Search

Linguistic knowledge helps a lot in scene text recognition by providing semantic information to refine the character sequence. The visual model only focuses on the visual texture of characters without actively learning linguistic information, which leads to poor model recognition rates in some noisy (distorted and blurry, etc.) images. In order to address the aforementioned issues, this study builds upon the most recent findings of the Vision Transformer, and our approach (called Display-Semantic Transformer, or DST for short) constructs a masked language model and a semantic visual interaction module. The model can mine deep semantic information from images to assist scene text recognition and improve the robustness of the model. The semantic visual interaction module can better realize the interaction between semantic information and visual features. In this way, the visual features can be enhanced by the semantic information so that the model can achieve a better recognition effect. The experimental results show that our model improves the average recognition accuracy on six benchmark test sets by nearly 2% compared to the baseline. Our model retains the benefits of having a small number of parameters and allows for fast inference speed. Additionally, it attains a more optimal balance between accuracy and speed.

Patients undergoing immunotherapy always exhibit a low-response rate due to tumor heterogeneity and immune surveillance in the tumor. Angiogenesis plays an important role in affecting the status of tumor-infiltrated lymphocytes by inducing hypoxia and acidosis microenvironment, suggesting its synergistic potential in immunotherapy. However, the antitumor efficacy of singular anti-angiogenesis therapy often suffers from failure in the clinic due to the compensatory pro-angiogenesis signaling pathway. In this work, classic injectable thermosensitive PLGA-PEG-PLGA copolymer was used to construct a platform to co-deliver CA4P (vascular disruptive agent) and EPI for inducing immunogenic cell death of cancer cells by targeting the tumor immune microenvironment. Investigation of 4T1 tumor-bearing mouse models suggests that local administration of injectable V+E@Gel could significantly inhibit the proliferation of cancer cells and prolong the survival rate of 4T1 tumor-bearing mouse models. Histological analysis further indicates that V+E@Gel could effectively inhibit tumor angiogenesis and metastasis by down-regulating the expression of CD34, CD31, MTA1 and TGF-β. Moreover, due to the sustained release kinetics of V+E@Gel, its local administration relieves the immune surveillance in tumor tissues and thus induces a robust and long-lasting specific antitumor immune response. Overall, this work provides a new treatment strategy through the mediation of the tumor immune microenvironment by vascular disruption to fulfill enhanced chemotherapy and immunotherapy.

In this study, Friction plug welding (FPW) for 8 mm thickness AA2219-T87 sheets were carried out, and defect-free joints were obtained. The geometric size of plug and plate hole, rotational speed and welding force exhibit significant effects on the weld formation. Meanwhile, it is concluded that significant inhomogeneity of microstructure and mechanical properties exists in FPW joints. The recrystallization zone has the highest mechanical properties owing to the fine equiaxed grains and uniformly distributed θ precipitates. The entire plug, thermo-mechanically affected zone and nugget thermo-mechanically affected zone closed to the bonding interface are significantly softened due to the deformation of the grains and θ’ precipitate dissolution. The ultimate tensile strength (UTS) and elongation of the FPW joints can reach 359 MPa and 7.3% at 77 K and 305 MPa and 5% at 298 K, respectively.

Girth weld cracking of long-distance oil and gas pipelines yields substantial harm to pipeline safety and may cause serious accidents. As of today, non-destructive testing has been one of the most common methods for predicting potential faults and ensuring safe operation. Classical pipeline non-destructive testing methods include magnetic flux leakage testing and the use of ultrasonic testing by electromagnetic acoustic transducers. However, they are incapable of identifying the defects in complex surfaces like girth welds. Magnetic flux leakage testing exhibits poor anti-interference abilities and low space resolution. Ultrasonic testing by electromagnetic acoustic transducers suffer from low conversion efficiency and poor signal quality. In order to overcome the disadvantages of conventional pipeline non-destructive testing methods, we propose an embedded eddy current testing system by leveraging image processing and neural networks. Hough transform and the contour extraction technique are employed to extract the characteristic features from the two-dimensional (2D) eddy current impedance image. Experiment results show that the system can effectively identify the girth weld defects, featuring an accuracy of up to 92%. The low power consumption and compactness of the proposed system makes it a great candidate for pipeline inner inspection.