Snoring and breath-stopping are key symptoms of sleep apnea. Most existing studies primarily focus on wearable devices or smartphone-based systems. Wearable devices can be uncomfortable, while smartphone-based systems often require specific angles, distances, or positions, making them sensitive to environmental changes. This paper proposes a contactless and engagement-free system for snoring and breath-stopping detection using a seismic sensor. Distinguishing between snoring, breath-stopping, and normal breathing from raw data alone is challenging. Snoring features typically reside in a higher frequency range than breath-stopping and normal breathing, with breath-stopping features appearing in a lower frequency range. Calculating the differential and integral of raw data can enhance features in low and high frequencies, respectively. We introduce AFFCL, an attention feature fusion and contrastive learning framework to leverage information from differential and integral signals. AFFCL generates both shared and exclusive features from the differential and integral signals and employs an attention mechanism for feature fusion. Additionally, cluster-level supervised contrastive learning in AFFCL further enhances system performance. Our system has been performed 5-fold cross-validation on 44 people, which achieves an average accuracy of 93.40% and an F1 score of 92.42%. The accuracy for detecting breath-stopping, snoring, and normal breathing are 89.54%, 94.60%, and 96.06%, respectively. Evaluation results demonstrate that our system effectively identifies breath-stopping and snoring.

Open-source repository platforms have become essential for the development and collaboration of modern deep learning (DL) projects. Efficient and accurate classification of issue reports submitted during the development process is critical for enhancing project quality and development efficiency. However, compared to traditional software projects, issue reports in DL projects exhibit substantial differences in terms of error causes and symptom manifestations, making conventional classification approaches less effective and harder to deal with. To address this challenge, we propose a novel issue classification dialogue framework based on large language models (llMs), which aligns with the full lifecycle of issue handling, i.e., from issue proposal to label assignment in open-source repositories. Specifically, our framework is built upon Qwen2.5 and incorporates a multi-turn dialogue mechanism that leverages comment information from different roles to enhance context understanding through multi-source signals. It not only relies on the semantic reasoning capabilities of LLMs to analyze each step of the conversation but also introduces a built-in selfreflection mechanism to verify and refine classification decisions. We conduct extensive experiments on datasets that comprise $\mathbf{9, 0 7 3}$ issue reports from TensorFlow, PyTorch, and Caffe. The evaluation involves four LLMs and six fine-tuned pre-trained models (PTMs) and the experimental results demonstrate that the proposed dialogue framework based on Qwen2.5 significantly outperforms state-of-the-art fine-tuned PTMs in both coarse- and fine-grained issue classification, particularly in identifying specific issue types. Our findings highlight the effectiveness of LLMbased dialogue frameworks in issue classification and open up new directions for applying LLMs in software engineering tasks, encouraging further exploration into their generalizability and robustness.

Brain lesion segmentation is a critical yet challenging task in the medical analysis applications, primarily due to lesion heterogeneity and low-contrast boundaries. However, existing methods give rise to two main concerns: 1) lacking effective utilization of multi-modality information results in incomplete complementary cues of heterogeneous tumor regions; 2) relying on prompt-based decoder leads to dependency on manual annotation priors. In light of these issues, we focus on investigating a fully automated 3D segmentation model specifically tailored for substantial brain lesions, dubbed as Brain-SAM, which is powered by two appealing designs: (1) Modality-Agnostic Encoder that is capable of automatically transitioning between single-modality and multi-modality input modes. To achieve synergistic integration of structurally divergent modalities, a parameter-efficient Agent Cross Attention mechanism is intro-duced, facilitating the extraction of complementary pathological patterns. (2) Memorable Scale-Aware Decoder that enhances hierarchically focuses on challenging lesions (e.g., small sizes and fuzzy boundaries), discarding the reliance on prompt information. Benefiting from the memory guidance, the prior knowledge is leveraged for contextual learning, which optimally enhances the continuity of three-dimensional features. We evaluate Brain-SAM on four common brain disease segmentation benchmarks across five datasets of substantial brain lesions, including cases of focal cortical dysplasia, glioma, cerebral hemorrhage, and cerebral ischemia, yielding consistent improvements over the state-of-the-art methods on two metrics. Our code is currently open-source on https://anonymous.4open.science/r/Brain-SAM-50F4.

In inverse rendering, accurately modeling visibility and indirect radiance for incident light is essential for capturing secondary effects. Due to the absence of a powerful Gaussian ray tracer, previous 3DGS-based methods have either adopted a simplified rendering equation or used learnable parameters to approximate incident light, resulting in inaccurate material and lighting estimations. To this end, we introduce inter-reflective Gaussian splatting (IRGS) for inverse rendering. To capture inter-reflection, we apply the full rendering equation without simplification and compute incident radiance on the fly using the proposed differentiable 2D Gaussian ray tracing. Additionally, we present an efficient optimization scheme to handle the computational demands of Monte Carlo sampling for rendering equation evaluation. Furthermore, we introduce a novel strategy for querying the indirect radiance of incident light when relighting the optimized scenes. Extensive experiments on multiple standard benchmarks validate the effectiveness of IRGS, demonstrating its capability to accurately model complex inter-reflection effects.

Brain cognitive state recognition based on functional Magnetic Resonance Imaging(fMRI) can capture brain functional activities under different tasks and help understand the neural mechanisms of the brain, which has always been one of the focuses of neuroscience research. Different from the prediction of the brain cognitive domain, the prediction of brain fine-grained cognitive state is based on each moment in the process of executing the task. Therefore, it is necessary to extract more fine-grained effective information. Existing studies focus on modeling and classifying the complete time series, ignoring the brain activity state at each time. So we propose a hierarchical spatiotemporal attention network(FineBrainNet) to recognize fine-grained brain cognitive state. Guided by coarse-grained cognitive domain labels, we trained different sub-modules for fine-grained states under each cognitive domain to capture relevant cognitive state changes more accurately in specific task. Extensive experiments on the HCP-Task dataset show that FineBrainNet can achieve accurate prediction of fine-grained brain cognitive state.

Novel view synthesis has experienced significant advancements owing to increasingly capable NeRF- and 3DGS-based methods. However, reflective object reconstruction remains challenging, lacking a proper solution to achieve real-time, high-quality rendering while accommodating inter-reflection. To fill this gap, we introduce a Reflective Gaussian splatting (Ref-Gaussian) framework characterized with two components: (I) Physically based deferred rendering that empowers the rendering equation with pixel-level material properties via formulating split-sum approximation; (II) Gaussian-grounded inter-reflection that realizes the desired inter-reflection function within a Gaussian splatting paradigm for the first time. To enhance geometry modeling, we further introduce material-aware normal propagation and an initial per-Gaussian shading stage, along with 2D Gaussian primitives. Extensive experiments on standard datasets demonstrate that Ref-Gaussian surpasses existing approaches in terms of quantitative metrics, visual quality, and compute efficiency. Further, we show that our method serves as a unified solution for both reflective and non-reflective scenes, going beyond the previous alternatives focusing on only reflective scenes. Also, we illustrate that Ref-Gaussian supports more applications such as relighting and editing.

Classifying the bug issue types correctly plays a vital role in improving the quality of the deep learning (DL)-oriented projects. Although prior studies have proposed different approaches based on Pre-Trained Models (PTMs) for issue type classification in traditional GitHub repositories, DL-oriented projects are different from traditional software, especially in terms of bugs with different causes and symptoms. More importantly, these PTMs-based approaches trained on the issue reports are labeled when software users submit, which would be wrong and non-subdivided bug issue types. Therefore, an automated approach with the ground-truth bug issue types for labeling issues in DL-oriented projects is necessary for DL software repositories. To fill these gaps, we first manually labeled 9,073 issue reports from 11 DL-oriented projects as the ground truths to establish authentic labels. We then explore the effectiveness of six PTMs on the bug issues identification for the DL software repository. Our findings indicate that i) PTMs (especially BERT) could identify more precise bug issue types of DL software than prior DL approaches in all the datasets. ii) contrary to their performance in traditional software bug classification tasks, Software Engineering (SE) domain-specific PTMs cannot achieve significantly better performance than our compared general PTMs and may even perform worse for the DL bug issue classification. iii) in the cross-framework scenarios, the Fl-score of PTMs declined by 18.5% to 19.8%. Despite that the performance is suffered, BERT can still achieve the best results. Conclusively, we propose that PTM-based bug issue classification offers potential for more widespread applications and prompt future studies to further examine and verify the generalizability of PTM-based methods in software engineering.

Health monitoring is essential for both humans and animals in daily life. While numerous health monitoring systems have been developed, the majority are designed exclusively for either humans or animals, and most require direct physical contact. We have developed BedDot, a contactless health monitoring system for both humans and animals using a seismic sensor. BedDot can be deployed in various environments, such as bed and seat settings for humans, as well as in cages for animals, to monitor occupancy, heart rate (HR), respiratory rate (RR), and blood pressure (BP). Our system demonstrates high accuracy in the clinical experiments of 150 patients and 16 dogs and cats.

Nowadays, vehicles with a high level of automation are being driven everywhere. With the apparent success of autonomous driving technology, we keep working to achieve fully autonomous vehicles on roads. Efficient and accurate vehicle detection is one of the essential tasks in the environment perception of an autonomous vehicle. Therefore, numerous algorithms for vehicle detection have been developed. However, their strengths in terms of performance have not been deeply assessed or highlighted yet. This work comprehensively reviews the existing methods and datasets for vehicle detection considering their performances and applications in the field of autonomous driving. First, we briefly describe tasks, evaluation criteria, and existing public datasets for vehicle detection in autonomous driving. Second, we provide a rigorous review of both classical and latest vehicle detection methods, including machine vision-based, mmWave radar-based, LiDAR-based, and sensor fusion-based methods. Finally, we analyze the pertinent challenges of autonomous vehicles and provide recommendations for future works concerning vehicle detection. The present review covers over 300 research works and aims to help researchers interested in autonomous driving, especially in vehicle detection.

Anti-piracy is fundamentally a procedure that relies on collecting data from the open anonymous population, so how to incentivize credible reporting is a question at the center of the problem. Industrial alliances and companies are running anti-piracy incentive campaigns, but their effectiveness is publicly questioned due to the lack of transparency. We believe that full transparency of a campaign is necessary to truly incentivize people. It means that every role, e.g., content owner, licensee of the content, or every person in the open population, can understand the mechanism and be assured about its execution without trusting any single role. We see this as a distributed system problem. In this paper, we present Argus, a fully transparent incentive system for anti-piracy campaigns. The groundwork of Argus is to formulate the objectives for fully transparent incentive mechanisms, which securely and comprehensively consolidate the different interests of all roles. These objectives form the core of the Argus design, highlighted by our innovations about a Sybil-proof incentive function, a commit-and-reveal scheme, and an oblivious transfer scheme. In the implementation, we overcome a set of unavoidable obstacles to ensure security despite full transparency. Moreover, we effectively optimize several cryptographic operations so that the cost for a piracy reporting is reduced to an equivalent cost of sending about 14 ETH-transfer transactions to run on the public Ethereum network, which would otherwise correspond to thousands of transactions. With the security and practicality of Argus, we hope real-world anti-piracy campaigns will be truly effective by shifting to a fully transparent incentive mechanism.

Object localization and local feature representation are key issues in fine-grained image retrieval. However, the existing unsupervised methods still need to be improved in these two aspects. For conquering these issues in a unified framework, a novel unsupervised scheme, named DSAW for short, is presented in this paper. Firstly, we proposed a dual-selection (DS) method, which achieves more accurate object localization by using an adaptive threshold method to perform feature selection on local and global activation map. Secondly, a novel and faster self-attention weights (AW) method is developed to weight local features by measuring their importance in the global context. Finally, we also evaluated the performance of the proposed method on five fine-grained image datasets and the results showed that our DSAW outperformed the existing best method.