Home

Contact

Publications

Code

Videos

Projects

Bio

Press


RESEARCH

Multimodal Object Recognition using Random Clustering Trees
M. Villamizar, A. Garrell, A. Sanfeliu and F. Moreno-Noguer

Abstract - In this paper, we present an object recognition approach that in addition allows to discover intra-class modalities exhibiting high-correlated visual information. Unlike to more conventional approaches based on computing multiple specialized classifiers, the proposed approach combines a single classifier, Boosted Random Ferns (BRFs), with probabilistic Latent Semantic Analysis (pLSA) in order to recognize an object class and to find automatically the most prominent intra-class appearance modalities (clusters) through tree-structured visual words. The proposed approach has been validated in synthetic and real experiments where we show that the method is able to recognize objects with multiple appearances.

Link

PDF

Poster

Code

Random Clustering Ferns

Random Clustering Ferns 2D