Medical image translation plays a crucial role in assisting clinical diagnosis by enabling cross-modal synthesis (e.g., Computed Tomography to Magnetic Resonance Imaging) and super-resolution, effectively addressing clinical challenges such as radiation exposure, prolonged scan times, and allergic reactions to contrast agents. However, existing approaches primarily focus on developing specialized models for specific tasks, limiting their adaptability across different applications. Developing a general model capable of handling arbitrary medical image translation tasks not only enhances cross-domain generalization but also aligns with the broader trend of artificial intelligence evolving from specialized to general-purpose solutions. Achieving such one-for-all model, however, presents three key challenges: (1) varying task complexity, (2) modality discrepancies, and (3) structural variations across anatomical regions within the same modality. To tackle the first challenge, we utilize an advanced diffusion-based training paradigm to endow the denoising model with extensive pattern coverage capabilities, thereby handling tasks of varying difficulty levels. Subsequently, a General Diffusion Transformer incorporating a Fuzzy Mixture-of-Experts (FMoE) module and an Entropy-guided Attention Soft Prompt (EASP) module is proposed. The FMoE module, equipped with nonlinear modeling capabilities, is designed to address modality discrepancies, while the EASP module is employed to enhance the model's perception of structural variations in images. Extensive qualitative and quantitative experiments demonstrate the effectiveness of the proposed model in the arbitrary medical image translation task.

Recent self-supervised stereo matching methods have made significant progress. They typically rely on the photometric consistency assumption, which presumes corresponding points across views share the same appearance. However, this assumption could be compromised by real-world disturbances, resulting in invalid supervisory signals and a significant accuracy gap compared to supervised methods. To address this issue, we propose SMFormer, a framework integrating more reliable self-supervision guided by the Vision Foundation Model (VFM) and data augmentation. We first incorporate the VFM with the Feature Pyramid Network (FPN), providing a discriminative and robust feature representation against disturbance in various scenarios. We then devise an effective data augmentation mechanism that ensures robustness to various transformations. The data augmentation mechanism explicitly enforces consistency between learned features and those influenced by illumination variations. Additionally, it regularizes the output consistency between disparity predictions of strong augmented samples and those generated from standard samples. Experiments on multiple mainstream benchmarks demonstrate that our SMFormer achieves state-of-the-art (SOTA) performance among self-supervised methods and even competes on par with supervised ones. Remarkably, in the challenging Booster benchmark, SMFormer even outperforms some SOTA supervised methods, such as CFNet.

Zero-shot Sketch-based Image Retrieval (ZS-SBIR) is a challenging yet rewarding task, as it demands models to possess both brain- like zero-shot learning and cross-view alignment capabilities. Recent advances suggest that powerful pre-trained vision encoders, such as CLIP, offer a promising alternative for addressing the ZS-SBIR task. However, the problem of simultaneously evoking the zero-shot learning capability and cross-view alignment capability of pre-trained vision encoders has barely been discussed. To this end, we propose the CrOss-view Attention Prompt (COP) framework, which is composed of an Attention Prompt module and a Cross-view Query module. Specifically, we formulate prompt construction as a retrieval problem by introducing a prompt pool and attention mechanism, thereby constructing attention prompts with fine granularity to enhance the zero-shot learning capability. Furthermore, to endow COP with cross-view alignment capabilities, we replace single-view queries with carefully designed cross-view queries, which can be smoothly inserted into the Attention Prompt module. The proposed COP is scenario-agnostic and supports vision encoders with diverse pre-training schemes. Comprehensive experiments show that COP achieves competitive performance in ZS-SBIR, Generalized ZS-SBIR, and Cross-data ZS-SBIR scenarios, regardless of whether it is based on the ImageNet pre-trained vision encoder or the CLIP pre-trained vision encoder.

Self-supervised stereo matching has drawn attention due to its ability to estimate disparity without needing ground-truth data. However, existing self-supervised stereo matching methods heavily rely on the photo-metric consistency assumption, which is vulnerable to natural disturbances, resulting in ambiguous supervision and inferior performance compared to the supervised ones. To relax the limitation of the photo-metric consistency assumption and even bypass this assumption, we propose a novel self-supervised framework named DualNet, which consists of two key steps: robust self-supervised teacher learning and pseudo-label supervised student training. Specifically, the teacher model is first trained in a self-supervised manner with a focus on feature-metric consistency and data augmentation consistency. Then, the output of the teacher model is geometrically constrained to obtain high-quality pseudo labels. Benefiting from these high-quality pseudo labels, the student model can outperform its teacher model by a large margin. With the two well-designed steps, the proposed framework DualNet ranks 1st among all self-supervised methods on multiple benchmarks, surprisingly even outperforming several supervised counterparts.

Predicting stock trends is a highly rewarding but high-risk endeavor due to the complex interplay of market dynamics, irrational behaviors, and diverse sentiments. Previous studies have used time-series analysis on historical prices or sentiment analysis on textual information. However, these methods often fail to capture the dynamic interactions between text and time-series modalities and overlook the different perspectives embedded in textual data. To address these limitations, we propose the pleno-alignment framework (PAFrame) that enhances multimodal stock information through intermodal and intramodal alignment to capture market dynamics. Our framework first integrates textual and time-series data in a shared representation space to learn modal-invariant information. To tackle divergent sentiments in textual data, we employ a contrastive learning approach to extract abstract semantic meanings from objective and subjective perspectives, thereby improving the robustness of language representations. Finally, we use a hybrid approach that explicitly combines cross-attention mechanisms to create a unified representation and utilizes prompts to implicitly guide language models with numerical financial indicators for final prediction. Our comprehensive experiments on five real-world datasets show that PAFrame outperforms existing methods in predicting stock trends.

Multimodal Emotion Recognition is challenging because of the heterogeneity gap among different modalities. Due to the powerful ability of feature abstraction, Deep Neural Networks (DNNs) have exhibited significant success in bridging the heterogeneity gap in cross-modal retrieval and generation tasks. In this work, a DNNs-based Multi-channel Weight-sharing Autoencoder with Cascade Multi-head Attention (MCWSA-CMHA) is proposed to generically address the affective heterogeneity gap in MER. Specifically, multimodal heterogeneity features are extracted by multiple independent encoders, and then a scalable heterogeneous feature fusion module (CMHA) is realized by connecting multiple multi-head attention modules in series. The core of the proposed algorithm is to reduce the heterogeneity between the output features of different encoders through the unsupervised training of MCWSA, and then to model the affective interactions between different modal features through the supervised training of CMHA. Experimental results demonstrate that the proposed MCWSA-CMHA achieves outperformance on two publicly available datasets compared with the state-of-the-art techniques. In addition, visualization experiments and approximation experiments are used to verify the effectiveness of each module in the proposed algorithm, and the experimental results show that the proposed MCWSA-CMHA can mine more emotion-related information among multimodal features compared with other fusion methods.

Memristors are widely used to construct multi-scroll/wing chaotic systems with complex dynamics. However, the generation of a multi-scroll/wing attractor is typically not induced by the memristor but depends on other nonlinear functions in the system, which does not take advantage of the unique features of the memristor for chaos-based applications. To address this issue, the present paper introduces a memristor coupling (MC) method to construct a novel memristive Sprott A system (MSAS) through coupling a flux-controlled memristor with multi-piecewise linear memductance into the chaotic Sprott A system. From theoretical analysis and numerical simulations, the MSAS is shown to be able to generate any number of multi-type hidden attractors, including multi-one-scroll, multi-double-scroll and multi-double-wing hidden attractors. In addition, it has two kinds of multistabilities, that is, heterogeneous multistability and homogeneous multistability. Based on these unique properties, different numbers of coexisting heterogeneous hidden attractors and coexisting homogeneous hidden attractors are derived respectively by switching the memristor initial states. These interesting dynamical properties are comprehensively investigated using nonlinear analysis tools. Furthermore, hardware experiments are implemented to demonstrate the feasibility of the MSAS and the effectiveness of the MC method. Finally, a new pseudo-random number generator (PRNG) is proposed to explore the practical applications of the MSAS. Performance evaluation results verify the high-quality randomness of the designed PRNG.