Abstract | ||
---|---|---|
Indexing and retrieving broadcast news stories within a large collection requires automatic detection of story boundaries. This video news story segmentation can use a wide range of audio, language, video, and image features. In this paper, we investigate the correlation between automatically-derived multimodal features and story boundaries in seven different broadcast news sources in three languages. We identify several features that are important for all seven sources analyzed, and we discuss the contributions of other features that are important for a subset of the seven sources. |
Year | Venue | Keywords |
---|---|---|
2004 | HLT-NAACL (Short Papers) | feature selection,automatic detection,video news story segmentation,different broadcast news source,trainable multilingual broadcast news,image feature,large collection,retrieving broadcast news story,story boundary,wide range,automatically-derived multimodal feature |
Field | DocType | ISBN |
Broadcasting,Information retrieval,Feature selection,Computer science,Feature (computer vision),Segmentation,Search engine indexing,Natural language processing,Artificial intelligence | Conference | 1-932432-24-8 |
Citations | PageRank | References |
2 | 0.40 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
David D. Palmer | 1 | 252 | 46.19 |
Marc Reichman | 2 | 4 | 0.94 |
Elyes Yaich | 3 | 2 | 0.40 |