Xingran Zhou, Kun Yang, Changtao Miao, Bingyu Hu, Zhuoer Xu, Shiwen Cui, Changhua Meng, Dan Hong. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Abstract Digital image noise may be introduced during acquisition, transmission, or processing and affects readability and image processing effectiveness. The accuracy of established image processing techniques, such as segmentation, recognition, and edge detection, is adversely impacted by noise. There exists an extensive body of work which focuses on circumventing such issues through digital image enhancement and noise reduction, but this work is limited by a number of constraints including the application of non-adaptive parameters, potential loss of edge detail information, and (with supervised approaches) a requirement for clean, labeled, training data. This paper, developed on the principle of Noise2Void, presents a new unsupervised learning approach incorporating a pseudo-siamese network. Our method enables image denoising without the need for clean images or paired noise images, instead requiring only noise images. Two independent branches of the network utilize different filling strategies, namely zero filling and adjacent pixel filling. Then, the network employs a loss function to improve the similarity of the results in the two branches. We also modify the Efficient Channel Attention module to extract more diverse features and improve performance on the basis of global average pooling. Experimental results show that compared with traditional methods, the pseudo-siamese network has a greater improvement on the ADNI dataset in terms of quantitative and qualitative evaluation. Our method therefore has practical utility in cases where clean images are difficult to obtain.

Smart healthcare has undergone new opportunities and challenges with the arrival of the Industry 4.0 era. The intelligent imaging diagnosis system is a staple part of smart healthcare, helping doctors make clinical decisions. Nevertheless, intelligent diagnosis analysis is still confronted with the issue that it is challenging to extract effective features from the limited and high‐dimensional data, particularly in resting‐state data of amnesic mild cognitive impairment (aMCI). Furthermore, the intelligent imaging diagnosis system for aMCI is conductive to make timely predicting groups that may convert to Alzheimer’s disease (AD). To improve the system’s detection performance and reduce its data redundancy, we first develop an adaptive structure feature generation strategy (ASFGS) based on the Laplacian matrix and sparse autoencoder to obtain the structural features of brain functional network (BFN). Concurrently, we present a multiscale local feature detection strategy (MLFDS) to overcome the low utilization of local features of BFN. And finally, multiscale features, including structural features and multiscale local features, are fused by concatenation method to further improve the detection performance of aMCI system. Support vector machine based on radial basis function (RBF‐SVM) for small data learning is adopted to evaluate the effectiveness of the proposed features. Besides, we employ leave‐one‐out cross‐validation strategy to avoid the overfitting problem of classifier training process. The experiment results elucidate that the accuracy (ACC) and the area under the curve (AUC) in this work provide 86.57% and 86.36%, respectively, which outperforms the traditional methods and offers new insights for accuracy requirements of the aMCI system.

Many prediction tasks of real-world applications need to model multi-order feature interactions in user's event sequence for better detection performance. However, existing popular solutions usually suffer two key issues: 1) only focusing on feature interactions and failing to capture the sequence influence; 2) only focusing on sequence information, but ignoring internal feature relations of each event, thus failing to extract a better event representation. In this paper, we consider a two-level structure for capturing the hierarchical information over user's event sequence: 1) learning effective feature interactions based event representation; 2) modeling the sequence representation of user's historical events. Experimental results on both industrial and public datasets clearly demonstrate that our model achieves significantly better performance compared with state-of-the-art baselines.

With the rapid growth of the Internet, more and more people interact with their friends in online social networks like Facebook. Current online social networks have designed some strategies to protect users' privacy, but they are not stringent enough. Some public information of profile or relationship can be utilized to infer users' private information. Online social networks usually contain little public available information of users (labeled data) but with a large number of hidden ones (unlabeled data). Recently, Semi-Supervised Learning (SSL), which has the advantage of utilizing fewer labeled data to achieve better performance compared to classical Supervised Learning, attracts much attention from the web research community with a massive set of unlabeled data. In our paper, we focus on the privacy issue of online social networks, which is a hot and dynamic research topic. More specifically, we propose a novel SSL framework that can be used to exploit security issues in online social networks. We first introduce the general SSL framework and outline two exploit models with associated strategies within it, e.g., graph-based models and co-training model. Finally, we conduct a series of experiments on real-world data from Facebook and StudiVZ to evaluate the effectiveness of this SSL exploit framework. Experimental results demonstrate that our approaches can accurately infer sensitive information of online users and more effective compared to previous models.

We propose a new Web page transformation method to facilitate Web browsing on handheld devices such as Personal Digital Assistants (PDAs). In our approach, an original Web page that does not fit on the screen is transformed into a set of subpages, each of which fits on the screen. This transformation is done through slicing the original page into page blocks iteratively, with several factors considered. These factors include the size of the screen, the size of each page block, the number of blocks in each transformed page, the depth of the tree hierarchy that the transformed pages form, as well as the semantic coherence between blocks. We call the tree hierarchy of the transformed pages an SP-tree. In an SP-tree, an internal node consists of a textually enhanced thumbnail image with hyperlinks, and a leaf node is a block extracted from a subpage of the original Web page. We adaptively adjust the fanout and the height of the SP-tree so that each thumbnail image is clear enough for users to read, while at the same time, the number of clicks needed to reach a leaf page is few. Through this transformation algorithm, we preserve the contextual information in the original Web page and reduce scrolling. We have implemented this transformation module on a proxy server and have conducted usability studies on its performance. Our system achieved a shorter task completion time compared with that of transformations from the Opera browser in nine of ten tasks. The average improvement on familiar pages was 44%. The average improvement on unfamiliar pages was 37%. Subjective responses were positive.

Recent advances in mobile technologies and infrastructures have led to increasing demands for ubiquitous access to enterprise services from mobile handheld devices, such as mobile phones and PDAs. The context in which such a service is used becomes an integral part of the associated enterprise application. This demands a new paradigm for system requirements elicitation and design in order to make good use of such extended context information. Instead of redesigning or adapting existing enterprise services in an ad-hoc manner, we introduce a methodology for the elicitation of context-aware adaptation requirements and the matching of context-awareness features to the target context by capability matching. For the implementation of these adaptations, we propose the use of three tiers of views: user interface views, data views, and process views. This approach centers on a novel notion of process views to service adaptation according to their context. We demonstrate our methodology by extending an enterprise appointment service into a ubiquitous one with context support

With the invention of new interaction devices and the requirements for ubiquitous access to application systems, user's interactions have moved beyond the desktop and evolved into a trend of ongoing development. The context in which the application is being used becomes an integral part of the activity carried out with the system. The inclusion of context-awareness provides convenience and efficiency to users for their ubiquitous access. Traditional human-computer interface (HCI) theories are now inadequate for developing these context-aware applications, as we believe that the notion of context should be extended to different categories: computing contexts, user contexts, and physical contexts for ubiquitous computing. This demands a new paradigm for system requirements elicitation and design in order to make good use of such extended context information. In this paper, we introduce a methodology for the elicitation of context-aware requirements and the matching of context-awareness features to the target context by capability matching. Based on this model, we analyze the design issues of some common ubiquitous access situations and show how to fit them systematically into a context-aware application by considering the requirements of a ubiquitous tourist application. Copyright 2005 ACM.

We propose a new Web page transformation method for browsing on mobile devices with small displays. In our approach, an original web page that does not fit into the screen is transformed into a set of pages, each of which fits into the screen. This transformation is done through slicing the original page. The resulting set of transformed pages form a multi-level tree structure, called a slicing*-tree, in which an internal node consists of a thumbnail image with hyperlinks and a leaf node is a block from the original web page. Our slicing*-tree based Web page transformation eases Web browsing on small displays by providing screen-fitting visual context and reducing page scrolling effort.

Context-aware applications can better meet users' needs when sensing agents installed in the environment automatically provide input relevant to the application. However, this non-intrusive context usage may cause privacy concerns since sensitive user data could be leaked to unauthorized parties. Therefore, data privacy protection becomes one of the major issues for context-aware applications. In this paper, in order to provide services based on various levels of privacy concerns, we extend the Platform for Privacy Preferences of W3C and define a specification for representing user privacy preferences for context-aware applications. We also propose a privacy infrastructure, which could be installed as a plug-in service for middleware supporting context-aware applications. This infrastructure enables the middleware to automatically generate a privacy policy and the user preference file according to the current context. The middleware simply matches these two files to decide whether to proceed with the application. We demonstrate the efficacy of this approach through a prototype implementation.