Recent interest in large-scale text-driven diffusion models has highlighted their ability to generate diverse images from textual prompts, with style transfer being a significant application. However, existing text-guided stylization methods are constrained by the reliance on manually created masks for localized transformations, which limits scalability and automation. In this work, a novel framework, OmniStyle, is introduced for text-driven global and localized image style transfer, leveraging diffusion model inversion and attention-based mask generation. Input images are mapped into latent noise representations using DDIM inversion, while cross-attention maps are utilized to automatically generate precise semantic masks, eliminating the need for manual annotations. Latent features are dynamically optimized with mask-guided constraints and attention manipulations, enabling fine-grained style transfer confined to target regions while maintaining the integrity of global content. Extensive experiments demonstrate the scalability and effectiveness of OmniStyle.

Multimodal Emotion Recognition in Conversations (MERC) enhances emotional understanding through the fusion of multimodal signals. However, unpredictable modality absence in real-world scenarios significantly degrades the performance of existing methods. Conventional missing-modality recovery approaches, which depend on training with complete multimodal data, often suffer from semantic distortion under extreme data distributions, such as fixed-modality absence. To address this, we propose the Federated Dialogue-guided and Semantic-Consistent Diffusion (FedDISC) framework, pioneering the integration of federated learning into missing-modality recovery. By federated aggregation of modality-specific diffusion models trained on clients and broadcasting them to clients missing corresponding modalities, FedDISC overcomes single-client reliance on modality completeness. Additionally, the DISC-Diffusion module ensures consistency in context, speaker identity, and semantics between recovered and available modalities, using a Dialogue Graph Network to capture conversational dependencies and a Semantic Conditioning Network to enforce semantic alignment. We further introduce a novel Alternating Frozen Aggregation strategy, which cyclically freezes recovery and classifier modules to facilitate collaborative optimization. Extensive experiments on the IEMOCAP, CMUMOSI, and CMUMOSEI datasets demonstrate that FedDISC achieves superior emotion classification performance across diverse missing modality patterns, outperforming existing approaches.

Diffusion-based generative models have long depended on Gaussian priors, with little exploration of alternative distributions. We introduce a Proper Hölder-Kullback Dirichlet framework that uses time-varying multiplicative transformations to define both forward and reverse diffusion processes. Moving beyond conventional reweighted evidence lower bounds (ELBO) or Kullback–Leibler upper bounds (KLUB), we propose two novel divergence measures: the Proper Hölder Divergence (PHD) and the Proper Hölder–Kullback (PHK) divergence, the latter designed to restore symmetry missing in existing formulations. When optimizing our Dirichlet diffusion model with PHK, we achieve a Fréchet Inception Distance (FID) of 2.78 on unconditional CIFAR-10. Comprehensive experiments on natural-image datasets validate the generative strengths of model and confirm PHK’s effectiveness in model training. These contributions expand the diffusion-model family with principled non-Gaussian processes and effective optimization tools, offering new avenues for versatile, high-fidelity generative modeling.

Federated learning (FL) has gained prominence in electroencephalogram (EEG)-based emotion recognition because of its ability to enable secure collaborative training without centralized data. However, traditional FL faces challenges due to model and data heterogeneity in smart healthcare settings. For example, medical institutions have varying computational resources, which creates a need for personalized local models. Moreover, EEG data from medical institutions typically face data heterogeneity issues stemming from limitations in participant availability, ethical constraints, and cultural differences among subjects, which can slow model convergence and degrade model performance. To address these challenges, we propose FedKDC, a novel FL framework that incorporates clustered knowledge distillation (CKD). This method introduces a consensus-based distributed learning mechanism to facilitate the clustering process. It then enhances the convergence speed through intraclass distillation and reduces the negative impact of heterogeneity through interclass distillation. Additionally, we introduce a DriftGuard mechanism to mitigate client drift, along with an entropy reducer to decrease the entropy of aggregated knowledge. The framework is validated on the SEED, SEED-IV, SEED-FRA, and SEED-GER datasets, demonstrating its effectiveness in scenarios where both the data and the models are heterogeneous. Experimental results show that FedKDC outperforms other FL frameworks in emotion recognition, achieving a maximum average accuracy of 85.2%, and in convergence efficiency, with faster and more stable convergence.

Phonocardiogram classification methods using deep neural networks have been widely applied to the early detection of cardiovascular diseases recently.Despite their excellent recognition rate, the sizeable computational complexity limits their further development.Nowadays, knowledge distillation (KD) is an established paradigm for model compression.While current research on multi-teacher KD has shown potential to impart more comprehensive knowledge to the student than single-teacher KD, this approach is not suitable for all scenarios.This paper proposes a novel KD strategy to realise an adaptive multi-teacher instruction mechanism.We design a teacher selection strategy called voting network to tell the contribution of different teachers on each distillation points, so that the student can choose the useful information and renounce the redundant one.An evaluation demonstrates that our method reaches excellent accuracy (92.8 %) while maintaining a low computational complexity (0.7 M).