|
|||||
|
|
Naming persons in video: Using the weak supervision of textual stories |
|
| Authors: | Phi The Pham Koen Deschacht Tinne Tuytelaars Marie-Francine Moens |
| Affiliation: | 1. KU Leuven, Computer Science Department, Celestijnenlaan 200A, B-3001 Leuven, Belgium;2. Foreach, St-Bartholomeusstraat 130, B-2170 Merksem, Belgium;3. KU Leuven, ESAT-PSI, iMinds, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium |
| Abstract: | |
| Keywords: | Cross-media mining Video annotation Expectation Maximization Unsupervised alignment |
| 本文献已被 ScienceDirect 等数据库收录！ | |