DCU at VideoCLEF 2008
نویسندگان
چکیده
We describe a baseline system for the VideoCLEF Vid2RSS task. The system uses an unaltered off-the-shelf Information Retrieval system. ASR content is indexed using default stemming and stopping methods. The subject categories are populated by using the category label as a query on the collection, and assigning the retrieved items to that particular category. We describe the results of the system and provide some high-level analysis of its performance. General Terms ASR, IR, Classification
منابع مشابه
DCU at VideoClef
We describe a baseline system for the VideoCLEF Vid2RSS task in which videos are to be classified into thematic categories based on their content. The system uses an off-the-shelf Information Retrieval system. Speech transcripts generated using automated speech recognition are indexed using default stemming and stopping methods. The categories are populated by using the category theme (or label...
متن کاملDCU at VideoCLEF 2009
DCU participated in the VideoCLEF 2009 Linking Task. Our approach was based on identifying relevant related content using the Lemur information retrieval toolkit. We implemented two distinctive variants of our approach. One version performs the search in the Dutch Wikipedia with the exact words (either stemmed or not) of the search query extracted from the ASR transcription, and returns the cor...
متن کاملWhen to Cross Over? Cross-Language Linking Using Wikipedia for VideoCLEF 2009
We describe Dublin City University (DCU)’s participation in the VideoCLEF 2009 Linking Task. Two approaches were implemented using the Lemur information retrieval toolkit. Both approaches first extracted a search query from the transcriptions of the Dutch TV broadcasts. One method first performed search on a Dutch Wikipedia archive, then followed links to corresponding pages in the English Wiki...
متن کاملSINAI at VideoCLEF 2008
This paper describes the first participation of the SINAI research group in the VideoCLEF 2008 track. We have only submitted runs for the classification task on Dutch and English languages. Our approach has consisted in the use of a particular Information Retrieval system as classification architecture, using the speech transcriptions as textual queries and generating textual corpus for each to...
متن کاملClassification of Dual Language Audio-Visual Content: Introduction to the VideoCLEF 2008 Pilot Benchmark Evaluation Task
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 dua...
متن کامل