This article presents a novel approach for 3D mesh labeling by using deep Convolutional Neural Networks (CNNs). Many previous methods on 3D mesh labeling achieve impressive performances by using predefined geometric features. However, the generalization abilities of such low-level features, which are heuristically designed to process specific meshes, are often insufficient to handle all types of meshes. To address this problem, we propose to learn a robust mesh representation that can adapt to various 3D meshes by using CNNs. In our approach, CNNs are first trained in a supervised manner by using a large pool of classical geometric features. In the training process, these low-level features are nonlinearly combined and hierarchically compressed to generate a compact and effective representation for each triangle on the mesh. Based on the trained CNNs and the mesh representations, a label vector is initialized for each triangle to indicate its probabilities of belonging to various object parts. Eventually, a graph-based mesh-labeling algorithm is adopted to optimize the labels of triangles by considering the label consistencies. Experimental results on several public benchmarks show that the proposed approach is robust for various 3D meshes, and outperforms state-of-the-art approaches as well as classic learning algorithms in recognizing mesh labels.

Figure 1: Our edit propagation algorithm can be applied for various applications including color manipulation and matting. From left to right, these are the results of video recoloring, video color theme editing, image colorization and matting. Shown on the top are the input images (with a few user edits). Below are their corresponding output. AbstractWe propose a novel edit propagation algorithm for interactive image and video manipulations. Our approach uses the locally linear embedding (LLE) to represent each pixel as a linear combination of its neighbors in a feature space. While previous methods require similar pixels to have similar results, we seek to maintain the manifold structure formed by all pixels in the feature space. Specifically, we require each pixel to be the same linear combination of its neighbors in the result. Compared with previous methods, our proposed algorithm is more robust to color blending in the input data. Furthermore, since every pixel is only related to a few nearest neighbors, our algorithm easily achieves good runtime efficiency. We demonstrate our manifold preserving edit propagation on various applications.

No abstract

Signal transducer and activator of transcription 3 (STAT3) has important roles in cancer aggressiveness and has been confirmed as an attractive target for cancer therapy. In this study, we used a dual-luciferase assay to identify that pectolinarigenin inhibited STAT3 activity. Further studies showed pectolinarigenin inhibited constitutive and interleukin-6-induced STAT3 signaling, diminished the accumulation of STAT3 in the nucleus and blocked STAT3 DNA-binding activity in osteosarcoma cells. Mechanism investigations indicated that pectolinarigenin disturbed the STAT3/DNA methyltransferase 1/HDAC1 histone deacetylase 1 complex formation in the promoter region of SHP-1, which reversely mediates STAT3 signaling, leading to the upregulation of SHP-1 expression in osteosarcoma. We also found pectolinarigenin significantly suppressed osteosarcoma cell proliferation, induced apoptosis and reduced the level of STAT3 downstream proteins cyclin D1, Survivin, B-cell lymphoma 2 (Bcl-2), B-cell lymphoma extra-large (Bcl-xl) and myeloid cell leukemia 1 (Mcl-1). In addition, pectolinarigenin inhibited migration, invasion and reserved epithelial–mesenchymal transition (EMT) phenotype in osteosarcoma cells. In spontaneous and patient-derived xenograft models of osteosarcoma, we identified administration (intraperitoneal) of pectolinarigenin (20 mg/kg/2 days and 50 mg/kg/2 days) blocked STAT3 activation and impaired tumor growth and metastasis with superior pharmacodynamic properties. Taken together, our findings demonstrate that pectolinarigenin may be a candidate for osteosarcoma intervention linked to its STAT3 signaling inhibitory activity.