Electroencephalography (EEG) foundation models, pre-trained on large-scale unlabeled data via self-supervised learning, have demonstrated strong generalization capabilities across various brain-computer interface (BCI) tasks. However, their practical deployment remains constrained by the expensive cost of data annotation required for task-specific fine-tuning. To mitigate this limitation, we propose EEGTune, a data-efficient fine-tuning framework for EEG foundation models that integrates active learning with consistency-based semi-supervised learning. Specifically, EEGTune first selects the most informative samples for expert annotation under a limited labeling budget and performs initial fine-tuning on this augmented annotated dataset. It then employs a consistency-based pseudo-labeling strategy, which enhances robustness to noise and eliminates manual confidence thresholding by leveraging prediction stability under stochastic augmentations. The model is finally fine-tuned on both the labeled and pseudo-labeled data, maximizing the use of all available samples. To evaluate the efficacy of EEGTune, we have conducted extensive experiments involving two state-of-the-art EEG foundation models across four representative downstream BCI tasks, including sleep staging, seizure detection, emotion recognition, and motor imagery. Experimental results demonstrate that our method achieves superior fine-tuning performance with significantly reduced labeling effort. Notably, on sleep staging and seizure detection tasks, EEGTune attains performance within 1-2% of fully supervised fine-tuning using only 15% of the labeled data. These results underscore the potential of our framework to substantially reduce annotation requirements while maintaining high performance, facilitating broader applications of EEG foundation models in real-world scenarios. The source code will be released at https://github.com/zer02her0/EEGTune .

Multimodal medical image registration critically relies on anatomical guidance for accurate spatial alignment. However, existing registration approaches fail to fully exploit the potential of segmentation labels, while joint registrationsegmentation (JRS) frameworks lack effective mechanisms for bidirectional task co-enhancement. To address these challenges, we propose CROSS-JRS, a novel framework that achieves mutual reinforcement between both tasks through synergistic innovations. Specifically, CROSS-JRS comprises three synergistic modules, each targeting a key aspect of the bidirectional interaction: The Segmentation-Guided Local-Global (SGLG) module hierarchically estimates deformations by progressively integrating multi-scale segmentation features with registration cues, while the Registration-Assisted Cross-Enhancement (RACE) module reciprocally improves segmentation accuracy through registrationderived spatial correspondences. To bridge features from complementary tasks, the Dual-Attention Domain Fusion (DADF) module aligns and fuses cross-task features via dynamic attention gating, enabling feature-level co-adaptation. Extensive experiments on two public 3D prostate MRI-US datasets demonstrate that the proposed CROSS-JRS outperforms the state-of-the-art JRS methods for both registration and segmentation tasks. The code is available at https://github.com/scuterGuoyulong/CROSS-JRS.

The convergence of large language models (LLMs) and virtual reality (VR) technologies has led to significant breakthroughs across multiple domains, particularly in healthcare and medicine. Owing to its immersive and interactive capabilities, VR technology has demonstrated exceptional utility in surgical simulation, rehabilitation, physical therapy, mental health, and psychological treatment. By creating highly realistic and precisely controlled environments, VR not only enhances the efficiency of medical training but also enables personalized therapeutic approaches for patients. The convergence of LLMs and VR extends the potential of both technologies. LLM-empowered VR can transform medical education through interactive learning platforms and address complex healthcare challenges using comprehensive solutions. This convergence enhances the quality of training, decision-making, and patient engagement, paving the way for innovative healthcare delivery. This study aims to comprehensively review the current applications, research advancements, and challenges associated with these two technologies in healthcare and medicine. The rapid evolution of these technologies is driving the healthcare industry toward greater intelligence and precision, establishing them as critical forces in the transformation of modern medicine.

Previous methods for Video Frame Interpolation (VFI) have encountered challenges, notably the manifestation of blur and ghosting effects. These issues can be traced back to two pivotal factors: unavoidable motion errors and misalignment in supervision. In practice, motion estimates often prove to be error-prone, resulting in misaligned features. Furthermore, the reconstruction loss tends to bring blurry results, particularly in misaligned regions. To mitigate these challenges, we propose a new paradigm called PerVFI (Perception-oriented Video Frame Interpolation). Our approach incorporates an Asymmetric Synergistic Blending module (ASB) that utilizes features from both sides to synergistically blend intermediate features. One reference frame emphasizes primary content, while the other contributes complementary information. To impose a stringent constraint on the blending process, we introduce a self-learned sparse quasi-binary mask which effectively mitigates ghosting and blur artifacts in the output. Additionally, we employ a normalizing flow-based generator and utilize the negative log-likelihood loss to learn the conditional distribution of the output, which further facilitates the generation of clear and fine details. Experimental results validate the superiority of PerVFI, demonstrating significant improvements in perceptual quality compared to existing methods. Codes are available at https://github.com/mulns/PerVFI

Emotion classification based on electroencephalogram (EEG) signals has drawn huge attention in affective brain computer interface (BCI). Recently, plenty of deep learning approaches have been proposed to improve the performance of EEG emotion recognition, especially the application of domain adaptation methods to tackle the challenge of large individual differences of EEG signals from subject to subject. However, these conventional transfer learning methods would result in information leakage during the sharing of domain data to enhance the accuracy of the target tasks. Therefore, in this paper, we proposed a distributed deep learning method, named adaptive federated learning (AdaFL) for EEG emotion recognition. In AdaFL, a server collaboratively learns a global model by adaptively aggregating the local models according to their importance in several communication rounds. In particular, an importance function is developed to evaluate each client, which would determine to select a subset of optimal clients for subsequent global model aggregation. The function is a simple transformation of the training loss and the sample size of the local models. Then, the resulting importance scores of selected clients are further converted into aggregation coefficients to measure the weights of the local models for global model aggregation. The distinct advantage of AdaFL is that the cross-subject information could be well utilized and the information leakage risk could be significantly reduced. To validate the efficacy of the proposed AdaFL, we conduct extensive experiments on two real EEG emotion datasets, i.e., SEED and DEAP. The experimental results show that the proposed AdaFL has achieved 94.95 ± 0.40% and 91.06 ± 0.29% average classification accuracy on the SEED and DEAP datasets, respectively, which reflects the superiority of our method over the state-of-the-art approaches.

Recent deep learning-based optical flow estimators have exhibited impressive performance in generating local flows between consecutive frames. However, the estimation of long-range flows between distant frames, particularly under complex object deformation and large motion occlusion, remains a challenging task. One promising solution is to accumulate local flows explicitly or implicitly to obtain the desired long-range flow. Nevertheless, the accumulation errors and flow misalignment can hinder the effectiveness of this approach. This paper proposes a novel recurrent framework called AccFlow, which recursively backward accumulates local flows using a deformable module called as AccPlus. In addition, an adaptive blending module is designed along with AccPlus to alleviate the occlusion effect by backward accumulation and rectify the accumulation error. Notably, we demonstrate the superiority of backward accumulation over conventional forward accumulation, which to the best of our knowledge has not been explicitly established before. To train and evaluate the proposed AccFlow, we have constructed a large-scale high-quality dataset named CVO, which provides ground-truth optical flow labels between adjacent and distant frames. Extensive experiments validate the effectiveness of AccFlow in handling long-range optical flow estimation. Codes are available at https://github.com/mulns/AccFlow.

In obstetric sonography, the quality of acquisition of ultrasound scan video is crucial for accurate (manual or automated) biometric measurement and fetal health assessment. However, the nature of fetal ultrasound involves free-hand probe manipulation and this can make it challenging to capture high-quality videos for fetal biometry, especially for the less-experienced sonographer. Manually checking the quality of acquired videos would be time-consuming, subjective and requires a comprehensive understanding of fetal anatomy. Thus, it would be advantageous to develop an automatic quality assessment method to support video standardization and improve diagnostic accuracy of video-based analysis. In this paper, we propose a general and purely data-driven video-based quality assessment framework which directly learns a distinguishable feature representation from high-quality ultrasound videos alone, without anatomical annotations. Our solution effectively utilizes both spatial and temporal information of ultrasound videos. The spatio-temporal representation is learned by a bi-directional reconstruction between the video space and the feature space, enhanced by a key-query memory module proposed in the feature space. To further improve performance, two additional modalities are introduced in training which are the sonographer gaze and optical flow derived from the video. Two different clinical quality assessment tasks in fetal ultrasound are considered in our experiments, i.e., measurement of the fetal head circumference and cerebellar diameter; in both of these, low-quality videos are detected by the large reconstruction error in the feature space. Extensive experimental evaluation demonstrates the merits of our approach.

Video inpainting remains a challenging problem to fill with plausible and coherent content in unknown areas in video frames despite the prevalence of data-driven methods. Although various transformer-based architectures yield promising result for this task, they still suffer from hallucinating blurry contents and long-term spatial-temporal inconsistency. While noticing the capability of discrete representation for complex reasoning and predictive learning, we propose a novel Discrete Latent Transformer (DLFormer) to reformulate video inpainting tasks into the discrete latent space rather the previous continuous feature space. Specifically, we first learn a unique compact discrete codebook and the corresponding autoencoder to represent the target video. Built upon these representative discrete codes obtained from the entire target video, the subsequent discrete latent transformer is capable to infer proper codes for unknown areas under a self-attention mechanism, and thus produces fine-grained content with long-term spatial-temporal consistency. Moreover, we further explicitly enforce the short-term consistency to relieve temporal visual jitters via a temporal aggregation block among adjacent frames. We conduct comprehensive quantitative and qualitative evaluations to demonstrate that our method significantly outperforms other state-of-the-art approaches in reconstructing visually-plausible and spatial-temporal coherent content with fine-grained details. Code is available at https://github.com/JingjingRenabc/dlformer.

In this article, we study a tensor-based multitask learning (MTL) method for classification. Taking into account the fact that in many real-world applications, the given training samples are limited and can be inherently arranged into multidimensional arrays (tensors), we are motivated by the advantages of MTL, where the shared structural information among related tasks can be leveraged to produce better generalization performance. We propose a regularized tensor-based MTL method for joint feature selection and classification. For feature selection, we employ the Fisher discriminant criterion to both select discriminative features and control the within-class nonstationarity. For classification, we take both shared and task-specific structural information into consideration. We decompose the regression tensor for each task into a linear combination of a shared tensor and a task-specific tensor and propose a composite tensor norm. Specifically, we use the scaled latent trace norm for regularizing the shared tensor and the$\ell _{1}$-norm for task-specific tensor. Further, we give a computationally efficient optimization algorithm based on the alternating direction method of multipliers (ADMMs) to tackle the joint learning of discriminative features and multitask classification. The experimental results on real electroencephalography (EEG) datasets demonstrate the superiority of our method over the state-of-the-art techniques.

In the context of motor imagery, electroencephalography (EEG) data vary from subject to subject such that the performance of a classifier trained on data of multiple subjects from a specific domain typically degrades when applied to a different subject. While collecting enough samples from each subject would address this issue, it is often too time-consuming and impractical. To tackle this problem, we propose a novel end-to-end deep domain adaptation method to improve the classification performance on a single subject (target domain) by taking the useful information from multiple subjects (source domain) into consideration. Especially, the proposed method jointly optimizes three modules, including a feature extractor, a classifier, and a domain discriminator. The feature extractor learns the discriminative latent features by mapping the raw EEG signals into a deep representation space. A center loss is further employed to constrain an invariant feature space and reduce the intrasubject nonstationarity. Furthermore, the domain discriminator matches the feature distribution shift between source and target domains by an adversarial learning strategy. Finally, based on the consistent deep features from both domains, the classifier is able to leverage the information from the source domain and accurately predict the label in the target domain at the test time. To evaluate our method, we have conducted extensive experiments on two real public EEG data sets, data set IIa, and data set IIb of brain-computer interface (BCI) Competition IV. The experimental results validate the efficacy of our method. Therefore, our method is promising to reduce the calibration time for the use of BCI and promote the development of BCI.

Robust and efficient image alignment remains a challenging task, due to the massiveness of images, great illumination variations between images, partial occlusion, and corruption. To address these challenges, we propose an online image alignment method via subspace learning from image gradient orientations (IGOs). The proposed method integrates the subspace learning, transformed the IGO reconstruction and image alignment into a unified online framework, which is robust for aligning images with severe intensity distortions. Our method is motivated by a principal component analysis (PCA) from gradient orientations that provides more reliable low-dimensional subspace than that from pixel intensities. Instead of processing in the intensity-domain-like conventional methods, we seek alignment in the IGO domain, such that the aligned IGO of the newly arrived image can be decomposed as the sum of a sparse error and a linear composition of the IGO-PCA basis learned from previously well-aligned ones. The optimization problem is tackled by an iterative linearization that minimizes the ℓ1-norm of the sparse error. Furthermore, the IGO-PCA basis is adaptively updated based on incremental thin singular value decomposition, which takes the shift of IGO mean into consideration. The efficacy of the proposed method is validated on the extensive challenging datasets through image alignment, medical atlas construction, and face recognition. The experimental results demonstrate that our algorithm provides more illumination- and occlusion-robust image alignment than the state-of-the-art methods.

Robust and effective shape prior modeling from a set of training data remains a challenging task, since the shape variation is complicated, and shape models should preserve local details as well as handle shape noises. To address these challenges, a novel robust projective dictionary learning (RPDL) scheme is proposed in this paper. Specifically, the RPDL method integrates the dimension reduction and dictionary learning into a unified framework for shape prior modeling, which can not only learn a robust and representative dictionary with the energy preservation of the training data, but also reduce the dimensionality and computational cost via the subspace learning. In addition, the proposed RPDL algorithm is regularized by using the norm to handle the outliers and noises, and is embedded in an online framework so that of memory and time efficiency. The proposed method is employed to model prostate shape prior for the application of magnetic resonance transrectal ultrasound registration. The experimental results demonstrate that our method provides more accurate and robust shape modeling than the state-of-the-art methods do. The proposed RPDL method is applicable for modeling other organs, and hence, a general solution for the problem of shape prior modeling.

Robust and efficient image alignment remains a challenging task, due to the massiveness of images, great illumination variations between images, partial occlusion and corruption. To address these challenges, we propose an online image alignment method via subspace learning from image gradient orientations (IGO). The proposed method integrates the subspace learning, transformed IGO reconstruction and image alignment into a unified online framework, which is robust for aligning images with severe intensity distortions. Our method is motivated by principal component analysis (PCA) from gradient orientations provides more reliable low-dimensional subspace than that from pixel intensities. Instead of processing in the intensity domain like conventional methods, we seek alignment in the IGO domain such that the aligned IGO of the newly arrived image can be decomposed as the sum of a sparse error and a linear composition of the IGO-PCA basis learned from previously well-aligned ones. The optimization problem is accomplished by an iterative linearization that minimizes the L1-norm of the sparse error. Furthermore, the IGO-PCA basis is adaptively updated based on incremental thin singular value decomposition (SVD) which takes the shift of IGO mean into consideration. The efficacy of the proposed method is validated on extensive challenging datasets through image alignment and face recognition. Experimental results demonstrate that our algorithm provides more illumination- and occlusion-robust image alignment than state-of-the-art methods do.

This paper proposes a STATCOM compensation scheme for suppressing commutation failure (CF) in HVDC. In this scheme, the neutral-point of CHB-STATCOM with star configuration is grounded and thus possesses three advantages. Firstly, it keeps the high economy of CHB-STATCOM with star configuration. Secondly, three phases are independent of each other, which can be considered as three single-phase STATCOMs, leading to a simple and flexible control strategy and overcoming the control problem when CHB-STATCOM with star configuration operations under unbalance grid. Thirdly, it forms zero-sequence current channel by taking the characteristic of HVDC, which is the neutral-point of the AC grid connected by HVDC is directly grounded, thus it can compensate not only harmonics, positive and negative-sequence reactive power, but also zero-sequence reactive power, resulting in excellent compensatory capacity. In this paper, first of all, feasibility of the proposed scheme in HVDC is analyzed in detail. Then, zero-sequence current is calculated in detail under unbalance power grid condition. Finally, simulations based on PSCAD/EMTDC are carried out to illustrate the effectiveness to suppress CF in HVDC.

In order to overcome the difficulties of poor voltage regulation and narrow speed range for the traditional permanent magnet synchronous machine used in the generation system, a parallel-connected open-winding topology is adopted with the inverter in series to one side of the windings and the rectifier to another side. Due to the parallel-connected dc sides of the rectifier and inverter, the zero-sequence current would flow in the windings under the conventional space vector pulse width modulation method for the voltage regulation, and it was result in the low efficiency. Therefore, the operation principle of the parallel-connected topology was given, and the causes and components of zero-sequence current for conventional space vector pulse with modulation algorithm was analyzed. Then, the hysteresis modulation method is adopted to suppress the zero-sequence current, and the suppression efficiency and feasibility of hysteresis modulation algorithm is verified by Simulation and experimental results.