In this article, we introduce PingTactics, a multimodal dataset tailored for table tennis action recognition and tactical analysis. Derived from professional table tennis matches, the dataset comprises annotated video clips capturing detailed player actions, positional dynamics, and scoring outcomes. A key feature of PingTactics is its comprehensive temporal annotation framework, which includes sequences of previous and next actions, enabling the study of fine-grained action relationships and their tactical implications. We ensured annotation quality through a semi-automated pipeline that combines machine-assisted pre-labeling with manual refinement by domain experts. To validate the dataset, we conducted extensive experiments using state-of-the-art deep learning models for action recognition, demonstrating PingTactics’ effectiveness for capturing the complex and dynamic action patterns typical of high-stakes matches. Beyond action recognition, PingTactics serves as a foundation for tactical evaluation, as evidenced by our quadrant-based scoring analysis, which reveals interaction patterns, key scoring strategies, and player tendencies. By offering fine-grained action annotations and enabling tactical insights, PingTactics provides a significant resource for advancing research in sports analytics, with implications for intelligent coaching, player performance evaluation, and strategic planning in table tennis and related domains.

MOTIVATION: Virus mutation is one of the most important research issues which plays a critical role in disease progression and has prompted substantial scientific publications. Mutation extraction from published literature has become an increasingly important task, benefiting many downstream applications such as vaccine design and drug usage. However, most existing approaches have low performances in extracting virus mutation due to both lack of precise virus mutation information and their development based on human gene mutations. RESULTS: We developed ViMRT, a text-mining tool and search engine for automated virus mutation recognition using natural language processing. ViMRT mainly developed 8 optimized rules and 12 regular expressions based on a development dataset comprising 830 papers of 5 human severe disease-related viruses. It achieved higher performance than other tools in a test dataset (1662 papers, 99.17% in F1-score) and has been applied well to two other viruses, influenza virus and severe acute respiratory syndrome coronavirus-2 (212 papers, 96.99% in F1-score). These results indicate that ViMRT is a high-performance method for the extraction of virus mutation from the biomedical literature. Besides, we present a search engine for researchers to quickly find and accurately search virus mutation-related information including virus genes and related diseases. AVAILABILITY AND IMPLEMENTATION: ViMRT software is freely available at http://bmtongji.cn:1225/mutation/index.

In multi-site studies of Alzheimer's disease (AD), the difference of data in multi-site datasets leads to the degraded performance of models in the target sites. The traditional domain adaptation method requires sharing data from both source and target domains, which will lead to data privacy issue. To solve it, federated learning is adopted as it can allow models to be trained with multi-site data in a privacy-protected manner. In this paper, we propose a multi-site federated domain adaptation framework via Transformer (FedDAvT), which not only protects data privacy, but also eliminates data heterogeneity. The Transformer network is used as the backbone network to extract the correlation between the multi-template region of interest features, which can capture the brain abundant information. The self-attention maps in the source and target domains are aligned by applying mean squared error for subdomain adaptation. Finally, we evaluate our method on the multi-site databases based on three AD datasets. The experimental results show that the proposed FedDAvT is quite effective, achieving accuracy rates of 88.75%, 69.51%, and 69.88% on the AD vs. NC, MCI vs. NC, and AD vs. MCI two-way classification tasks, respectively.