No abstract

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for topdown recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks. Starting from a full shape represented as a point cloud, our model performs recursive binary decomposition, where the decomposition network at all nodes in the hierarchy share weights. At each node, a node classifier is trained to determine the type (adjacency or symmetry) and stopping criteria of its decomposition. The features extracted in higher level nodes are recursively propagated to lower level ones. Thus, the meaningful decompositions in higher levels provide strong contextual cues constraining the segmentations in lower levels. Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part. Our method segments a 3D shape in point cloud into an unfixed number of parts, depending on the shape complexity, showing strong generality and flexibility. It achieves the stateof-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work. We also demonstrate its application for fine-grained part refinements in image-to-shape reconstruction.

No abstract

No abstract

Chronic administration of D-galactose simulates the changes in natural senescence and accelerates aging in animal models and has been used in aging research. The present study was undertaken to investigate the molecular mechanisms underlying the effects of exercise on learning and memory in rats with D-galactose-induced aging. The learning and memory performance in aging rats, either after exercise or without exercise, was assessed with the Morris water maze test. The effect of treadmill exercise on the expression of amyloid-β 42 and two key enzymes involved in processing of the β-amyloid precursor protein, a disintegrase and metalloprotease domain 17 and β-site amyloid precursor protein-cleaving enzyme 1, in the hippocampi of rats were monitored using real-time quantitative PCR. Moreover, oxidative stress-associated changes, including changes in superoxide dismutase activity and malondialdehyde content, in the hippocampi were assessed after exercise. Our results showed that treadmill exercise significantly improved learning and memory performance in aging rats. The behavioral changes were likely induced by repression of amyloid-β 42 protein levels, through the upregulation of a disintegrase and metalloprotease domain 17 mRNA and downregulation of β-site amyloid precursor protein-cleaving enzyme 1 mRNA, and a concomitant increase in superoxide dismutase activity and decrease in malondialdehyde content, in rat hippocampi. Our data suggest that exercise may be an effective therapy for alleviating learning and memory decline due to aging or the onset of neurodegenerative diseases.