In this paper we consider a version of the zero-shot learning problem where seen class source and target do-main data are provided. The goal during test-time is to ac-curately predict the class label of an unseen target domain instance based on revealed source domain side information (e.g. attributes) for unseen classes. Our method is based on viewing each source or target data as a mixture of seen class proportions and we postulate that the mixture patterns have to be similar if the two instances belong to the same unseen class. This perspective leads us to learning source/target embedding functions that map an arbitrary source/target domain data into a same semantic space where similarity can be readily measured. We develop a max-margin frame-work to learn these similarity functions and jointly opti-mize parameters by means of cross validation. Our test re-sults are compelling, leading to significant improvement in terms of accuracy on most benchmark datasets for zero-shot recognition. 1.