Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
Object classification in far-field video sequences is a challenging problem because of low resolution imagery and projective image distortion. Most existing far-field classificati...
In web search, recency ranking refers to ranking documents by relevance which takes freshness into account. In this paper, we propose a retrieval system which automatically detect...
Anlei Dong, Yi Chang, Zhaohui Zheng, Gilad Mishne,...
Recently there has been interest in the use of classifiers based on the product of experts (PoE) framework. PoEs offer an alternative to the standard mixture of experts (MoE) fram...
Content-based audio classification techniques have focused on classifying events that are both semantically and perceptually distinct (such as speech, music, environmental sounds...