We present an approach to synthesizing shapes from complex domains, by identifying new plausible combinations of components from existing shapes. Our primary contribution is a new...
We propose an approach for learning visual models of object categories in an unsupervised manner in which we first build a large-scale complex network which captures the interacti...
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
We propose to model relative attributes1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can captur...
Abstract - Organizational learning requires individual learning. Individual learning has to interact in a dynamic social environment in order to contribute to organizational learni...