Spoken language from older adults often deviates from written norms due to omission, disordered syntax, constituent errors, and redundancy, limiting the usefulness of automatic transcripts in downstream tasks.We present COAS2W, a Chinese spoken-to-written corpus of 10,004 utterances from older adults, each paired with a written version, finegrained error labels, and four-sentence context.Fine-tuned lightweight open-source models on COAS2W outperform larger closed-source models.Context ablation shows the value of multi-sentence input, and normalization improves performance on downstream translation tasks.COAS2W supports the development of inclusive, context-aware language technologies for older speakers.Our annotation convention, data, and code are publicly available at https://github.com/Springrx/COAS2W.

Mobile technology is being increasingly adopted in teleconsultation for its convenience and mobility. Although widely accepted by physicians for informal online consultations, the effectiveness of mobile platforms in formal medical interventions, such as follow-up treatments, remains largely underexplored. This research presents a case study from a Chinese hospital, examining how physicians use mobile platforms to treat chronic patients, the challenges they encounter, and their overall experience. The study aims to determine whether mobile technology can enable physicians to fulfill their responsibilities in managing chronic disease follow-ups online. Through observations and interviews, we found that using mobile platforms introduces significant challenges. Physicians operate in complex and varying environments, such as workplaces, homes, and even public areas, making them struggle to access comprehensive information, communicate effectively, and maintain detailed medical records. As a result, physicians face poor working conditions, reduced efficiency, and struggle to make accurate treatment decisions. This study highlights the need for policy reforms and technological innovations to ensure sustainable teleconsultation practices on mobile platforms. It contributes to the HCI and CSCW communities by highlighting the feasibility of using mobile platforms in online chronic disease follow-ups.

This study examines how Chinese older adults leverage Douyin, a short video platform, for informal learning purposes, analyzing their usage patterns, motivations, and encountered challenges. Although Douyin was not explicitly designed with educational features, it has emerged as a significant informal learning platform for this demographic. Through a qualitative investigation comprising participant observations and semi-structured interviews with 17 participants, we reveal the distinctive learning experience that Douyin facilitates. The platform's unique combination of short-form videos, live streaming capabilities, and interactive community features creates an engaging learning environment that particularly resonates with older adults. Our findings demonstrate that participants derive substantial social-emotional benefits beyond knowledge acquisition, including strengthened social connections, enhanced companionship, and a reinforced sense of purpose through their Douyin engagement. These social-emotional aspects emerge as crucial factors driving older adults' selection of Douyin as their preferred learning platform. By providing comprehensive insights into older adults' engagement with digital platforms for lifelong learning, this research offers valuable implications for HCI, particularly in understanding how technology can be optimized to support the learning needs of older populations.

Older adults are often underserved and marginalized in technology engagement due to their reluctance and the barriers they face in adopting and engaging with mainstream technology. However, Pinxiaoquan, a social feature of an e-commerce platform in China, has gained a large number of older users. This work investigates how and why Chinese older adults use Pinxiaoquan, aiming to unveil the underlying logic and inspire technology-inclusive design for older adults. To this end, we conducted a mixed-methods qualitative study over two years, which included online observation, and semi-interview. We found that Pinxiaoquan's success among Chinese older adults is mainly due to its ability to inspire technological autonomy and provide social-emotional support. Rather than simply lowering technical barriers or asking them to seek assistance outside the platform, Pinxiaoquan builds a semi-acquaintance online community based on location and social ties that allows older adults to realize technical support mutually. Pinxiaoquan also fulfills their social-emotional needs, such as free online expression, memory creation and preservation, relationship expansion and maintenance, and a sense of value. Our research contributes to the HCI community by highlighting the importance of improving older adults' technology autonomy following their specific social and cultural background and social-emotional needs. This work also provides unique insights and implications for building inclusive technology for the growing aging population.

In hyperspectral image (HSI) classification, the challenge of the small-sample-size problem persists as a significant obstacle due to the high cost of labeling samples. To effectively train models with a limited sample set, the application of a transfer learning approach called cross-scene HSI classification is considered a viable solution to address this problem. In cross-scene HSI classification, a source scene with sufficient labeled samples is leveraged to assist in classifying a target scene that lacks labeled samples. Considering that real HSIs may be captured by different sensors, we propose a novel heterogeneous transfer learning algorithm called dual-stream discriminative attention network (DSDAN) to address the task of cross-scene HSI classification. The DSDAN predominantly comprises three pivotal modules. 1) A dual-stream lightweight hybrid CNN (DSLHC) incorporates both the source stream and the target stream is applied to extract alignment spatial-spectral features from heterogeneous data. 2) A discriminative attention block (DAB) is created to address the domain shift between two scenes. Following the DSLHC, the DAB assigns discriminative attention weights to the source features, facilitating a closer alignment of features from two scenes. 3) A specially designed cross-domain loss (CDL) is designed to drive intra-class samples from two scenes to become more consistent, while inter-class samples from two scenes become more distinct, thereby further mitigating domain shift. By combining DSLHC, DAB, and CDL, the complete DSDAN model is established. The effectiveness of DSDAN is validated using three real cross-scene HSI datasets.

Temporal Knowledge Graph Question Answering (TKGQA) task aims to find an entity or timestamp from a temporal knowledge graph to answer temporal reasoning questions. However, most existing models fail to capture the implicit temporal information in the questions, resulting in weak performance when handling complex temporal reasoning tasks. To address this issue, this paper proposes a novel TKGQA model called GATQR, which integrates graph attention mechanism. The model utilizes a pre-trained temporal knowledge base in the form of quadruples and introduces Graph Attention Network (GAT) to effectively capture the implicit temporal information in the questions. By integrating with relation representations trained by the RoBERTa, it further enhances the temporal relationship representation in the queries. Finally, this representation is combined with the pre-trained TKG embeddings to predict the entity or timestamp with the highest score as the answer. Experimental results on the largest benchmark dataset CronQuestion demonstrate that compared to baseline models such as CronKGQA, EntityQR, and TempoQR-Soft, the GATQR achieves significant improvements in Hits@l results for handling complex and temporal question types, with increases of 35% and 13%, 18% and 9%, and 9% and 3%, respectively. These results validate the effectiveness and superiority of the GATQR model in capturing implicit temporal information and enhancing complex reasoning capabilities.

Vision Language Pre-training (VLP) has made significant progress in the field of universal multimodality in recent years. Universal multimodal datasets (such as MSCOCO, Flickr30k, etc.) have become one of the standards for evaluating VLP models which rely on images and corresponding captions for representation modeling. However, in a public opinion event, besides image captions, it also includes other texts such as content texts and comments, which may have a positive impact on image-text representations of public opinion. In this paper, we propose the method to explore the positive effect of content texts on initial multimodal representations. We name our model CLIP-PubOp, which is based on CLIP, a famous VLP model using contrastive learning. We add a linear fusion layer before the fusion of image and text representations, which fuses event content text representations and caption representations in a certain proportion to obtain enhanced text representations. On this basis, multimodal representations can be obtained by fusing enhanced text representations with image representations. We crawl through four mainstream categories of public opinion events online as our datasets and conduct experiments on both Chinese and English version of datasets. The experimental results show that content texts of public opinion events have a significant positive effect on multimodal representations, with an average accuracy improvement of about 2%-10% in image-text retrieval tasks.

In developing countries suffering from a severe shortage of physicians, the follow-up clinical consultation of long-term chronic care becomes a high-speed collaborative work, which has to be conducted in a few minutes. Although much existing work studies how time factors affect physicians' workflows and requirements for information systems, high-speed chronic care is yet to be well investigated. This work bridges the gap by presenting a case of a pediatric hospital in China. We focus on the processes of follow-up consultations, the factors enabling physicians to complete consultation in several minutes, as well as the challenges faced by physicians and patients. Through observations and interviews, we find that physicians conduct multiple tasks (information acquisition, patient-provider communication, and medical data documentation) simultaneously to reduce the consultation duration. Adopting an information summary alternative is the key to fast information acquisition. Templates and references in EMR contribute to rapid documentation and prescription. However, multitasking brings physicians a heavy cognitive load. It also severely compresses the duration of patient-provider communication. As a result, some of the patients' needs, especially emotional ones, are neglected. Based on these findings, we discuss the characteristics and requirements of high-speed chronic care and accordingly propose design suggestions.

The electronic medical record (EMR) systems face many challenges in supporting chronic disease treatment, especially in medical information summary. Many solutions have recently been proposed for hospitals in developed countries. However, these solutions maybe not suitable for hospitals in developing countries because their workflow and patterns may be quite different due to their resource limitations, especially in shortage of physicians. Investigating the information summary alternatives in treating chronic diseases in such hospitals can shed light on EMR system design, especially on that for developing countries. We study one of the best pediatric hospitals in China. It suffers from a severe shortage of physicians. We introduce its information summary alternative, \fs. In particular, we study how and why pediatricians treat chronic diseases with the sheet. Our work unveils the intense work patterns and their corresponding information requirements of hospitals in China. We also demonstrate the characteristics of the \fs\ and accordingly discuss how EMR systems can be optimized.

Summary Most Android applications include third‐party libraries (3PLs) to make revenues, to facilitate their development, and to track user behaviors. 3PLs generally require specific permissions to realize their functionalities. Current Android systems manage permissions in app (process) granularity. As a result, the permission sets of apps with 3PLs (3PL‐apps) may be augmented, introducing overprivilege risks. In this paper, we firstly study how severe the problem is by analyzing the permission sets of 27 718 real‐world Android apps with and without 3PLs downloaded in both 2016 and 2017. We find that the usage of 3PLs and the permissions required by 3PL‐apps have increased over time. As a result, the possibility of overprivilege risks increases. We then propose Perman, a fine‐grained permission management mechanism for Android. Perman isolates the permissions of the host app and those of the 3PLs through dynamic code instrumentation. It allows users to manage permission requests of different modules of 3PL‐apps during app runtime. Unlike existing tools, Perman does not need to redesign Android apps and systems. Therefore, it can be applied to millions of existing apps and various Android devices. We conduct experiments to evaluate the effectiveness and efficiency of Perman. The experimental results verify that Perman is capable of managing permission requests of the host app and those of the 3PLs. We also confirm that the overhead introduced by Perman is comparable to that by existing commercial permission management tools.

Third-party libraries (3PLs) are widely introduced into Android apps and they typically request permissions for their own functionalities. Current Android systems manage permissions in process (app) granularity. Hence, the host app and the 3PLs share the same permission set. 3PL-apps may therefore introduce security risks. Separating the permission sets of the 3PLs and those of the host app are critical to alleviate such security risks. In this paper, we provide Perman, a tool that allows users to manage permissions of different modules (i.e., a 3PL or the host app) of an app at runtime. Perman relies on dynamic code instrumentation to intercept permission requests, and accordingly provide a policy-based permission control. Unlike existing tools that generally require to redesign 3PL-apps, it can thus be applied to the existing apps in market. We evaluate Perman on real-world apps. The experiment results verify its effectiveness in fine-grained permission management.