Combining learning with vision techniques in interactive image retrieval has been an active research topic during the past few years. However, existing learning techniques either ...
Inhomogeneous Gibbs model (IGM) [4] is an effective maximum entropy model in characterizing complex highdimensional distributions. However, its training process is so slow that th...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation...
Ofer Meshi, David Sontag, Tommi Jaakkola, Amir Glo...
`Embedded phenomena' is a learning technology framework in which simulated scientific phenomena are mapped onto the physical space of classrooms. Students monitor and control...