We propose an unsupervised approach to learn associations between continuous-valued attributes from different modalities. These associations are used to construct a multi-modal t...
We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Ou...
Unsupervised word representations are very useful in NLP tasks both as inputs to learning algorithms and as extra word features in NLP systems. However, most of these models are b...
Eric H. Huang, Richard Socher, Christopher D. Mann...
In a typical content-based image retrieval (CBIR) system, query results are a set of images sorted by feature similarities with respect to the query. However, images with high fea...
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...