Abstract | ||
---|---|---|
This paper describes an experiment in creating cross-media descriptors from football-related text and videos. We used video analysis results and combined them with several textual resources - both semi- structured (tabular match reports) and unstructured (textual minute-by-minute match reports). Our aim was to discover the relations among six video data detectors and their behavior during a time window that corresponds to an event described in the textual data. The experiment shows how football events extracted from text can be mapped to corresponding scenes in video and how this may help in extracting event-specific video detectors. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/WIAMIS.2007.43 | Santorini |
Keywords | Field | DocType |
textual minute-by-minute match report,event alignment,unstructured textual data mapping.,cross-media descriptors,tabular match report,textual data,video analysis result,index terms— cross-media descriptors,text-to-video mapping,football-related text,textual resource,cross-media feature extraction,eventspecific video detector,corresponding scene,video data detector,football domain,detectors,filtering,indexing terms,image analysis,feature extraction,algorithm design and analysis,support vector machines,information analysis,data mining,ontologies,sport | Ontology (information science),Computer vision,Football,Algorithm design,Pattern recognition,Computer science,Support vector machine,Cross media,Filter (signal processing),Feature extraction,Artificial intelligence,Detector | Conference |
ISBN | Citations | PageRank |
0-7695-2818-X | 1 | 0.36 |
References | Authors | |
3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jan Nemrava | 1 | 9 | 3.45 |
Paul Buitelaar | 2 | 994 | 121.79 |
Vojtech Svatek | 3 | 122 | 7.02 |
Thierry Declerck | 4 | 309 | 65.24 |