Shengyu Zhao’s research while affiliated with Nanjing Forestry University and other places

Single image super-resolution aims to restore high-resolution images from low-resolution images. Recently, many methods have tackled image super-resolution by leveraging local or global features to boost performance. However, they fail to combine both feature types and often have high parameter counts. We propose a Lightweight Self-Attention Guidance Network (LSAGNet) to address the aforementioned issues. We designed a simple and efficient dynamic local attention (DLA) module to effectively extract local features. Existing Transformer networks often rely on query-key similarities for feature aggregation. However, blindly using these similarities hinders super-resolution reconstruction by failing to retain strong correlations and introducing weak ones. To address this issue, we propose a global self-attention (GSA) mechanism based on a soft-thresholding operation, designed to retain strongly correlated information. Experimental results demonstrate that the proposed LSAGNet achieves an excellent balance between performance and parameter efficiency while also achieving competitive accuracy compared to state-of-the-art methods.

To address the issues of low detection accuracy and poor adaptability in complex orchard environments (such as varying lighting conditions, branch and leaf occlusion, fruit overlap, and small targets), this paper proposes an improved pear detection model based on YOLO11, called YOLO11-Pear. First, to improve the model’s capability in detecting occluded pears, the C2PSS module is introduced to replace the original C2PSA module. Second, a small target detection layer is added to improve the model’s ability to detect small pears. Finally, the upsampling process is replaced with DySample, which not only maintains a high efficiency but also improves the processing speed and expands the model’s application range. To validate the effectiveness of the model, a dataset of images of Qiu Yue pears and Cui Guan pears was constructed. The experimental results showed that the improved YOLO11-Pear model achieved precision, recall, mAP50, and mAP50–95 values of 96.3%, 84.2%, 92.1%, and 80.2%, respectively, outperforming YOLO11n by 3.6%, 1%, 2.1%, and 3.2%. With only a 2.4% increase in the number of parameters compared to the original model, YOLO11-Pear enables fast and accurate pear detection in complex orchard environments.

Open source has revolutionized how software development is carried out, with a growing number of individuals and organizations contributing to open source projects. As the importance of open source continues to grow, companies also expect to grow thriving and sustainable open source communities with continued contributions and better collaborations. In this study, we applied the contribution leaderboard to seven open source projects initiated by Alibaba. We conducted a case study to investigate the perceptions and facts regarding how to motivate collaboration through gamification. Specifically, we employed a social network algorithm, OpenRank, to evaluate and steer developers' contributions. We validated the effectiveness of OpenRank by comparing it with other evaluation metrics and surveying developers. Through semi-structured interviews and project metric analysis, we found that the OpenRank Leaderboard can promote transparent communication environments, a better community atmosphere, and improved collaboration behavior.

As one of the important components of Earth observation technology, land use and land cover (LULC) image classification plays an essential role. It uses remote sensing techniques to classify specific categories of ground cover as a means of analyzing and understanding the natural attributes of the Earth’s surface and the state of land use. It provides important information for applications in environmental protection, urban planning, and land resource management. However, remote sensing images are usually high-dimensional data and have limited available labeled samples, so performing the LULC classification task faces great challenges. In recent years, due to the emergence of deep learning technology, remote sensing data processing methods based on deep learning have achieved remarkable results, bringing new possibilities for the research and development of LULC classification. In this paper, we present a systematic review of deep-learning-based LULC classification, mainly covering the following five aspects: (1) introduction of the main components of five typical deep learning networks, how they work, and their unique benefits; (2) summary of two baseline datasets for LULC classification (pixel-level, patch-level) and performance metrics for evaluating different models (OA, AA, F1, and MIOU); (3) review of deep learning strategies in LULC classification studies, including convolutional neural networks (CNNs), autoencoders (AEs), generative adversarial networks (GANs), and recurrent neural networks (RNNs); (4) challenges faced by LULC classification and processing schemes under limited training samples; (5) outlooks on the future development of deep-learning-based LULC classification.

Single-image super-resolution (SISR) is an important task in image processing, aiming to achieve enhanced image resolution. With the development of deep learning, SISR based on convolutional neural networks has also gained great progress, but as the network deepens and the task of SISR becomes more complex, SISR networks become difficult to train, which hinders SISR from achieving greater success. Therefore, to further promote SISR, many challenges have emerged in recent years. In this review, we briefly review the SISR challenges organized from 2017 to 2022 and focus on the in-depth classification of these challenges, the datasets employed, the evaluation methods used, and the powerful network architectures proposed or accepted by the winners. First, depending on the tasks of the challenges, the SISR challenges can be broadly classified into four categories: classic SISR, efficient SISR, perceptual extreme SISR, and real-world SISR. Second, we introduce the datasets commonly used in the challenges in recent years and describe their characteristics. Third, we present the image evaluation methods commonly used in SISR challenges in recent years. Fourth, we introduce the network architectures used by the winners, mainly to explore in depth where the advantages of their network architectures lie and to compare the results of previous years’ winners. Finally, we summarize the methods that have been widely used in SISR in recent years and suggest several possible promising directions for future SISR.

This article introduces the open source program office best practices of a Chinese tech giant, Ant Group. We summarize roles and challenges and discuss the tool sets adapted by Ant Group.