RESUMO
The mining of diverse patterns from bike flow has attracted widespread interest from researchers and practitioners. Prior arts concentrate on forecasting the flow evolution from bike demand records. Nevertheless, a tricky reality is the frequent occurrence of missing bike flow, which hinders us from accurately understanding flow patterns. This study investigates an interesting task, i.e., Bike-sharing demand recovery (Biker). Biker is not a simple time-series imputation problem, rather, it confronts three concerns: observation uncertainty, complex dependencies, and environmental facts. To this end, we present a novel diffusion probabilistic solution with factual knowledge fusion, namely DBiker. Specifically, DBiker is the first attempt to extend the diffusion probabilistic models to the Biker task, along with a conditional Markov decision-making process. In contrast to existing probabilistic solutions, DBiker forecasts missing observations through progressive steps guided by an adaptive prior. Particularly, we introduce a Flow Conditioner with step embedding and a Factual Extractor to explore the complex dependencies and multiple environmental facts, respectively. Additionally, we devise a self-gated fusion layer that adaptively selects valuable knowledge to act as an adaptive prior, guiding the generation of missing observations. Finally, experiments conducted on three real-world bike systems demonstrate the superiority of DBiker against several baselines.
RESUMO
With the prevalent use of LiDAR sensors in autonomous driving, 3D point cloud object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames. Motivated by the success of transformers, we propose Point Tracking TRansformer (PTTR), which efficiently predicts high-quality 3D tracking results in a coarse-to-fine manner with the help of transformer operations. PTTR consists of three novel designs. 1) Instead of random sampling, we design Relation-Aware Sampling to preserve relevant points to the given template during subsampling. 2) We propose a Point Relation Transformer for effective feature aggregation and feature matching between the template and search region. 3) Based on the coarse tracking results, we employ a novel Prediction Refinement Module to obtain the final refined prediction through local feature pooling. In addition, motivated by the favorable properties of the Bird's-Eye View (BEV) of point clouds in capturing object motion, we further design a more advanced framework named PTTR++, which incorporates both the point-wise view and BEV representation to exploit their complementary effect in generating high-quality tracking results. PTTR++ substantially boosts the tracking performance on top of PTTR with low computational overhead. Extensive experiments over multiple datasets show that our proposed approaches achieve superior 3D tracking accuracy and efficiency.
RESUMO
Soybean is one of the important oil crops and a major source of protein and lipids. Drought can cause severe soybean yields. Dehydrin protein (DHN) is a subfamily of LEA proteins that play an important role in plant responses to abiotic stresses. In this study, the soybean GmDHN9 gene was cloned and induced under a variety of abiotic stresses. Results showed that the GmDHN9 gene response was more pronounced under drought induction. Subcellular localization results indicated that the protein was localized in the cytoplasm. The role of transgenic Arabidopsis plants in drought stress response was further studied. Under drought stress, the germination rate, root length, chlorophyll, proline, relative water content, and antioxidant enzyme content of transgenic Arabidopsis thaliana transgenic genes were higher than those of wild-type plants, and transgenic plants contained less O2-, H2O2 and MDA contents. In short, the GmDHN9 gene can regulate the homeostasis of ROS and enhance the drought resistance of plants.