Deepfake detection plays a key role in preventing the misuses of artificial intelligence in video editing. Current deep learning-based deepfake detection methods often perform quite well in intra-dataset testing, but they may lose good performance in cross-dataset testing. In other words, generalization capability is still a crucial problem to be resolved. In this paper, we address deepfake detection by treating an image as non-Euclidean data and representing it as a graph so as to infer the informative connections between image patches/nodes to improve the detector’s generalization capability. Specifically, we propose a graph neural network-based paradigm that casts deepfake detection as a graph binary classification problem. First, we propose a dual-branch network to extract node features from both RGB images and their color difference images (CDIs) via the Transformer-based trainable node encoder module (TNEM). Second, we adopt the adjacency matrix to establish the connections of the nodes and further optimize the graph representation by applying the adaptive threshold to the adjacency matrix. Third, multi-head graph convolutional neural networks are carried out for node feature extraction. RGB node features and CDI node features are concatenated and separately fed into the graph classifier and node classifier for forgery detection and forgery localization. Experimental results demonstrate that our method can overall outperform other state-of-the-art methods on 7 popular benchmark datasets. Notably, our model achieves the highest AUC values of 96.19%, 80.99% and 87.68% on Celeb-DF-V2, DFDC and DFDCP in turn when trained on FF++ (C23). The visualization of node classification results also provides good interpretability of our proposed approach.
Current video steganography operates with either the decoded frame images or the compression coding parameters, which could cause quality degradation of the reconstructed frames. In this letter, by exploiting the advanced motion vector prediction (AMVP) technique of High Efficiency Video Coding (HEVC) standard, we propose a non-degraded adaptive steganographic approach for H.265/HEVC videos. The index value in the candidate list of the prediction unit (PU) is used for embedding. Experimental results demonstrate the superiority of the proposed steganographic approach against both hand-crafted feature-based and deep learning network-based steganalytic detectors. Our work explores a new embedding space that is not previously studied. It is a significant development in finding new ways to escape from video quality change-based steganalysis.
One of the challenges faced by surveillance video analysis is to detect objects from the frames. For outdoor surveillance, detection of small object like pedestrian is of particular interest. This paper proposes a fast, lightweight, and auto-zooming-based framework for small pedestrian detection. An attentive virtual auto-zooming scheme is proposed to adaptively zoom-in the input frame by splitting it into non-overlapped tiles and pay attention to the only important tiles. Without sacrificing detection performance, we have obtained a fully convolutional pedestrian detection model which can be run on low computational resources. It has been trained on an outdoor surveillance dataset and evaluated on two specially prepared testing sets of small (far) pedestrians in outdoor surveillance. We have compared our framework performance with different single-step customized pedestrian detectors as well as the two-step detector faster R-CNN. The results validate the efficiency of our framework.