Text Image Tampering Detection and Localization is vital for verifying digital text images authenticity. The neglect of text image-specific tampering features in existing methods constrains their robustness and generalization across diverse scenarios. To address this, we propose TRAMFuse, a framework combining the Directional Residual Attention Mechanism (DRAM), tailored for text image tampering, and the Feature Neighborhood Constraint Module (FNCM), a general-purpose tampering feature extractor. DRAM captures geometric and directional features unique to text images, while FNCM enhances robustness by identifying inconsistencies. A cross-modal fusion for RGB-X (CMX) module is employed to integrate multi-modal features. To further advance research in text image tampering detection, we have constructed a large-scale mixed text image tampering dataset, named DocTamperMix. Experiments demonstrate that TRAMFuse outperforms state-of-the-art methods in both tampering detection and localization, showcasing its effectiveness across diverse scenarios.

Image denoising is essential in low-level vision applications such as photography and automated driving. Existing methods struggle with distinguishing complex noise patterns in real-world scenes and consume significant computational resources due to reliance on Transformer-based models. In this work, the Context-guided Receptance Weighted Key-Value (CRWKV) model is proposed, combining enhanced multi-view feature integration with efficient sequence modeling. The Context-guided Token Shift (CTS) mechanism is introduced to effectively capture local spatial dependencies and enhance the model's ability to model real-world noise distributions. Also, the Frequency Mix (FMix) module extracting frequency-domain features is designed to isolate noise in high-frequency spectra, and is integrated with spatial representations through a multi-view learning process. To improve computational efficiency, the Bidirectional WKV (BiWKV) mechanism is adopted, enabling full pixel-sequence interaction with linear complexity while overcoming the causal selection constraints. The model is validated on multiple real-world image denoising datasets, outperforming the state-of-the-art methods quantitatively and reducing inference time up to 40%. Qualitative results further demonstrate the ability of our model to restore fine details in various scenes. The code is publicly available at https://github.com/Seeker98/CRWKV.