Music emotion recognition is a key task in symbolic music understanding (SMER). Recent approaches have shown promising results by fine-tuning large-scale pre-trained models (e.g., MIDIBERT, a benchmark in symbolic music understanding) to map musical semantics to emotional labels. While these models effectively capture distributional musical semantics, they often overlook tonal structures, particularly musical modes, which play a critical role in emotional perception according to music psychology. In this paper, we investigate the representational capacity of MIDIBERT and identify its limitations in capturing mode-emotion associations. To address this issue, we propose a Mode-Guided Enhancement (MoGE) strategy that incorporates psychological insights on mode into the model. Specifically, we first conduct a mode augmentation analysis, which reveals that MIDIBERT fails to effectively encode emotion-mode correlations. Motivated by this observation, we further identify the MIDIBERT layer that shows the weakest emotion relevance and introduce a Mode-guided Feature-wise linear modulation injection (MoFi) framework to inject explicit mode features, thereby enhancing the model's capability in emotional representation and inference. Extensive experiments on the EMOPIA and VGMIDI datasets demonstrate that our mode injection strategy significantly improves SMER performance, achieving accuracies of 75.2% and 59.1%, respectively. These results validate the effectiveness of mode-guided modeling in symbolic music emotion recognition.

Diabetic retinopathy (DR), a serious complication of diabetes, is one of the primary causes of vision loss in retinal vascular diseases. While deep learning has been widely used for DR grading, their performance declines significantly when applied to data outside the training distribution due to domain shifts. Domain generalization (DG) addresses this challenge, yet most existing DG methods neglect lesion-specific features, limiting diagnostic accuracy.In this paper, we propose a novel approach that enhances existing DG methods by incorporating structural priors, inspired by the observation that DR grading is heavily dependent on vessel and lesion structures. We introduce Low-rank Adaptive Structural Priors (LoASP), a plug-and-play framework designed for seamless integration with existing DG models. LoASP improves generalization by learning adaptive structural representations that are finely tuned to the complexities of DR diagnosis.Extensive experiments on eight diverse datasets validate its effectiveness in both single-source and multisource domain scenarios. Visualizations show the learned priors align with vessel/lesion structures, enhancing interpretability and diagnostic relevance.

Precise polyp segmentation is extremely challenging due to the diverse appearances and shaps’s of polyps along with severe light imbalance. To this end, we propose a novel network architecture, GroupSeg, which aims to learn robust representations by fully exploring global contextual representations and texture features of polyps through grouping segmentation to improve polyp segmentation performance. Specifically, GroupSeg groups features from the transformer encoder into progressively larger segments of different shapes, making full use of global contextual information to generate segmentation maps from fine to coarse, and thus can automatically adapt to polyps of different shapes and sizes, and is highly adaptive to the distribution of different polyp datasets. To further mine texture features to improve the performance of polyp segmentation, we introduce a Grouping Feature Aggregation Module (GFA), which adaptively mines the clues of local pixels and grouping feature segments, making the grouping features more accurate.GroupSeg demonstrates superior performance compared to state-of-the-art methods on ETIS, Endoscene, and ColonDB datasets, while high competitiveness on ClinicDB. It offers propsective outcomes in polyp segmentation.

Joint direction-of-arrival (DOA) and range estimation based on frequency diverse array (FDA) have been a critical issue in radar detection, tracking, and navigation. This paper first proposes a bidirectional extension frequency diverse coprime array (BE-FDCA) to obtain an extended 2D virtual array with a larger degree of freedom (DOF). Furthermore, on top of BE-FDCA, we introduce a sparse reconstruction algorithm, referred to as SR-BE-FDCA, to avoid time-consuming peak searches. The algorithm includes two key steps: sparse reconstruction of Decoupled Atomic Norm Minimization (DANM) and 2D ESPRIT estimation. With the aid of these designs, our approach achieves more accurate DOA and range estimations. Finally, numerical simulations are implemented to demonstrate the effectiveness of our method.