This paper focuses on a novel and challenging detection scenario: A majority of true objects/instances is unlabeled in the datasets, so these missing-labeled areas will be regarded as the background during training. Previous art [1] on this problem has proposed to use soft sampling to re-weight the gradients of RoIs based on the overlaps with positive instances, while their method is mainly based on the two-stage detector (i.e. Faster RCNN) which is more robust and friendly for the missing label scenario. In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image. Our design is built on the one-stage detector which is faster and lighter. Inspired by the Focal Loss [2] formulation, we make several significant modifications to fit on the missing-annotation circumstance. We conduct extensive experiments on the curated PASCAL VOC [3] and MS COCO [4] datasets. The results demonstrate that our proposed method outperforms the baseline and other state-of-the-arts by a large margin.
Newcastle disease virus (NDV) causes an infectious disease that poses a major threat to poultry health. Our previous study identified a chicken brain-specific caspase recruitment domain-containing protein 11 (CARD11) that was upregulated in chicken neurons and inhibited NDV replication. This raises the question of whether CARD11 plays a role in inhibiting viruses in non-neural cells. Here, chicken fibroblasts were used as a non-neural cell model to investigate the role. CARD11 expression was not significantly upregulated by either velogenic or lentogenic NDV infection in chicken fibroblasts. Viral replication was decreased in DF-1 cells stably overexpressing CARD11, while viral growth was significantly increased in the CARD11-knockdown DF-1 cell line. Moreover, CARD11 colocalized with the viral P protein and aggregated around the fibroblast nucleus, suggesting that an interaction existed between CARD11 and the viral P protein; this interaction was further examined by suppressing viral RNA polymerase activity by using a minigenome assay. Viral replication was inhibited by CARD11 in fibroblasts, and this result was consistent with our previous report in chicken neurons. Importantly, CARD11 was observed to reduce the syncytia induced by either velogenic virus infection or viral haemagglutinin-neuraminidase (HN) and F cotransfection in fibroblasts. We found that CARD11 inhibited the expression of the host protease furin, which is essential for cleavage of the viral F protein to trigger fusogenic activity. Furthermore, the CARD11-Bcl10-MALT1 (CBM) signalosome was found to suppress furin expression, which resulted in a reduction in the cleavage efficiency of the viral F protein to further inhibit viral syncytia. Taken together, our findings mainly demonstrated a novel CARD11 inhibitory mechanism for viral fusogenic activity in chicken fibroblasts, and this mechanism explains the antiviral roles of this molecule in NDV pathogenesis.
The estimation of continuous and simultaneous multijoint angle based on surface electromyography (sEMG) signal is of considerable significance in rehabilitation practice. However, there are few studies on the continuous joint angle of multiple joints at present. In this paper, the wavelet packet energy entropy (WPEE) of the special subspace was investigated as a feature of the sEMG signal. An Elman neural network optimized by genetic algorithm (GA) was established to estimate the joint angle of shoulder and elbow. First, the accuracy of the method is verified by estimating the angle of the shoulder joint. Then, this method was used to simultaneously and continuously estimate the shoulder and elbow joint angle. Six subjects flexed and extended the upper limbs according to the intended movements of the experiment. The results show that this method can obtain a decent performance with a RMSE of 3.4717 and R2 of 0.8283 in shoulder movement and with a RMSE of 4.1582 and R2 of 0.8114 in continuous synchronous movement of the shoulder and elbow.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.