Point-based networks achieve high accuracy by preserving the intrinsic spatial structure of point clouds. The spatial information is effectively extracted by set abstraction, a critical module for feature learning in point-based networks. However, set abstraction introduces a computational bottleneck, and naive parallelization often degrades sampling quality, leading to accuracy loss. To address these challenges, we propose Parallel-SA, a framework that accelerates point-based networks by transforming set abstraction from sequential to parallel processing without sacrificing accuracy. Parallel-SA leverages a multi-scale sampling distribution approximation to preserve sampling quality under parallel execution. In addition, it employs distribution-aware balanced partitioning and adaptive load-balancing refinement to further improve efficiency. Experiments show that Parallel-SA achieves an average 2.38× speedup in set abstraction with minimal accuracy degradation.

As a fundamental perception task, 3D point cloud detection has become essential for applications in autonomous driving and robotics. However, point cloud detection faces significant challenges of high computational cost due to complex point processing operations. To address this issue, we propose DAWN, an acceleration framework for point cloud object detection that identifies partial similarities between adjacent frames and reduces computational cost by filtering redundant points. DAWN uses object-aware partitioning that defines boundaries based on previous detection results for localized similarity analysis. Additionally, it applies axis-sorted point selection to refine partitioning for point clouds with non-uniform distribution. An efficient 3D similarity algorithm then filters redundant points to reduce computational load. DAWN enables flexible latencyaccuracy trade-offs by tuning point filtering ratios. Experimental results show that DAWN achieves a $1.59 \times$ average speedup and up to $1.70 \times$ on state-of-the-art detection networks by filtering more than $50 \%$ of points on average, with negligible impact on accuracy.

Log-Structured-Merge-tree (LSM-tree) has been extensively adopted because of its exceptional write efficiency and high space utilization. Compaction is invoked periodically in LSM-tree based key-value(LSM KV) systems to maintain good system performance. As the size of LSM-KV grows, large-scale compaction is now frequently seen. Compaction throughput significantly degrades with larger inputs, leading to frequent write stalls and decrement in overall write throughput. This paper proposes STEM, a stream-based compaction framework with FPGA to address this issue. A clean-cut algorithm is introduced to enable streaming-based compaction for large-scale data. With a multi-unit pipeline and dynamic pipeline schedule, STEM can handle large-scale compaction tasks efficiently. Based on the experiment result, the compaction throughput of STEM can achieve$27\times$on average and up to$35\times$improvement compared with the current RocksDB compaction,$2.09\times$to$2.27\times$improvement compared with the state-of-the-art FPGA accelerator.

This paper presents a brand-new Thanka picture inpainting technique based on Euler’s elastica, iterative denoising, and backward projections (EEIDBP). Specifically, a model of Euler’s elastica is introduced to estimate the original observation due to its lower staircasing effects and better approximation of natural images. A method for backward projection and iterative denoising is applied to achieve a more accurate estimate of the original signal by alternating iterations between the estimation of the original signal and the estimation of the original observation. The experimental findings demonstrate that, in terms of a subjective assessment, the quantitative peak signal-to-noise ratio (PSNR), and the structural similarity (SSIM), the proposed technique outperforms the state-of-the-art picture inpainting methods.

Early diagnosis and prediction of chronic kidney disease (CKD) progress within a given duration are critical to ensure personalized treatment, which could improve patients' quality of life and prolong survival time. In this study, we explore the intelligibility of machine-learning and deep-learning models on end-stage renal disease (ESRD) prediction, based on readily-accessible clinical and laboratory features of patients suffering from CKD. Eight machine learning models were used to predict whether a patient suffering from CKD would progress to ESRD within three years based on demographics, clinical,and comorbidity information. LASSO, random forest, and XGBoost were used to identify the most significant markers. In addition, we introduced four advanced attribution methods to the deep learning model to enhance model intelligibility. The deep learning model achieved an AUC-ROC of 0.8991, which was significantly higher than that of baseline models. The interpretation generated by deep learning with attribution methods, random forest, and XGBoost was consistent with clinical knowledge, whereas LASSO-based interpretation was inconsistent. Hematuria, proteinuria, potassium, urine albumin to creatinine ratio were positively associated with the progression of CKD, while eGFR and urine creatinine were negatively associated. In conclusion, deep learning with attribution algorithms could identify intelligible features of CKD progression. Our model identified a number of critical, but under-reported features, which may be novel markers for CKD progression. This study provides physicians with solid data-driven evidence for using machine learning for CKD clinical management and treatment.

Scene text detection is an important research branch of artificial intelligence technology whose goal is to locate text in scene images. In the Tibetan areas of China, scene images containing both Tibetan and Chinese texts are ubiquitous. Thus, detecting bilingual Tibetan-Chinese scene texts is important in promoting intelligent applications for minority languages. In this study, a scene text detection database for bilingual Tibetan-Chinese is constructed using a manually labeled method and an automatic synthesis method, and a text detection method is proposed. First, we predict a text rectangular region and the text center region for each text instance and simultaneously learned the expansion distance of the text center region. Second, based on the classification score of the text center region and the text rectangular region, we obtain the final confidence of each text instance and then filter out the text center region with lower confidence. Third, through the learned expansion distance, the full-text instance from the remaining text center region is recovered. The results show that our method obtains good detection performance; it achieves an accuracy of up to 75.47% during the text detection phase, laying the foundation for scene text recognition in the subsequent step.

The text lines of ancient Tibetan books are skewed and distorted, strokes are broken, and complex adjacent text lines touch each other, which makes text line segmentation extremely challenging. In this paper, a text line segmentation method based on local baselines and connected component allocation is proposed. First, the pseudotext line is detected by analyzing the horizontal projection, straight line detection and the average character height information, and then the local baseline position is determined in the pseudotext line area by the projection method. Second, the adhesion area detection is performed, which mainly includes the adhesion between characters and the adhesion between characters and strokes. The position relationship between the connected components is used to complete the adhesion between characters. A convolutional neural network is used to complete the adhesion between characters and strokes. Then, the watershed algorithm is used to segment touching connected components. Finally, the broken strokes are assigned to the text lines in which they belong according to the characteristics of Tibetan character structures. Subsequently, the assigned strokes are postprocessed to complete stroke correction, and finally the line segmentation is completed. Experiments show that this method can effectively reduce the influence of text line distortion and skew on text line segmentation, has a high degree of robustness, and has good segmentation accuracy for image text lines in Tibetan documents with touching and broken strokes.

Thanka murals are important cultural heritages of Tibet, but many precious murals were damaged during history. Thanka mural restoration is very important for the protection of Tibetan cultural heritage. Partial convolution has great potential for Thanka mural restoration due to its outstanding performance for inpainting irregular holes. However, three challenges prevent the existing partial convolution-based methods from solving Thanka restoration problems: 1) the features of multi-scale objects in Thanka murals cannot be extracted correctly because of single-scale partial convolution; 2) the stroke-like Thanka inpainting mode cannot be effectively simulated and learned by existing rectangular or arbitrary masks; and 3) the original content of damaged Thanka murals cannot be restored. To resolve these problems, we propose a Thanka mural inpainting method based on multi-scale adaptive partial convolution and stroke-like masks. The proposed method consists of three parts: 1) a kernel-level multi-scale adaptive partial convolution (MAPConv) to accurately discriminate valid pixels from invalid pixels, and to extract the features of multi-scale objects; 2) a parameter-configurable stroke-like mask generation method to simulate and learn the stroke-like Thanka inpainting mode; and 3) a 2-phase learning framework based on MAPConv Unet and different loss functions to restore the original content of Thanka murals. Experiments on both simulated and real damages of Thanka murals demonstrated that our approach works well on a small dataset (N=2780), generates realistic mural content, and restores the damaged Thanka murals with high speed (600 ms for multiple holes in 512×512 images). The proposed end-to-end method can be applied to other small datasets-based inpainting tasks.

Functional imaging has successfully been applied to capture functional changes in the pathological tissues of a body in recent years. Nuclear medicine functional imaging has been used to acquire information about areas of concerns (e.g. lesions and organs) in a non‐invasive manner, enabling semi‐automated or automated decision‐making for disease diagnosis, treatment, evaluation, and prediction. Focusing on functional nuclear medicine images, in this study, the authors review existing work on the classification of single‐photon emission computed tomography, positron emission tomography, and their hybrid modalities with computed tomography and magnetic resonance imaging images by using convolutional neural network (CNN) techniques. Specifically, they first present an overview of nuclear imaging and the CNN technique, such as nuclear imaging modalities, nuclear image data format, CNN architecture, and the main CNN classification models. According to the diseases of concern, they then classify the existing CNN‐based work on the classification of functional nuclear images into three different categories. For the typical work in each of these categories, they present details about their research objectives, adopted CNN models, and achieved main results. Finally, they discuss research challenges and directions for developing technological solutions to classify nuclear medicine images based on the CNN technique.

It is common that historical Tibetan documents belonging to historical collections are poorly preserved and are prone to degradation processes. This causes many challenges that can be addressed by image binarization, the most common of which is stains. A lack of uniform standard datasets makes it difficult to evaluate binarization effects. Motivated by the poor effects and difficulty of evaluating the binarization of historical Tibetan document images, a combined approach is proposed that aims to improve overall performance. The method includes the following parts: first, image generation through standard binarization and the background extraction of color images, which are both used for image synthesis in preparing for an evaluation. Then, preliminary binarization processing is implemented through channel combination in the lab color space and through local binarization. The synthetic images are used to select the coefficient when the channels are combined. Furthermore, Local Binary Pattern (hereafter LBP) and image smoothing is carried out after the combination of the channels to obtain the outline of the text area. Finally, the final binarization image is obtained by combining the preliminary binarization image and the text area contour image. Our method achieved top performance compared to other methods after a large number of synthetic image tests with a variety of background types.

The online handwriting recognition of Tibetan characters is still in its infancy. For further research, an online handwriting database of large Tibetan character set was developed, and a recognition research was carried out on this database as a baseline result. The Northwest Minzu University Online Tibetan Handwriting Database (NMU-OLTHWDB) contains 7240 different types of characters, and the sample number in each type is 5000. The total number of samples is [Formula: see text]. The database covers Tibetan Character Collection, Information Technology Tibetan Coded Character set (Extension Set A), and Information Technology Tibetan Coded Character set (Extension Set B). The characters in the database are composed of 170 types of different components. We studied the online handwritten Tibetan recognition software also, and the character feature extraction, classifier training, and the statistics and analysis of the recognition results on the test set were mainly introduced. The character features included the direction attribute coefficients and spatial combination, and the feature matrix was compressed by Linear Discriminate Analysis (LDA). A quick classifier was designed by a modified quadratic discriminate function (QMQDF), and was trained with 4500 sets of samples. In the large character set, the recognition rates of top 1, top 3, top 5, and top 10 were 75.2%, 89.56%, 93.02%, and 95.96%, respectively. Moreover, an online handwriting recognition system for Tibetan large character set was designed with good performance.

As an art image, Thangka images have rich themes, various forms of expression, complex picture content and many layers of color representation. This paper mainly constructs a multi-core support vector machine (SVM) based on the information entropy feature-weighted radial basis kernel function. In this paper, the kernel function is optimized, and the feature reduction is performed by using the random forest feature selection algorithm with average accuracy degradation. Finally, the effective classification of the icon image and the mandala image in Thangka is realized. The research results provide support for the follow-up study of Thangka image annotation and retrieval.

In online handwriting Tibetan transliteration of the Sanskrit character recognition (HTTSCR), many misclassification errors come from the confusion of similar characters. A recognition method based on 2DLDA compound distance was proposed to fully using the discriminative information in the original feature space, to improve the discrimination ability of the existing quadratic classifier on the similar characters. The method uses 2DLDA to extract the features for better discriminability distance measure of similar character pairs is calculated on the subspace and is added to the baseline classifier for reordering two candidate classes, which efficiently reduces the classification errors. Experiments show that this method can effectively improves the recognition accuracy of online HTTSCR, compared to the baseline classifier, the proposed method reduces the errors rates by factors of 21.7%.

In this paper, we proposed a novel method for text line segmentation of Tibetan historical document image with uchen script based on contour tracking. Our method is mainly to segment the text lines from the image documents using the contour curve of the text lines, which consists of three parts: First, we calculate the barycentre coordinates of the connected components for the text regions, and then the barycentre of each text line is connected in order, so that the main part of each text line is connected and a new connected component is formed; then the contour curve of the connected component is obtained using the contour tracing algorithm; Second, the contour curve and the barycentre gravity are used to assign key elements (such as the syllable point, the upper vowel, the lower vowel, and the broken strokes and so on) of the text lines, and next the candidate text lines are obtained based on these connected components; Finally, the contour tracking algorithm is used to calculate the contour curve of the candidate text lines and segment the text lines. We evaluated our text line segmentation method on the 200 document image data sets. Experimental results show that the proposed method based on contour curve tracing can accurately segment the text lines of image documents and achieve the encouraging results.

Thangka is a treasure of Tibetan culture. In its digital protection, most of the current research focuses on the content of Thangka images, not the fabrication process. For silk embroidered Thangka of "Guo Tang", there are two craft methods, namely, weave embroidered and piles embroidered. The local texture of weave embroidered Thangka is rough, and that of piles embroidered Thangka is more smooth. In order to distinguish these two kinds of fabrication processes from images, a effectively segmentation algorithm of color blocks is designed firstly, and the obtained color blocks contain the local texture patterns of Thangka image; Secondly, the local texture features of the color block are extracted and screened; Finally, the selected features are analyzed experimentally. The experimental analysis shows that the proposed features can well reflect the difference between methods of weave embroidered and piles embroidered.