Abstract. We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task learning problem, our model is able to selectively predict partial poses in the presence of noise and occlusion. Our approach leverages a convolutional and recurrent network architecture with a top-down error feedback mechanism to self-correct previous pose estimates in an end-to-end manner. We evaluate our model on a previously published depth dataset and a newly collected human pose dataset containing 100K annotated depth images from extreme viewpoints. Experiments show that our model achieves competitive performance on frontal views while achieving state-of-the-art performance on alternate viewpoints.

We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos. Given a pair of images from a video clip, our framework learns to predict the long-term 3D motions. To reduce the complexity of the learning framework, we propose to describe the motion as a sequence of atomic 3D flows computed with RGB-D modality. We use a Recurrent Neural Network based Encoder-Decoder framework to predict these sequences of flows. We argue that in order for the decoder to reconstruct these sequences, the encoder must learn a robust video representation that captures long-term motion dependencies and spatial-temporal relations. We demonstrate the effectiveness of our learned temporal representations on activity classification across multiple modalities and datasets such as NTU RGB+D and MSR Daily Activity 3D. Our framework is generic to any input modality, i.e., RGB, depth, and RGB-D videos.

MicroRNAs can coordinately repress multiple target genes and interfere with the biological functions of the cell, such as proliferation and apoptosis. In the present study, we report that miR-200b was downregulated in malignant glioma cell lines and specimens. Overexpression of miR-200b suppressed the proliferation and colony formation of glioma cells. An oncogene encoding cAMP responsive element-binding protein 1 (CREB1), which has been shown to be an important transcription factor involved in the proliferation, survival, and metastasis of tumor cells, was here confirmed as a direct target gene of miR-200b. CREB1 was also found to be present at a high level in human glioma tissues. This was inversely correlated with miR-200b expression. Ectopic expression of CREB1 attenuated the growth suppressive phenotypes of glioma cells caused by miR-200b. These results indicate that miR-200b targets the CREB1 gene and suppresses glioma cell growth, suggesting that miR-200b shows tumor-suppressive activity in human malignant glioma.

Objective: To analyze the clinical features in children with anti-NMDAR encephalitis combined with myelin oligodendrocyte glycoprotein antibody (MOG ab).

No abstract