42 search results - page 6 / 9 » How small labels create big improvements |
SIGIR
2009
ACM
14 years 2 months ago
2009
ACM
When search is against structured documents, it is beneficial to extract information from user queries in a format that is consistent with the backend data structure. As one step...
ICCV
2007
IEEE
14 years 1 months ago
2007
IEEE
This paper treats tracking as a foreground/background classification problem and proposes an online semisupervised learning framework. Initialized with a small number of labeled ...
ICASSP
2008
IEEE
14 years 1 months ago
2008
IEEE
In previous work, we reported dramatic improvements in automatic speech recognition (ASR) and spoken language translation (SLT) gained by applying information extracted from spoke...
IR
2010
13 years 6 months ago
2010
Abstract We present a new ranking algorithm that combines the strengths of two previous methods: boosted tree classification, and LambdaRank, which has been shown to be empiricall...
BMVC
2010
13 years 5 months ago
2010
Image auto-annotation is a challenging task in computer vision. The goal of this task is to predict multiple words for generic images automatically. Recent state-of-theart methods...