Search

Visual information extraction (VIE), which aims to simultaneously perform OCR and information extraction in a unified framework, has drawn increasing attention due to its essential role in various applications like understanding receipts, goods, and traffic signs. However, as existing benchmark datasets for VIE mainly consist of document images without the adequate diversity of layout structures, background disturbs, and entity categories, they cannot fully reveal the challenges of real-world applications. In this paper, we propose a large-scale dataset consisting of camera images for VIE, which contains not only the larger variance of layout, backgrounds, and fonts but also much more types of entities. Besides, we propose a novel framework for end-to-end VIE that combines the stages of OCR and information extraction in an end-to-end learning fashion. Different from the previous end-to-end approaches that directly adopt OCR features as the input of an information extraction module, we propose to use contrastive learning to narrow the semantic gap caused by the difference between the tasks of OCR and information extraction. We evaluate the existing end-to-end methods for VIE on the proposed dataset and observe that the performance of these methods has a distinguishable drop from SROIE (a widely used English dataset) to our proposed dataset due to the larger variance of layout and entities. These results demonstrate our dataset is more practical for promoting advanced VIE algorithms. In addition, experiments demonstrate that the proposed VIE method consistently achieves the obvious performance gains on the proposed and SROIE datasets., 15 pages, 6 figures, ICDAR2023

Background: Rhizoctonia solani is a pathogenic fungus that causes serious diseases in many crops, including rice, wheat, and soybeans. In crop production, it is very important to understand the pathogenicity of this fungus, which is still elusive. It might be helpful to comprehensively understand its genomic information using different genome annotation strategies. Methods: Aiming to improve the genome annotation of R. solani, we performed a proteogenomic study based on the existing data. Based on our study, a total of 1060 newly identified genes, 36 revised genes, 139 single amino acid variants (SAAVs), 8 alternative splicing genes, and diverse post-translational modifications (PTMs) events were identified in R. solani AG3. Further functional annotation on these 1060 newly identified genes was performed through homology analysis with its 5 closest relative fungi. Results: Based on this, 2 novel candidate pathogenic genes, which might be associated with pathogen-host interaction, were discovered. In addition, in order to increase the reliability and novelty of the newly identified genes in R. solani AG3, 1060 newly identified genes were compared with the newly published available R. solani genome sequences of AG1, AG2, AG4, AG5, AG6, and AG8. There are 490 homologous sequences. We combined the proteogenomic results with the genome alignment results and finally identified 570 novel genes in R. solani. Conclusion: These findings extended R. solani genome annotation and provided a wealth of resources for research on R. solani.

Protein homeostasis is tightly regulated by protein quality control systems such as chaperones and proteases. In cyanobacteria, the ClpXP proteolytic complex is regarded as a representative proteolytic system and consists of a hexameric ATPase ClpX and a tetradecameric peptidase ClpP. However, the functions and molecular mechanisms of ClpX in cyanobacteria remain unclear. This study aimed to decipher the unique contributions and regulatory networks of ClpX in the model cyanobacterium Synechocystis sp. PCC 6803 (hereafter Synechocystis). We showed that the interruption of clpX led to slower growth, decreased high light tolerance, and impaired photosynthetic cyclic electron transfer. A quantitative proteomic strategy was employed to globally identify ClpX-regulated proteins in Synechocystis cells. In total, we identified 172 differentially expressed proteins (DEPs) upon the interruption of clpX. Functional analysis revealed that these DEPs are involved in diverse biological processes, including glycolysis, nitrogen assimilation, photosynthetic electron transport, ATP-binding cassette (ABC) transporters, and two-component signal transduction. The expression of 24 DEPs was confirmed by parallel reaction monitoring (PRM) analysis. In particular, many hypothetical or unknown proteins were found to be regulated by ClpX, providing new candidates for future functional studies on ClpX. Together, our study provides a comprehensive ClpX-regulated protein network, and the results serve as an important resource for understanding protein quality control systems in cyanobacteria.

Discharge faults in the gas-insulated transmission lines (GIL) induce fast transient overvoltages. The voltage traveling waves generated by the discharge faults are characterized by their high amplitudes, short rise times, and high frequencies. Traditionally, sensors installed inside the GIL enclosure are used to measure the transient overvoltage signals. However, it is difficult to be applied to the substations under operation. In order to measure transient overvoltage safely and conveniently, this paper proposed a sensing method based on capacitive divider which is outside the GIL enclosure. The high-voltage arm capacitor is composed of stray capacitance between the GIL lead-out line and the electrode plate. And the low-voltage arm of the sensor is chip capacitors. Calibration and field tests proved that the sensor has a broad bandwidth response and can accurately measure the overvoltages caused by GIL discharge failures. The external overvoltage sensor provided a new solution for GIL discharge fault monitoring in the GIL.

Scene text recognition (STR) is very challenging due to the diversity of text instances and the complexity of scenes. The community has paid increasing attention to boost the performance by improving the pre-processing image module, like rectification and deblurring, or the sequence translator. However, another critical module, i.e., the feature sequence extractor, has not been extensively explored. In this work, inspired by the success of neural architecture search (NAS), which can identify better architectures than human-designed ones, we propose automated STR (AutoSTR) to search data-dependent backbones to boost text recognition performance. First, we design a domain-specific search space for STR, which contains both choices on operations and constraints on the downsampling path. Then, we propose a two-step search algorithm, which decouples operations and downsampling path, for an efficient search in the given space. Experiments demonstrate that, by searching data-dependent backbones, AutoSTR can outperform the state-of-the-art approaches on standard benchmarks with much fewer FLOPS and model parameters., Comment: ECCV 2020

Ethylene glycol (EG) starts to attract attention as a robust solvent for lignin processing. However its solution structure has not been revealed. In this effort, small angle neutron scattering (SANS) and dynamic light scattering are used to understand the dissolution of kraft lignin in EG and the impact of the resultant solution structure on nanoparticle preparation. Lignin solutions with different concentrations (0.6 to 13.0wt%) were explored by SANS, allowing evaluation of the solvent quality, the conformation of lignin subunits and their aggregation in EG. Molecular interactions between EG and lignin were discussed and compared to those between DMSO and lignin. The process of nanoparticle preparation from EG solutions upon addition of anti-solvents was also discussed.

Chinese scene text reading is one of the most challenging problems in computer vision and has attracted great interest. Different from English text, Chinese has more than 6000 commonly used characters and Chinesecharacters can be arranged in various layouts with numerous fonts. The Chinese signboards in street view are a good choice for Chinese scene text images since they have different backgrounds, fonts and layouts. We organized a competition called ICDAR2019-ReCTS, which mainly focuses on reading Chinese text on signboard. This report presents the final results of the competition. A large-scale dataset of 25,000 annotated signboard images, in which all the text lines and characters are annotated with locations and transcriptions, were released. Four tasks, namely character recognition, text line recognition, text line detection and end-to-end recognition were set up. Besides, considering the Chinese text ambiguity issue, we proposed a multi ground truth (multi-GT) evaluation method to make evaluation fairer. The competition started on March 1, 2019 and ended on April 30, 2019. 262 submissions from 46 teams are received. Most of the participants come from universities, research institutes, and tech companies in China. There are also some participants from the United States, Australia, Singapore, and Korea. 21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4. The official website for the competition is http://rrc.cvc.uab.es/?ch=12., Comment: International Conference on Document Analysis and Recognition, 2019

The electro-hydraulic servo pump control system (EHSPCS) is a high-performance control unit that integrates a permanent magnet synchronous motor (PMSM) and a closed hydraulic system (CHS). The design features of high integration and a high power-weight ratio lead to the poor heat dissipation capacity and high thermal balance temperature of the system. Excessive temperature will seriously affect the system’s performance and service life. Therefore, the thermal balance analysis method of the EHSPCS under different loads and different wind speeds was proposed in this paper. Firstly, the PMSM and CHS were taken as research objects to analyze the heating source of the system. The thermal power model was established, and the calculation was performed. The variation rule of the thermal power generated by each component with the load torque under the typical rotating speed was obtained. Secondly, the system’s temperature field thermal balance solution model was established. ANSYS and AMESim software were used to calculate the thermal balance points of the PMSM and CHS under different working conditions. The change rule of the thermal balance temperature field of the EHSPCS under different loads was analyzed with the conditions of the natural cooling and forced wind cooling of the PMSM. Finally, an experimental platform was built for experimental research, and the experimental temperature of the system under different loads and different wind speeds was measured. Through comparison and analysis with the simulation results, the correctness and feasibility of the thermal balance theoretical analysis method were verified. The research results will lay the foundation for thermal balance research on the EHSPCS, and have guiding significance for system design, component selection, and load matching.