Name
Abstract | ||
|---|---|---|
Finding a named person in broadcast news video is important to video retrieval. Relying on the text information such as video tran-script and OCR text, this task suffers from the temporal mismatch between a person's visual appearance and his/her name occurred in text. By exploring video grammar on the concurrence pattern between faces and names, we propose an extended text-based IR method to overcome this problem and yield superior performance. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1145/996350.996399 | JCDL |
Keywords | Field | DocType |
video tran-script,ocr text,broadcast news video,extended text-based ir method,video retrieval,video grammar,temporal mismatch,concurrence pattern,text information,superior performance,digital video broadcasting,information retrieval,degradation,grammars,broadcasting,frequency,cellular neural networks,computer science,optical character recognition,testing,image retrieval | Video processing,Computer science,Optical character recognition,Image retrieval,Speech recognition,Grammar,Video tracking,Smacker video,Multimedia,Visual Word,Visual appearance | Conference |
ISSN | ISBN | Citations |
2575-7865 | 1-58113-832-6 | 1 |
PageRank | References | Authors |
0.38 | 2 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jun Yang | 1 | 937 | 37.42 |
| Alexander G. Hauptmann | 2 | 7472 | 558.23 |