Rejoining fragment images of precious artifacts is a meaningful task because complete artifacts could provide valuable clues for the research of human civilization. However, existing rejoining methods face several challenges including time-consuming manual annotation, insufficient rejoining accuracy, and prohibitive computation cost. For rejoining fragment images of bone sticks (a precious artifact), we propose a lightweight vision graph neural network called RejoinViG to address these challenges. First, our method avoids time-consuming manual annotation of ballast contour data by experts. Specifically, our method directly takes a pair of fragment images as input and then determines whether the image pair is rejoinable. Second, our method improves rejoining accuracy by contour, script, and texture through dynamically constructing local and global graphs. Third, our method improves rejoining accuracy while reducing computation cost by introducing a new attention mechanism named node self-attention. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods significantly. For example, the Top-1 accuracy of our method is 3.9 times that of SFF-Siam. Surprisingly, our method successfully rejoins a pair of previously unknown but rejoinable fragment images of bone sticks in a real-world scenario.

Skin diseases are one of the most common diseases worldwide, and the mismatch between skin disease patients and dermatologists leads to a huge waste of healthcare resources. Accurately matching skin disease patients to appropriate dermatologists by an image-based method of skin disease recognition can reduce the waste of healthcare resources. However, existing image-based methods of skin disease recognition do not fully utilize multi-source and multi-scale features, which leaves us the chance to improve skin disease recognition further. In this paper, we propose a fusion method of multi-source image features and multi-scale image features to improve skin disease recognition. First, we design a fusion module of multi-source image features to integrate multi-source image information. By dual Convolutional Block Attention Module (CBAM) blocks, the fusion module of multi-source image features enhances the feature representation of key regions and then obtains a comprehensive representation of skin diseases. Second, we propose a fusion module of multi-scale image features. By two parallel backbone networks, the fusion module of multi-scale image features can extract deep feature representations from different scales and exploit their complementarity. To validate the effectiveness of our method, we conduct extensive experiments. The experiment results demonstrate that our method outperforms the state-of-the-art method, achieving improvements of 6.30%, 12.52%, 10.85%, 12.16%, and 5.06% in accuracy, precision, recall, F1-score, and AUC, respectively.

Recent advances in LVLMs have improved vision-language understanding, but they still struggle with spatial perception, limiting their ability to reason about complex 3D scenes. Unlike previous approaches that incorporate 3D representations into models to improve spatial understanding, we aim to unlock the potential of VLMs by leveraging spatially relevant image data. To this end, we introduce a novel 2D spatial data generation and annotation pipeline built upon scene data with 3D ground-truth. This pipeline enables the creation of a diverse set of spatial tasks, ranging from basic perception tasks to more complex reasoning tasks. Leveraging this pipeline, we construct SPAR-7M, a large-scale dataset generated from thousands of scenes across multiple public datasets. In addition, we introduce SPAR-Bench, a benchmark designed to offer a more comprehensive evaluation of spatial capabilities compared to existing spatial benchmarks, supporting both single-view and multi-view inputs. Training on both SPAR-7M and large-scale 2D datasets enables our models to achieve state-of-the-art performance on 2D spatial benchmarks. Further fine-tuning on 3D task-specific datasets yields competitive results, underscoring the effectiveness of our dataset in enhancing spatial reasoning.

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with multi-talker speech due to the unidentifiability of embedding vectors. In this paper, we propose Neural Scoring, a refreshed end-to-end framework that directly estimates verification posterior probabilities without relying on test-side embeddings, making it more robust to complex conditions, e.g., with multiple talkers. To make the training of such an end-to-end model more efficient, we introduce a large-scale trial e2e training strategy, where each test utterance pairs with a set of enrolled speakers, thus enabling processing of large-scale verification trials per batch. Experiments on VoxCeleb dataset demonstrate that Neural Scoring consistently outperforms both the baseline and competitive methods across various conditions, achieving an overall 70.36% reduction in Equal Error Rate compared to the baseline.

Multi-genre speaker recognition is becoming increasingly popular due to its ability to better represent the complexities of real-world applications. However, a major challenge is the significant shift in the distribution of speaker vectors across different genres. While distribution alignment is a common approach to address this challenge, previous studies have mainly focused on aligning a source domain with a target domain, and the performance of multi-genre data is unknown.This paper presents a comprehensive study of mainstream distribution alignment methods on multi-genre data, where multiple distributions need to be aligned. We analyze various methods both qualitatively and quantitatively. Our experiments on the CN-Celeb dataset show that within-between distribution alignment (WBDA) performs relatively better. However, we also found that none of the investigated methods consistently improved performance in all test cases. This suggests that solely aligning the distributions of speaker vectors may not fully address the challenges posed by multi-genre speaker recognition. Further investigation is necessary to develop a more comprehensive solution.

A fast and accurate frequency sweep method combining the mixed finite element method (MFEM) with the second-order Arnoldi algorithm is proposed to characterize the EM material properties for high-loss geoelectromagnetic problems. The MFEM exploits the tree–cotree splitting technique for spatial discretization to eliminate the spurious modes arising from the null space of the curl operator. The modal order reduction method based on the second-order Arnoldi algorithm is employed to generate a set of orthogonal basis of the projection subspace for the quadratic eigenvalue problem (QEP) with both the conduction current and displacement current considered. The efficiency and accuracy of the method are verified by comparing with commercial software HFSS for lossy dielectric characterization in subsurface.

To enhance deep learning-based automated interictal epileptiform discharge (IED) detection, this study proposes a multimodal method, vEpiNet, that leverages video and electroencephalogram (EEG) data. Datasets comprise 24 931 IED (from 484 patients) and 166 094 non-IED 4-second video-EEG segments. The video data is processed by the proposed patient detection method, with frame difference and Simple Keypoints (SKPS) capturing patients' movements. EEG data is processed with EfficientNetV2. The video and EEG features are fused via a multilayer perceptron. We developed a comparative model, termed nEpiNet, to test the effectiveness of the video feature in vEpiNet. The 10-fold cross-validation was used for testing. The 10-fold cross-validation showed high areas under the receiver operating characteristic curve (AUROC) in both models, with a slightly superior AUROC (0.9902) in vEpiNet compared to nEpiNet (0.9878). Moreover, to test the model performance in real-world scenarios, we set a prospective test dataset, containing 215 h of raw video-EEG data from 50 patients. The result shows that the vEpiNet achieves an area under the precision-recall curve (AUPRC) of 0.8623, surpassing nEpiNet's 0.8316. Incorporating video data raises precision from 70% (95% CI, 69.8%-70.2%) to 76.6% (95% CI, 74.9%-78.2%) at 80% sensitivity and reduces false positives by nearly a third, with vEpiNet processing one-hour video-EEG data in 5.7 min on average. Our findings indicate that video data can significantly improve the performance and precision of IED detection, especially in prospective real clinic testing. It suggests that vEpiNet is a clinically viable and effective tool for IED analysis in real-world applications.