作者: Monica Lestari Paramita , Michael Grubinger
DOI: 10.1007/978-3-642-15181-1_8
关键词:
摘要: CLEF was the first benchmarking campaign that organized an evaluation event for image retrieval: ImageCLEF photographic ad hoc retrieval task in 2003. Since then, this has become one of most popular tasks ImageCLEF, providing both resources and a framework necessary to carry out comparative laboratory–style multi–lingual visual information from collections. Running seven years, several challenges have been given participants, including: collection historic photographs; more generic with annotations; large news archive, promoting result diversity. This chapter summarizes each these tasks, describes individual test collections scenarios, analyzes results, discusses potential findings number research questions.