RESUMEN
With the advent of Transformer-based convolutional neural networks, stereo matching algorithms have achieved state-of-the-art accuracy in disparity estimation. Nevertheless, this method requires much model inference time, which is the main reason limiting its application in many vision tasks and robots. Facing the trade-off problem between accuracy and efficiency, this paper proposes an efficient and accurate multi-level cascaded recurrent network, LMCR-Stereo. To recover the detailed information of stereo images more accurately, we first design a multi-level network to update the difference values in a coarse-to-fine recurrent iterative manner. Then, we propose a new pair of slow-fast multi-stage superposition inference structures to accommodate the differences between different scene data. Besides, to ensure better disparity estimation accuracy with faster model inference speed, we introduce a pair of adaptive and lightweight group correlation layers to reduce the impact of erroneous rectification and significantly improve model inference speed. The experimental results show that the proposed approach achieves a competitive disparity estimation accuracy with a faster model inference speed than the current state-of-the-art methods. Notably, the model inference speed of the proposed approach is improved by 46.0% and 50.4% in the SceneFlow test set and Middlebury benchmark, respectively.
RESUMEN
The sweet potato, which is an important tuber crop in China, is susceptible to a variety of pathogens and insect pests during cultivation and production. Stem rot is a common sweet potato disease that seriously affects tuber yield and quality. Unfortunately, there have been relatively few studies on the mechanism mediating the stem rot resistance of sweet potatoes. In this study, a transcriptome sequencing analysis was completed using Xushu 48 samples at different stages (T1, T2, and T3) of the stem rot infection. The T1 vs. T2, T1 vs. T3, and T2 vs. T3 comparisons detected 44,839, 81,436, and 61,932 differentially expressed genes (DEGs), respectively. The DEGs encoded proteins primarily involved in alanine, aspartate, and glutamate metabolism (ko00250), carbon fixation in photosynthetic organisms (ko00710), and amino sugar and nucleotide sugar metabolism (ko00520). Furthermore, some candidate genes induced by phytopathogen infections were identified, including gene-encoding receptor-like protein kinases (RLK5 and RLK7), an LRR receptor-like serine/threonine protein kinase (SERK1), and transcription factors (bHLH137, ERF9, MYB73, and NAC053). The results of this study provide genetic insights that are relevant to future explorations of sweet potato stem rot resistance, while also providing the theoretical basis for breeding sweet potato varieties that are resistant to stem rot and other diseases.
