Vittorio Murino

TL;DR: In this article , a system exploiting machine learning on Resting-state functional connectivity matrices was proposed to discriminate different MS phenotypes and to identify relevant functional connections for MS stage characterization.

TL;DR: In this paper, a constrained autoregressive model is proposed to generate an effective connectivity matrix that model the structural connectivity integrating the functional activity, by minimizing the reconstruction error of an autoregression model constrained by the structural prior.

TL;DR: Experimental results show how stel component analysis can assist in image/video segmentation and object recognition where, in particular, it can be used as an alternative of, or in conjunction with, bag-of-features and related classifiers, where stel inference provides a meaningful spatial partition of features.

TL;DR: This work visualize the spatiotemporal cues that contribute to a deep model's classification/captioning output using the model's internal representation, and is able to localize segments within a video that correspond with a specific action, or phrase from a caption, without explicitly optimizing/training for these tasks.