We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...
—Recently, many object localization models have shown that incorporating contextual cues can greatly improve accuracy over using appearance features alone. Therefore, many of the...
Brian McFee, Carolina Galleguillos, Gert R. G. Lan...
This paper describes the participation of LIG lab, in the batch filtering task for the INFILE (INformation FILtering Evaluation) campaign of CLEF 2009. As opposed to the online ta...
This paper presents two metrics for the Nearest Neighbor Classifier that share the property of being adapted, i.e. learned, on a set of data. Both metrics can be used for similari...
—We present an overview of the combinatorial framework for similarity search. An algorithm is combinatorial if only direct comparisons between two pairwise similarity values are ...