This paper advocates a novel video saliency detection method based on the spatial-temporal saliency fusion and low-rank coherency guided saliency diffusion. In sharp contrast to the conventional methods, which conduct saliency detection locally in a frame-by-frame way and could easily give rise to incorrect low-level saliency map, in order to overcome the existing difficulties, this paper proposes to fuse the color saliency based on global motion clues in a batch-wise fashion. And we also propose low-rank coherency guided spatial-temporal saliency diffusion to guarantee the temporal smoothness of saliency maps. Meanwhile, a series of saliency boosting strategies are designed to further improve the saliency accuracy. First, the original long-term video sequence is equally segmented into many short-term frame batches, and the motion clues of the individual video batch are integrated and diffused temporally to facilitate the computation of color saliency. Then, based on the obtained saliency clues, inter-batch saliency priors are modeled to guide the low-level saliency fusion. After that, both the raw color information and the fused low-level saliency are regarded as the low-rank coherency clues, which are employed to guide the spatial-temporal saliency diffusion with the help of an additional permutation matrix serving as the alternative rank selection strategy. Thus, it could guarantee the robustness of the saliency map's temporal consistence, and further boost the accuracy of the computed saliency map. Moreover, we conduct extensive experiments on five public available benchmarks, and make comprehensive, quantitative evaluations between our method and 16 state-of-the-art techniques. All the results demonstrate the superiority of our method in accuracy, reliability, robustness, and versatility.

AIMTo introduce natural orifice transgastric endoscopic surgery (NOTES) tube ileostomy using pelvis-directed submucosal tunneling endoscopic gastrostomy and endoscopic tube ileostomy.METHODSSix live pigs (three each in the non-survival and survival groups) were used. A double-channeled therapeutic endoscope was introduced perorally into the stomach. A gastrostomy was made using a 2-cm transversal mucosal incision following the creation of a 5-cm longitudinal pelvis-directed submucosal tunnel. The pneumoperitoneum was established via the endoscope. In the initial three operations of the series, a laparoscope was transumbilically inserted for guiding the tunnel direction, intraperitoneal spatial orientation and distal ileum identification. Endoscopic tube ileostomy was conducted by adopting an introducer method and using a Percutaneous Endoscopic Gastrostomy Catheter Kit equipped with the Loop Fixture. The distal tip of the 15 Fr catheter was placed toward the proximal limb of the ileum to optimize intestinal content drainage. Finally, the tunnel entrance of the gastrostomy was closed using nylon endoloops with the aid of a twin grasper. The gross and histopathological integrity of gastrostomy closure and the abdominal wall-ileum stoma tract formation were assessed 1 wk after the operation.RESULTSTransgastric endoscopic tube ileostomy was successful in all six pigs, without major bleeding. The mean operating time was 71 min (range: 60-110 min). There were no intraoperative complications or hemodynamic instability. The post-mortem, which was conducted 1-wk postoperatively, showed complete healing of the gastrostomy and adequate stoma tract formation of ileostomy.CONCLUSIONTransgastric endoscopic tube ileostomy is technically feasible and reproducible in an animal model, and this technique is worthy of further improvement.

Existing neural stochastic differential equation models, such as SDE-Net, can quantify the uncertainties of deep neural networks (DNNs) from a dynamical system perspective. SDE-Net is either dominated by its drift net with in-distribution (ID) data to achieve good predictive accuracy, or dominated by its diffusion net with out-of-distribution (OOD) data to generate high diffusion for characterizing model uncertainty. However, it does not consider the general situation in a wider field, such as ID data with noise or high missing rates in practice. In order to effectively deal with noisy ID data for credible uncertainty estimation, we propose a vNPs-SDE model, which firstly applies variants of neural processes (NPs) to deal with the noisy ID data, following which the completed ID data can be processed more effectively by SDE-Net. Experimental results show that the proposed vNPs-SDE model can be implemented with convolutional conditional neural processes (ConvCNPs), which have the property of translation equivariance, and can effectively handle the ID data with missing rates for one-dimensional (1D) regression and two-dimensional (2D) image classification tasks. Alternatively, vNPs-SDE can be implemented with conditional neural processes (CNPs) or attentive neural processes (ANPs), which have the property of permutation invariance, and exceeds vanilla SDE-Net in multidimensional regression tasks.

As the state-of-the-art technology of Bayesian inference, based on low-dimensional principal components analysis (PCA) subspace inference methods can provide approximately accurate predictive distribution and well calibrated uncertainty. However, the main problem of PCA method is that it is a linear subspace feature extractor, and it cannot effectively represent the nonlinearly high-dimensional parameter space of deep neural networks (DNNs). Firstly, in this paper, in order to solve the main problem of the linear characteristics of PCA in high-dimensional space, we apply kernel PCA to extract higher-order statistical information in parameter space of DNNs. Secondly, to improve the efficiency of subsequent computation, we propose a strictly ordered incremental kernel PCA (InKPCA) subspace of parameter space within stochastic gradient descent (SGD) trajectories. In the proposed InKPCA subspace, we employ two approximation inference methods: elliptical slice sampling (ESS) and variational inference (VI). Finally, to further improve the memory efficiency of computing the kernel matrix, we apply Nyström approximation to determine the suitable size of subsets in the original datasets. The novelty of this paper is that it is the first time to apply the proposed InKPCA subspace with Nyström approximation for Bayesian inference in DNNs, and the results show that it can produce more accurate predictions and well-calibrated predictive uncertainty in regression and classification tasks of deep learning.