The Segment Anything Model (SAM) has recently demonstrated significant potential in medical image segmentation. Although SAM is primarily trained on 2D images, attempts have been made to apply it to 3D medical image segmentation. However, the pseudo 3D processing used to adapt SAM results in spatial feature loss, limiting its performance. Additionally, most SAM-based methods still rely on manual prompts, which are challenging to implement in real-world scenarios and require extensive external expert knowledge. To address these limitations, we introduce the Decoder Enhanced and Auto Prompt SAM (DEAP-3DSAM) to tackle these limitations. Specifically, we propose a Feature Enhanced Decoder that fuses the original image features with rich and detailed spatial information to enhance spatial features. We also design a Dual Attention Prompter to automatically obtain prompt information through Spatial Attention and Channel Attention. We conduct comprehensive experiments on four public abdominal tumor segmentation datasets. The results indicate that our DEAP-3DSAM achieves state-of-the-art performance in 3D image segmentation, outperforming or matching existing manual prompt methods. Furthermore, both quantitative and qualitative ablation studies confirm the effectiveness of our proposed modules.

Citing comprehensively and appropriately has become a challenging task with the explosive growth of scientific publications. Current citation recommendation systems aim to recommend a list of scientific papers for a given text context or a draft paper. However, none of the existing work focuses on already included citations of full papers, which are imperfect and still have much room for improvement. In the scenario of peer reviewing, it is a common phenomenon that submissions are identified as missing vital citations by reviewers. This may lead to a negative impact on the credibility and validity of the research presented. To help improve citations of full papers, we first define a novel task of Recommending Missed Citations Identified by Reviewers (RMC) and construct a corresponding expert-labeled dataset called CitationR. We conduct an extensive evaluation of several state-of-the-art methods on CitationR. Furthermore, we propose a new framework RMCNet with an Attentive Reference Encoder module mining the relevance between papers, already-made citations, and missed citations. Empirical results prove that RMC is challenging, with the proposed architecture outperforming previous methods in all metrics. We release our dataset and benchmark models to motivate future research on this challenging new task.

Automatically condensing multiple topic-related scientific papers into a succinct and concise summary is referred to as Multi-Document Scientific Summarization (MDSS). Currently, while commonly used abstractive MDSS methods can generate flexible and coherent summaries, the difficulty in handling global information and the lack of guidance during decoding still make it challenging to generate better summaries. To alleviate these two shortcomings, this paper introduces summary candidates into MDSS, utilizing the global information of the document set and additional guidance from the summary candidates to guide the decoding process. Our insights are twofold: Firstly, summary candidates can provide instructive information from both positive and negative perspectives, and secondly, selecting higher-quality candidates from multiple options contributes to producing better summaries. Drawing on the insights, we propose a summary candidates fusion framework - Disentangling Instructive information from Ranked candidates (DIR) for MDSS. Specifically, DIR first uses a specialized pairwise comparison method towards multiple candidates to pick out those of higher quality. Then DIR disentangles the instructive information of summary candidates into positive and negative latent variables with Conditional Variational Autoencoder. These variables are further incorporated into the decoder to guide generation. We evaluate our approach with three different types of Transformer-based models and three different types of candidates, and consistently observe noticeable performance improvements according to automatic and human evaluation. More analyses further demonstrate the effectiveness of our model in handling global information and enhancing decoding controllability.

Knowledge Tracing (KT) is the task of modeling a learner’s knowledge state to predict future performance in e-learning systems based on past performance. Deep learning-based methods, such as recurrent neural networks, memory-augmented neural networks, and attention-based neural networks, have recently been used in KT. Such methods have demonstrated excellent performance in capturing the latent dependencies of a learner’s knowledge state on recent exercises. However, these methods have limitations when it comes to dealing with the so-called Skill Switching Phenomenon (SSP), i.e., when learners respond to exercises in an e-learning system, the latent skills in the exercises typically switch irregularly. SSP will deteriorate the performance of deep learning-based approaches for simulating the learner’s knowledge state during skill switching, particularly when the association between the switching skills and the previously learned skills is weak. To address this problem, we propose the Memory-augmented Attentive Network (MAN), which combines the advantages of memory-augmented neural networks and attention-based neural networks. Specifically, in MAN, memory-augmented neural networks are used to model learners’ longer term memory knowledge, while attention-based neural networks are used to model learners’ recent term knowledge. In addition, we design a context-aware attention mechanism that automatically weighs the tradeoff between these two types of knowledge. With extensive experiments on several e-learning datasets, we show that MAN effectively improve predictive accuracies of existing state-of-the-art DLKT methods.

Multi-Document Scientific Summarization (MDSS) aims to produce coherent and concise summaries for clusters of topic-relevant scientific papers. This task requires precise understanding of paper content and accurate modeling of cross-paper relationships. Knowledge graphs convey compact and interpretable structured information for documents, which makes them ideal for content modeling and relationship modeling. In this paper, we present KGSum, an MDSS model centred on knowledge graphs during both the encoding and decoding process. Specifically, in the encoding process, two graph-based modules are proposed to incorporate knowledge graph information into paper encoding, while in the decoding process, we propose a two-stage decoder by first generating knowledge graph information of summary in the form of descriptive sentences, followed by generating the final summary. Empirical results show that the proposed architecture brings substantial improvements over baselines on the Multi-Xscience dataset.

Citing comprehensively and appropriately has become a challenging task with the rapid growth of academic publications. Citation recommendation helps alleviate the burden of finding relevant and appropriate citations by recommending a list of academic papers for a given text. Existing approaches tried to determine whether a paper should be cited by measuring its relevance or similarity to a given citation circumstance. Citation circumstance modeling should consider many factors, such as the content of the citing paper, citation context words, citation network, and so on. However, most models only focus on citation context words and learn representations of citing paper through citation networks, putting little attention on citing paper content. In this paper, we regard the title as a summative and informative sentence relative to paper content and propose a novel model based on Bidirectional Gated Recurrent Units (BiGRUs) and Attentions. Our approach uses sequential embedding of paper title words for paper semantic representation and models citation circumstances by integrating citing paper title and citation context. Moreover, we introduce a semantic weight parameter to distinguish the importance of academic papers and citation contexts. Experiments on the ACL anthology network dataset show that our approach outperforms other state-of-the-art models in recall, MAP, MRR, and nDCG criteria.

Research on GIS interoperability is very important for spatial data share and integration. GIS specifications play important roles. In This work, OpenGIS WMS (Web Map Service) specification is studied, and Web services technology is introduced for its implementation. Totally different from other implementations, the mapping Web service has advantages of cross-platform interoperability and high capability of integration etc. We also give an example of its integrated application in Spatial Information Search Engine (SISE) system using ASP.NET. Excellent performances are achieved for all the components in this distributed system.

Buffer analysis is an important function in geographical information system (GIS). It is also the base of many other more complicated spatial analyses. So it is important to improve the efficiency of buffer generalization. Generally, buffer generalization can be divided into two steps, primitive buffer boundary generalization and handling self-intersection of buffer boundary. A large number of points make the process of buffer generalization very time-consuming. However, many buffer boundary points are unnecessary to be generated. The larger radius is, the less the points on the original curve contribute to the ultimate buffer boundary. Such points are called noncharacteristic points. So it is a good way to remove these noncharacteristic points from the original curve and keep characteristic points of the curve. Douglas-Peucker algorithm is a good method for removing curve's noncharacteristic points and extracting characteristic points. This paper analyzes the efficiency of each step of buffer generalization and points out which procedures are time-consuming. Then This work uses Douglas-Peucker algorithm to extract curve's characteristic points before buffer generating. The experimental results show that this algorithm is a good way to speed up buffer generalization while keeping the geometric features of the ultimate buffer areas.

Web Map Service (WMS) provides spatial information to Internet users by map images. Commonly, spatial data are stored as vector data. It is a long job to create map images from vector data. To reduce the time cost, we employ Linux cluster. When a map is requested, coordinates scope that is a rectangle defined with xmin, ymin, xmax, ymax must be specified. We design a load balance algorithm to divide the request rectangles into some sub-rectangles. Each sub-rectangle is sent to a WMS node to produce some sub-maps. The resulting map will be reconstructed by these sub-maps. All these sub-maps are produced in parallel, so less time is spent in producing an entire map. How to split request rectangles is the key problem. First, we present a method to calculate the 2D load weights distribution in the map scope. Second, nodes load abilities are evaluated. Then, the authors present a method for splitting the entire rectangles. This paper also discusses the performance of the algorithm.

Traditionally, to provide Web Map Service (WMS), a program named "Map Server" must be run as a standalone process to create map images. Map server receives the requests from the clients, construct SQL statements and send them to spatial database. Spatial database execute the SQL statements and send the results to map server. Map server gets the features, render map images and send them to clients. In this way, map images can't be "select" from spatial database directly. In this work, the authors present extensions embedded in spatial database to enable the database can provide map service without any map servers. First, we implement a "Map Render" which can draw geometry on a canvas. Second, we give "Symbol" data type extension. Different symbols of a geometry may enable the geometry have different map expressions. The spatial database powered by "Map Render" and "Symbol" data type extensions was named "MapBase" by the authors. It is very simple to "select" a map image from "MapBase" directly by SQL statements. Finally, we give an example to explain how to use "MapBase".

In this paper, a B/S structured WebGIS-based information system of Yang Zhou city is designed and developed by integrating various data sources including aerial photos, video clips, digital pictures etc. Special focus is cast on hierarchical data structure, image pyramid, image compression and online dissemination technology in order to efficiently process and distribute the over all 700M high resolution aerial photos of the city area. The system can automatically display the exact area with the most appropriate resolution as a response to the user's operation at browser end. Also the integrated raster-and-vector Web publishing technology is utilized thus to simultaneously display necessary map legends and text notes at the according location on the aerial photo cover. The experimental results show that the system can satisfyingly meet the need of real-time map display and smooth roam of large data volume with the most proper resolution under present computer hardware configuration, network bandwidth and transfer speed thus to set a good example of WebGIS-based mass data online service