While significant progress has been achieved in multimodal facial generation using semantic masks and textual descriptions, conventional feature fusion approaches often fail to enable effective cross-modal interactions, thereby leading to suboptimal generation outcomes. To address this challenge, we introduce MDiTFace—a customized diffusion transformer framework that employs a unified tokenization strategy to process semantic mask and text inputs, eliminating discrepancies between heterogeneous modality representations. The framework facilitates comprehensive multimodal feature interaction through stacked, newly designed multivariate transformer blocks that process all conditions synchronously. Additionally, we design a novel decoupled attention mechanism by dissociating implicit dependencies between mask tokens and temporal embeddings. This mechanism segregates internal computations into dynamic and static pathways, enabling caching and reuse of features computed in static pathways after initial calculation, thereby reducing additional computational overhead introduced by mask condition by over 94% while maintaining performance. Extensive experiments demonstrate that MDiTFace significantly outperforms other competing methods in terms of both facial fidelity and conditional consistency.

Despite significant advancements in diffusion models for generating high-quality portrait images, the problem of malformed hands remains a critical and unresolved challenge. Existing methods primarily focus on structural restoration, often neglecting the semantic coherence between the corrected hand region and the overall image. To address this limitation, we propose a novel dual-pathway diffusion malformed hand correction method, named DD-MHC, which integrates a Global Context Aware Module (GCAM) and a Local Structure Refinement Module (LSRM) through a dual-path architecture. Under the synergy of cross-attention and spatial attention, these modules can effectively fuse global contextual features and local guiding cues, enabling precise restoration of the hand region. Comprehensive experiments demonstrate that DD-MHC significantly outperforms existing competing methods, particularly in enhancing the semantic consistency between the corrected hand region and the overall image. Additionally, to address the challenge of data scarcity in the research on correcting malformed hands within unconstrained scene portraits, we construct a brand-new General-Scene Portrait Dataset (GSPD), providing a standardized and reproducible data platform for subsequent related research.

Multi-modal trackers have drawn widespread attention for robust tracking in challenging scenarios. However, existing multi-modal trackers often rely solely on spatial matching between the initial target template and the search regions, or incorporate only single-frame historical information, failing to fully exploit temporal correlations in tracking sequences. Additionally, most trackers that introduce temporal modeling require either retraining the entire network or designing specialized modules for temporal feature extraction, which incurs additional computational costs. To alleviate these limitations, inspired by human visual memory, we propose MPTrack, a novel tracker that directly reuses pre-extracted historical target features as memory prompts, establishing temporal dependencies without redundant feature extraction or specially designed temporal extraction networks. Our proposed Memory Prompt Fusion module effectively combines initial target templates with multiple historical memory cues to generate enhanced templates, enabling the perception of long-term appearance dynamics while mitigating potential interference from individual memory. Simultaneously, to avoid the computational cost of full-model training, we design a lightweight memory adapter that allows the frozen backbone network to efficiently adapt to the memory-enhanced template. Extensive experiments demonstrate that our method effectively incorporates temporal information and achieves promising results across different multi-modal tracking scenarios, including RGB+Thermal, RGB+Event, and RGB+Depth tracking tasks.

In this paper, we propose a new method called \textit{Self-Training with Dynamic Weighting} (STDW), which aims to enhance robustness in Gradual Domain Adaptation (GDA) by addressing the challenge of smooth knowledge migration from the source to the target domain. Traditional GDA methods mitigate domain shift through intermediate domains and self-training but often suffer from inefficient knowledge migration or incomplete intermediate data. Our approach introduces a dynamic weighting mechanism that adaptively balances the loss contributions of the source and target domains during training. Specifically, we design an optimization framework governed by a time-varying hyperparameter $\varrho$ (progressing from 0 to 1), which controls the strength of domain-specific learning and ensures stable adaptation. The method leverages self-training to generate pseudo-labels and optimizes a weighted objective function for iterative model updates, maintaining robustness across intermediate domains. Experiments on rotated MNIST, color-shifted MNIST, portrait datasets, and the Cover Type dataset demonstrate that STDW outperforms existing baselines. Ablation studies further validate the critical role of $\varrho$'s dynamic scheduling in achieving progressive adaptation, confirming its effectiveness in reducing domain bias and improving generalization. This work provides both theoretical insights and a practical framework for robust gradual domain adaptation, with potential applications in dynamic real-world scenarios.

Image fusion aims to extract valuable information from each modality to create a fused image. Currently, state-of-the-art image fusion approaches tend to initially decompose each modality into distinct yet complementary features, and transfer beneficial information through carefully hand-crafted or learned fusion rules to the target. Nevertheless, previous approaches treat each modality in isolation before fusion, potentially under-utilising the complementary information available across modalities. In this word, we introduce a novel method called MEFusion that pioneers cross-modality mutual enhancement before feature decomposition. By harnessing the individual strengths of each modality, MEFusion elevates the overall quality and comprehensiveness of the fusion outcome. To facilitate a bidirectional enhancement for each feature across modalities, we have designed a pluggable co-attention mechanism that seamlessly integrates into a lightweight dual-path transformer. Furthermore, to enrich the details of each modality, we propose an unsupervised cross-modality mutual enhancement loss, which overcomes the limitations of requiring paired training data for enhancement tasks. Extensive experiments conducted on several benchmark datasets demonstrate the superiority of our proposed MEFusion method in terms of traditional fusion metrics and perceptual quality improvement of fused images.