Search

In the interdisciplinary field of modern computer vision and natural language processing, digital talking facial generation technology has become an increasingly important research topic. Digital facial generation technology focuses on generating realistic facial images based on predetermined text or audio sequences. In recent years, deep learning methods such as convolutional neural networks, generative adversarial networks, and neural rendering fields have been used for digital talking face generation, which shows significant research and application value. These methods have not only attract widespread attention from the academic community, but also have been applied in industry to solve specific problems in image processing and computer vision. Although some progress has been made, the practical application of these technologies still faces many challenges. Comprehensively review and evaluate the specific implementation of deep learning methods in the generation of digital talking face to identify the advantages and disadvantages of existing methods, explore common problems that need to be solved, and highlight open issues that still require further research. In addition, currently available datasets from a statistical perspective were listed, evaluated and compared so that researchers can more easily choose datasets that meet their needs.

Objective To investigate the expression level of long non-coding RNA (lncRNA) AL365181.2 in cholangiocarcinoma (CHOL) and its effect on the functional characteristics of CHOL cells. Methods The Cancer Genome Atlas (TCGA) database was used to compare the expression level of lncRNA AL365181.2 between cancerous tissue and paracancerous tissue in CHOL patients, and the association between the expression level of lncRNA AL365181.2 and immune cell infiltration in CHOL tissue was analyzed. The Gene Set Enrichment Analysis (GSEA) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis were performed for lncRNA AL365181.2. EdU assay, wound healing assay, Transwell assay, and xenograft tumor formation experiment were used to investigate the impact of lncRNA AL365181.2 on the proliferation, migration, invasion, and tumorigenic abilities of CHOL cells. Results The analysis of TCGA data showed that the expression level of lncRNA AL365181.2 in CHOL tissue was significantly higher than that in paracancerous tissue (Z=4.00,P

High-performance terahertz wave detectors at room temperature are still urgently required for a wide range of applications. The available technologies, however, are plagued by low sensitivity, narrow spectral bandwidth, complicated structure, and high noise equivalent power (NEP). Here, we have demonstrated a Weyl semimetal surface plasmon-enhanced high-performance terahertz wave detectors which are based on microdisk array deposited WTe2 nanofilm epitaxially grown on GaN substrate for room temperature operation. With the microdisk array combined the WTe2 layer, strong terahertz wave surface plasmon polaritons can be generated at the WTe2–air interfaces, which results in significant improvement in detecting performance. For the 40 μm diameter microdisk array, a detectivity (D *) of 5.52 × 1012 cm Hz1/2 pW−1 at 0.1 THz is achieved at room temperature. In addition, the responsivity (R A) of 8.78 A W−1 is also obtained. Such high-performance millimeter and terahertz wave photodetectors are useful for wide applications such as high capacity communications, walk-through security, biological diagnosis, spectroscopy, and remote sensing.

With the advancement of computer vision technology, vision-based target perception has emerged as a predominant approach for harvesting robots to identify and locate fruits. However, little attention has been paid to the fact that fruits may be obscured by stems or other objects. In order to improve the vision detection ability of fruit harvesting robot, a fruit target selection and location approach considering obstacle perception was proposed. To enrich the dataset for tomato harvesting, synthetic data were generated by rendering a 3D simulated model of the tomato greenhouse environment, and automatically producing corresponding pixel-level semantic segmentation labels. An attention-based spatial-relationship feature extraction module (SFM) with lower computational complexity was designed to enhance the ability of semantic segmentation network DeepLab v3+ in accurately segmenting linear-structured obstructions such as stems and wires. An adaptive K-means clustering method was developed to distinguish individual instances of fruits. Furthermore, a barrier-free fruit selection algorithm that integrates information of obstacles and fruit instances was proposed to identify the closest and largest non-occluded fruit as the optimal picking target. The improved semantic segmentation network exhibited enhanced performance, achieving an accuracy of 96.75%. Notably, the Intersection-over-Union (IoU) of wire and stem classes was improved by 5.0% and 2.3%, respectively. Our target selection method demonstrated accurate identification of obstacle types (96.15%) and effectively excluding fruits obstructed by strongly resistant objects (86.67%). Compared to the fruit detection method without visual obstacle avoidance (Yolo v5), our approach exhibited an 18.9% increase in selection precision and a 1.3% reduction in location error. The improved semantic segmentation algorithm significantly increased the segmentation accuracy of linear-structured obstacles, and the obstacle perception algorithm effectively avoided occluded fruits. The proposed method demonstrated an appreciable ability in precisely selecting and locating barrier-free fruits within non-structural environments, especially avoiding fruits obscured by stems or wires. This approach provides a more reliable and practical solution for fruit selection and localization for harvesting robots, while also being applicable to other fruits and vegetables such as sweet peppers and kiwis. [ABSTRACT FROM AUTHOR]

This paper describes a unique, extremely sensitive biophotonic sensor with a three-tier S-tapered (3S) structure. It is designed for the real-time detection of Shigella flexneri (S. flexneri), a common foodborne pathogen that causes severe gastrointestinal diseases. The sensor development includes three distinct diameters of S-tapered structures. The performance of tapered sections was improved by using molybdenum disulfide nanosheets (MoS2-NSs), zinc oxide nanowires (ZnO-NWs), and photoluminescent bimetallic gold–copper nanoclusters (AuCu–NCs). These nanoparticles greatly improve the sensor's performance. The sensor is further functionalized using anti-S. flexneri antibodies, allowing for the precise detection and capture of the target bacterium. The results show that the sensor can detect S. flexneri rapidly and accurately, with a linear detection range of 1–108 colony-forming units per milliliter (CFU/ml) and a low detection limit of 4.412 CFU/ml. In addition, the sensor's ability to identify S. flexneri biofilms is demonstrated. Biofilm detection allows us to better understand and control biofilm concerns in the environment, equipment, and biomedical devices. Aptamer examines confirm the sensor's ability to detect S. flexneri from the lateral direction. This study makes a significant contribution to the field of biosensing because no biophotonic sensor has previously been developed specifically for the detection of S. flexneri, fulfilling a critical gap in the arena of food safety and pathogen detection. The 3S sensor's performance, robustness, and potential for practical applications make it an important addition to the field of photonics. [ABSTRACT FROM AUTHOR]