEF track in 2008. Task participants deliver classification results in the form of a series of feeds, one for each thematic class. The data for the task are dual language television documentaries. Dutch is the dominant language and English-language content (mostly interviews) is embedded. Participants are provided with speech recognition transcripts of the data in both Dutch and English, and also with metadata generated by archivists. In addition to the classification task, participants can choose to participate in a translation task (translating the
feed into a language of their choice) and a keyframe selection task (choosing a semantically appropriate keyframe for depiction of the videos in the feed).
|Item Type:||Conference or Workshop Item (Paper)|
|Uncontrolled Keywords:||Multimedia analysis; classification; speech recognition; benchmark test; cross-language information retrieval|
|Subjects:||Computer Science > Information retrieval|
|DCU Faculties and Centres:||UNSPECIFIED|
|Use License:||This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License|
|Deposited On:||17 Jun 2011 10:34 by Shane Harper. Last Modified 17 Jun 2011 10:34|
Archive Staff Only: edit this record