We propose a framework for early action recognition and anticipation by correlating past features with the future using three novel similarity measures called Jaccard vector similarity, Jaccard cross-correlation and Jaccard Frobenius inner product over covariances.
We train two classifiers with two different views of the class labels: one classifier uses the one-hot view of the labels and disregards any potential similarity among the classes, while the other uses a distributed view of the labels and groups potentially similar classes together.
In practice, this is achieved by minimizing the disparity between the domains, usually measured in terms of their statistical properties.
This paper introduces a learning scheme to construct a Hilbert space (i. e., a vector space along its inner product) to address both unsupervised and semi-supervised domain adaptation problems.
Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation.