CMML: a New Metric Learning Approach for Cross Modal Matching
Abstract
This paper proposes a new approach for Cross Modal Matching, i.e. the matching of patterns represented in di erent modalities, when pairs of same/di erent data are available for training (e.g. faces of same/di erent persons). In this situation, standard approaches such as Partial Least Squares (PLS) or Canonical Correlation Analysis (CCA), map the data into a common latent space that maximizes the covariance, using the information brought by positive pairs only. Our contribution is a new metric learning algorithm, which alleviates this limitation by considering both positive and negative constraints and use them effi ciently to learn a discriminative latent space. The contribution is validated on several datasets for which the proposed approach consistently outperforms PLS/CCA as well as more recent discriminative approaches.
Origin : Files produced by the author(s)
Loading...