Publications by authors named "Tomas Simon"

An important goal of sustainable agriculture is to maintain soil quality. Soil aggregation, which can serve as a measure of soil quality, plays an important role in maintaining soil structure, fertility, and stability. The process of soil aggregation can be affected through impacts on biotic and abiotic factors.

View Article and Find Full Text PDF

Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image.

View Article and Find Full Text PDF

We present an approach to capture the 3D motion of a group of people engaged in a social interaction. The core challenges in capturing social interactions are: (1) occlusion is functional and frequent; (2) subtle motion needs to be measured over a space large enough to host a social group; (3) human appearance and configuration variation is immense; and (4) attaching markers to the body may prime the nature of interactions. The Panoptic Studio is a system organized around the thesis that social interactions should be measured through the integration of perceptual analyses over a large variety of view points.

View Article and Find Full Text PDF

Heavy metal soil contamination from mining and smelting has been reported in several regions around the world, and phytoextraction, using plants to accumulate risk elements in aboveground harvestable organs, is a useful method of substantially reducing this contamination. In our 3-year experiment, we tested the hypothesis that phytoextraction can be successful in local soil conditions without external fertilizer input. The phytoextraction efficiency of 15 high-yielding crop species was assessed in a field experiment performed at the Litavka River alluvium in the Příbram region of Czechia.

View Article and Find Full Text PDF

Recovering dynamic 3D structures from 2D image observations is highly under-constrained because of projection and missing data, motivating the use of strong priors to constrain shape deformation. In this paper, we empirically show that the spatiotemporal covariance of natural deformations is dominated by a Kronecker pattern. We demonstrate that this pattern arises as the limit of a spatiotemporal autoregressive process, and derive a Kronecker Markov Random Field as a prior distribution over dynamic structures.

View Article and Find Full Text PDF