Search for: All records

Recently 3D scene understanding attracts attention for many applications, however, annotating a vast amount of 3D data for training is usually expensive and time consuming. To alleviate the needs of ground truth, we propose a self-supervised schema to learn 4D spatio-temporal features (i.e. 3 spatial dimensions plus 1 temporal dimension) from dynamic point cloud data by predicting the temporal order of sampled and shuffled point cloud clips. 3D sequential point cloud contains precious geometric and depth information to better recognize activities in 3D space compared to videos. To learn the 4D spatio-temporal features, we introduce 4D convolution neural networks to predict the temporal order on a self-created large scale dataset, NTU- PCLs, derived from the NTU-RGB+D dataset. The efficacy of the learned 4D spatio-temporal features is verified on two tasks: 1) Self-supervised 3D nearest neighbor retrieval; and 2) Self-supervised representation learning transferred for action recognition on smaller 3D dataset. Our extensive experiments prove the effectiveness of the proposed self-supervised learning method which achieves comparable results w.r.t. the fully-supervised methods on action recognition on MSRAction3D dataset. 

Structural biology has provided valuable insights and high-resolution views of the biophysical processes in plants, such as photosynthesis, hormone signaling, nutrient transport, and toxin efflux. However, structural biology only provides a few “snapshots” of protein structure, whereas in vivo, protein function involves complex dynamical processes such as ligand binding and conformational changes that structures alone are unable to capture in full detail. Here, we present all-atom molecular dynamics (MD) simulations as a “computational microscope” that can be used to capture detailed structural and dynamical information about the molecular machinery in plants and gain high-resolution insights into plant growth and function. In addition to the background information provided here, we have prepared a set of tutorials that allow students to run and explore MD simulations of plant proteins.