With wide applications of image editing tools, forged images have become a great public concern. Although existing methods for image forgery localization (IFL) could achieve fairly good results on several public datasets, most of them perform unsatisfactorily for cross-dataset evaluation and online social network applications. To tackle this issue, a novel coarse-to-fine framework using Diffusion probabilistic model for Image Forgery Localization (Diff-IFL) is proposed in this paper, which consists of a coarse localization module and a mask diffusion module. The coarse localization module employs a transformer-based architecture to represent the tampered images and generate coarse masks. While the mask diffusion module formulates IFL as a mask reconstruction task, it relies on the extracted forgery feature representations as the conditional prior to gradually recover the clean ground-truth mask from the noisy mask. Extensive experiments demonstrate that Diff-IFL outperforms other SOTA methods and exhibits superior robustness against social media forgery.

This letter concentrates on the challenges of deep learning-based robust image watermarking against print-scanning, print-camera, and screen-shooting attacks for “physical channel transmission”. Given the excellent performance demonstrated by wavelet domain watermarking, in this paper, we incorporate the wavelet integrated convolutional neural networks (CNNs) and propose a Deep Wavelet-domain Watermarking (DWW) model, which is dedicated to embedding watermarks in the wavelet domain rather than the spatial domain of the previous arts. In addition, a frequency-domain enhanced mask loss is developed to increase the loss weight in the high-frequency regions of the image during back-propagation, thereby encouraging the model to embed the message in low-frequency components with priority so as to improve the robustness performance. Experiment results show that the proposed DWW consistently outperforms other state-of-the-art (SOTA) schemes by a clear margin in terms of embedding capacity, imperceptibility, and robustness.

There has been a growing interest in cross-source searching to gain rich knowledge in recent years. A data lake collects massive raw and heterogeneous data with different data schemas and query interfaces. Many real-life applications require query answering over the heterogeneous data lake, such as e-commerce, bioinformatics and healthcare. In this paper, we propose LakeAns that semantically integrates heterogeneous data schemas of the lake to enhance the semantics of query answers. To this end, we propose a novel framework to efficiently and effectively perform the cross-source searching. The framework exploits a reinforcement learning method to semantically integrate the data schemas and further create a global relational schema for the heterogeneous data. It then performs a query answering algorithm based on the global schema to find answers across multiple data sources. We conduct extensive experimental evaluations using real-life data to verify that our approach outperforms existing solutions in terms of effectiveness and efficiency.

Most real-time end-to-end text spotting methods employ sequence models as their recognition heads. However, these models generate characters one by one, which is inefficient when there are many characters. To solve this problem, we propose a Character Feature Summarization (CFS) Model, which can predict fixed-length characters in parallel, regardless of length. Specifically, we propose a Character Feature Summarization Module (CFSM) consisting of a Global Feature Capture and a Historical Feature Summarizer to extract and summarize global character features, enabling getting characters by simple linear prediction. We use Multi-stage Testing, cascading multiple CFSMs to obtain multi-stage summarized global character features to obtain several predictions for better convergence. The Result Selector is used to select the most likely result. Experiments on the Total-Text dataset show that CFS achieves a 3.53% improvement on the "Full" while being 3.6 times faster than ABCNet v2’s head.