no code implementations • 26 Jan 2018 • Mikhail Startsev, Michael Dorr
To this end, we (i) use algorithmic and manual annotations of SP and fixations for two well-established video saliency data sets, (ii) train Slicing Convolutional Neural Networks for saliency prediction on either fixation- or SP-salient locations, and (iii) evaluate our and 26 publicly available dynamic saliency models on three data sets against traditional saliency and supersaliency ground truth.
no code implementations • CVPR 2014 • Eleonora Vig, Michael Dorr, David Cox
Our models outperform the state of the art on MIT1003, on which features and classifiers are learned.