Architectural style classification differs from standard classification tasks due to the rich inter-class relationships between different styles, such as re-interpretation, revival, and territoriality. In this paper, we adopt Deformable Part-based Models (DPM) to capture the morphological characteristics of basic architectural components and propose Multinomial Latent Logistic Regression (MLLR)...

Abstract The logistic birth and death process is perhaps the simplest stochastic population model that has both density-dependent reproduction a phase transition, lot can be learned about by studying its extinction time, $\tau_n$ , as function of system size n . A number existing results describe scaling $n\to\infty$ for various choices reproductive rate $r_n$ initial $X_n(0)$ We collect comple...

We present a shared logistic normal distribution as a Bayesian prior over probabilistic grammar weights. This approach generalizes the similar use of logistic normal distributions [3], enabling soft parameter tying during inference across different multinomials comprising the probabilistic grammar. We show that this model outperforms previous approaches on an unsupervised dependency grammar ind...