LIP: Local Importance-Based Pooling

A local region based approach to lip tracking

Lip tracking has played a significant role in a lip reading system. In this paper, we present a local region based approach to lip tracking, which consists of two phases: (i) lip contour extraction for the first lip frame, and followed by (ii) lip tracking in the subsequent lip frames. Initially, we construct a localized color active color model provided that the foreground and background regio...

Probabilistic opinion pooling generalized Part two: Premise-based opinion pooling

We consider the classical problem of aggregating di¤erent individuals’probability assignments (opinions) over a -algebra of events. In practice, some events represent basic propositions, such as ‘it rains’or ‘CO2 emissions cause global warming’, while others represent combinations thereof, for instance disjunctions (unions) of basic events. It is plausible to treat the basic events as premises ...

Supplementary material of the CVPR’17 Viraliency: Pooling Local Virality

We implemented our LENA pooling layer within the Caffe framework and ran all our experiments using a Tesla K40 GPU. All the networks were fine-tuned from the convolutional filters obtained when training these networks for the 1,000 image classification task on the ImageNet dataset. We iterated the stochastic gradient descent algorithm for 10,000 iterations with a momentum of μ = 0.9 and a weigh...

Local processes and spatial pooling in texture and symmetry detection

We examined the ability of human observers to detect three kinds of statistical structure in binary arrays: first-order statistics (luminance), local fourth-order statistics (isodipole textures), and long-range statistics (bilateral symmetry). Performance was closest to ideal on the luminance task and furthest from ideal on the symmetry task. For each kind of statistic, the dependence of perfor...

Lip-based Behavioural Biometrics