Delayed treatment of infantile retinal disease can reduce its effectiveness and may cause severe and irreversible damage. Automated diagnosis of infant retinal diseases faces challenges including subtle early lesions, diverse clinical phenotypes, imaging variations, and imbalanced data. To address these, which cannot be well addressed by existing general foundation models, we propose structure-aware bidirectional proxy interaction network (SABPI-Net) in a universal learning framework. SABPI-Net incorporates a high-frequency mapping branch, and employs a proposed proxy interaction attention module to enable effective interaction between its trunk feature encoding branch and the high-frequency mapping branch, thereby facilitating enhanced perception of retinal detail structures. Domain-agnostic embedding space self-matching, guided by a memory-bank low-frequency component replacement strategy, promotes domain-invariant learning and consistent model performance under diverse image styles. Finally, the tail-aware feature fusion strategy for fine-tuning further enhances the model's diagnostic sensitivity to tailed diseases. In this study, three classification tasks related to infant retinal diseases are implemented on the largest clinical infant retina dataset to date, covering 19 infant retinal diseases or normal conditions. SABPI-Net achieves superior performance compared to 13 SOTA methods, with 95.32% accuracy on mainstream clinical tasks, 73.58% on ROP five-stage classification, and 84.25% on multi-disease classification, representing improvements of 1.57%, 1.88%, and 4.71% respectively over the best competing methods. Extensive experiments demonstrate the effectiveness and superiority of SABPI-Net in diagnosing infant retinal diseases.

Behavior recognition is a highly challenging task, particularly in scenarios requiring unified recognition across both human and animal subjects. Most existing approaches primarily focus on single-species datasets or rely heavily on prior information such as species labels, positional annotations, or skeletal keypoints, which limits their applicability in real-world scenarios where species labels may be ambiguous or annotations are insufficient. To address these limitations, we propose a query-based Multi-Granularity Behavior Recognition Network that directly mines cross-species shared spatiotemporal behavior patterns from raw video inputs. Specifically, we design a Multi-Granularity Query module to effectively fuse fine-grained and coarse-grained features, thereby enhancing the model's capability in capturing spatiotemporal dynamics at different granularities. Additionally, we introduce a Category Query Decoder that leverages learnable category query vectors to achieve explicit behavior category modeling and mapping. Without relying on any extra annotations, the proposed method achieves unified recognition of multi-species and multi-category behaviors, setting a new state-of-the-art on the Animal Kingdom dataset and demonstrating strong generalization ability on the Charades dataset.

Accurate segmentation of breast lesions is vital for diagnosing breast diseases. Masked image modeling (MIM) with random masking performs well in self-supervised learning but struggles in breast ultrasound segmentation due to (1) ambiguous representations from similar intensities near lesion boundaries and (2) a bias toward irrelevant regions. We propose UA-MAE, an uncertainty-aware masked autoencoder that uses pixel-wise uncertainty maps to dynamically select masking patches, prioritizing boundaries and morphologically relevant lesion areas. Experiments on two public datasets for pre-training and three for fine-tuning show UA-MAE outperforming four state-of-theart SSL methods and two supervised approaches in segmentation accuracy across diverse breast ultrasound images. The code is available at https://github.com/yXiangXiong/UA-MAE.

This paper studies the Time-Critical Cooperative Delivery with Unknown Demands (TCDUD) problem, developed from the well-studied Capacitated Vehicle Routing Problem with Stochastic Demands (CVRPSD), that corresponds to emergency situations requiring 1) time-critical delivery; 2) unknown demands; and 3) cooperative delivery. We formulate the problem as a multi-agent sequential decision problem with a Collaborative Semi-Markov Decision Process (CSMDP) model in which timecritical delivery is urged by the reward function that takes both the amount and the time of fulfilled demands into account. Unlike traditional CVRPSD, we do not include a priori information about a customer's demand in problem definition, and require vehicles to visit a customer before its demand is revealed. A Transformer-based multi-agent reinforcement learning approach, namely MAODN, is devised to learn online policies that direct the vehicles to visit the customers, and perform timely delivery in a cooperative manner. MAODN utilizes a demand updater to accommodate online updates about customers' demands from the vehicles during delivery. Vehicles then make cooperative decisions via individual policy networks, leveraging the fleet state provided by the state aggregator. Experiment results suggest that our approach outperforms the baseline by at least 27.8% and demonstrates better robustness.

Retinopathy of prematurity (ROP) is a retinal vascular disease that primarily affects premature infants with low birth weight. It is a leading cause of childhood blindness worldwide, but it can often be effectively managed with appropriate and timely diagnosis and treatment. To address the impact of image style on model classification performance, this paper proposes a dual-scale Swin Transformer (DS-Swin-T) network for ROP. The network comprises three components: image synthesis (IS), feature alignment, and advanced adversarial learning. The IS module generates synthesis style images as an intermediate latent space between source and target styles, reducing style difference. The DS-Swin-T serves as the primary framework for image feature extraction. Detail and style encoders extract features in the shallow feature space, with detail and style losses aligning these features to ensure consistency across styles. To extract rich style-invariant features and ensure consistent classification within the same category, adversarial learning is applied in the advanced feature space. Finally, feature fusion units process dual-scale classification representations. Our method achieves an average accuracy of 97.91% on the source style dataset. When transferred to other target style datasets, our method effectively mitigates the performance degradation caused by style difference, reaching a maximum average accuracy of 93.66%. Extensive experiments demonstrate the effectiveness of our method.

The Extremely-large Aperture Reconfigurable In-telligent Surface (RIS) stands out as a promising technology for future 6G communications. However, existing far-field or near-field channel models struggle to adapt effectively to channel estimation in the context of Extremely-large Aperture RIS-assisted wireless communication under a hybrid field. To address this challenge, this paper introduces an efficient hybrid-field channel estimation scheme tailored for Extremely-large Aperture RIS-assisted wireless communication. In this scheme, we initially extend the one-dimensional polar coordinate dictionary to a full-dimensional spherical coordinate dictionary to achieve a more uniform distribution of grid points in the spherical coordinate-domain. Subsequently, we propose a hybrid passive/active RIS architecture, utilizing a limited number of Radio Frequency (RF) chains to acquire channel observations. Finally, we introduce a hybrid-field channel estimation scheme designed to estimate both far-field and near-field components. Simulation results demonstrate that the proposed scheme outperforms purely far-field or near-field schemes.

Automatic and accurate classification of retinal optical coherence tomography (OCT) images is essential to assist physicians in diagnosing and grading pathological changes in pathologic myopia (PM). Clinically, due to the obvious differences in the position, shape, and size of the lesion structure in different scanning directions, ophthalmologists usually need to combine the lesion structure in the OCT images in the horizontal and vertical scanning directions to diagnose the type of pathological changes in PM. To address these challenges, we propose a novel feature interaction Transformer network (FIT-Net) to diagnose PM using OCT images, which consists of two dual-scale Transformer (DST) blocks and an interactive attention (IA) unit. Specifically, FIT-Net divides image features of different scales into a series of feature block sequences. In order to enrich the feature representation, we propose an IA unit to realize the interactive learning of class token in feature sequences of different scales. The interaction between feature sequences of different scales can effectively integrate different scale image features, and hence FIT-Net can focus on meaningful lesion regions to improve the PM classification performance. Finally, by fusing the dual-view image features in the horizontal and vertical scanning directions, we propose six dual-view feature fusion methods for PM diagnosis. The extensive experimental results based on the clinically obtained datasets and three publicly available datasets demonstrate the effectiveness and superiority of the proposed method. Our code is avaiable at: https://github.com/chenshaobin/FITNet.

In multi-site studies of Alzheimer's disease (AD), the difference of data in multi-site datasets leads to the degraded performance of models in the target sites. The traditional domain adaptation method requires sharing data from both source and target domains, which will lead to data privacy issue. To solve it, federated learning is adopted as it can allow models to be trained with multi-site data in a privacy-protected manner. In this paper, we propose a multi-site federated domain adaptation framework via Transformer (FedDAvT), which not only protects data privacy, but also eliminates data heterogeneity. The Transformer network is used as the backbone network to extract the correlation between the multi-template region of interest features, which can capture the brain abundant information. The self-attention maps in the source and target domains are aligned by applying mean squared error for subdomain adaptation. Finally, we evaluate our method on the multi-site databases based on three AD datasets. The experimental results show that the proposed FedDAvT is quite effective, achieving accuracy rates of 88.75%, 69.51%, and 69.88% on the AD vs. NC, MCI vs. NC, and AD vs. MCI two-way classification tasks, respectively.

Unsupervised sentence embeddings learning has been recently dominated by contrastive learning methods (e.g., SimCSE), which keep positive pairs similar and push negative pairs apart. The contrast operation aims to keep as much information as possible by maximizing the mutual information between positive instances, which leads to redundant information in sentence embedding. To address this problem, we present an information minimization based contrastive learning InforMin-CL model to retain the useful information and discard the redundant information by maximizing the mutual information and minimizing the information entropy between positive instances meanwhile for unsupervised sentence representation learning. Specifically, we find that information minimization can be achieved by simple contrast and reconstruction objectives. The reconstruction operation reconstitutes the positive instance via the other positive instance to minimize the information entropy between positive instances. We evaluate our model on fourteen downstream tasks, including both supervised and unsupervised (semantic textual similarity) tasks. Extensive experimental results show that our InforMin-CL obtains a state-of-the-art performance.