No abstract

Vehicle re-identification (ReID) focuses on searching for images of the same vehicle across different cameras and can be considered as the most fine-grained ID-level classification task. It is fundamentally challenging due to the significant differences in appearance presented by a vehicle with the same ID (especially from different viewpoints) coupled with the subtle differences between vehicles with different IDs. Spatial attention mechanisms that have been proven to be effective in computer vision tasks also play an important role in vehicle ReID. However, they often require expensive key-point labels or suffer from noisy attention masks when trained without key-point labels. In this work, we propose a transformer-based attention network (TAN) for learning spatial attention information and hence for facilitating learning of discriminative features for vehicle ReID. Specifically, in contrast to previous studies that adopted a transformer network, we designed the attention network as an independent branch that can be flexibly utilized in various tasks. Moreover, we combined the TAN with two other branches: one to extract global features that define the image-level structures, and the other to extract the auxiliary side-attribute features that are invariant to viewpoint, such as color, car type, etc. To validate the proposed approach, experiments were conducted on two vehicle datasets (the VeRi-776 and VehicleID datasets) and a person dataset (Market-1501). The experimental results demonstrated that the proposed TAN is effective in improving the performance of both the vehicle and person ReID tasks, and the proposed method achieves state-of-the-art (SOTA) perfomance.

No abstract

Targeting at the problems existing in the multi-objective scheduling of traditional flexible job shop and the complexity of multi-resource allocation, this paper establishes an improved calculation model considering the optimization of such four targets as completion time, labour distribution, equipment compliance and production cost. The multi-objective integrated constraint optimization algorithm is designed and the Pareto solution set following different rules based on the NSGA-П algorithm is finally obtained. The research results show that the centralized selection of processing equipment and low efficiency of the job sequencing in the scheduling of traditional flexible job shop get improved. The personnel scheduling in the flexible working resources is highlighted, and multi-rule dynamic programming is introduced to get the optimal completion time and personnel allocation program. The optimal scheduling program can be quickly searched out using the NSGA-П algorithm, which effectively improves the search efficiency. The batch production within certain range can reduce the product processing time, but at the same time, it will increase the manufacturing costs. The use of smooth movement can reduce the overall processing time, but a too small movement volume will cause the increase in the number of movements. The exact match between the operators, numerical control equipment and the product processing procedures contributes to the feasibility of the preproduction operation plan.

The interaction between 3-spiro-2'-pyrrolidine-3'-spiro-3″-piperidine-2,3″-dione (PPD) and bovine serum albumin (BSA) in aqueous solution was studied using fluorescence and UV-vis spectroscopy. Fluorescence emission data revealed that BSA (1.00 × 10(-5)  mol/L) fluorescence was statically quenched by PPD at various concentrations, which implies that a PPD-BSA complex was formed. The binding constant (KA ), the number of binding sites (n) and the specific binding site of the PPD with BSA were determined. Energy-transfer efficiency parameters were determined and the mechanism of the interaction discussed. The thermodynamic parameters, ΔG, ΔH and ΔS, were obtained according to van't Hoff's equation, showing the involvement of hydrophobic forces in these interactions. The effect of PPD acting on the BSA conformation was detected by synchronous fluorescence.