Ye Yao

Ye Yao, Tingfeng Han, Shan Jia et al.

Image inpainting, the process of filling in missing areas in an image, is a common image editing technique. Inpainting can be used to conceal or alter image contents in malicious manipulation of images, driving the need for research in image inpainting detection. Most existing methods use a basic encoder-decoder structure, which often results in a high number of false positives or misses the inpainted regions, especially when dealing with targets of varying semantics and scales. Additionally, the lack of an effective approach to capture boundary artifacts leads to less accurate edge localization. In this paper, we describe a new method for inpainting detection based on a Dense Feature Interaction Network (DeFI-Net). DeFI-Net uses a novel feature pyramid architecture to capture and amplify multi-scale representations across various stages, thereby improving the detection of image inpainting by better strengthening feature-level interactions. Additionally, the network can adaptively direct the lower-level features, which carry edge and shape information, to refine the localization of manipulated regions while integrating the higher-level semantic features. Using DeFI-Net, we develop a method combining complementary representations to accurately identify inpainted areas. Evaluation on seven image inpainting datasets demonstrates the effectiveness of our approach, which achieves state-of-the-art performance in detecting inpainting across diverse models. Code and models are available at https://github.com/Boombb/DeFI-Net_Inpainting.

Ye Yao

The annotation of video tampering dataset is a boring task that takes a lot of manpower and financial resources. At present, there is no published literature which is capable to improve the annotation efficiency of forged videos. We presented a computer-aided annotation method for video tampering dataset in this paper. This annotation method can be utilized to label the frames of forged video sequences. By means of comparing the original video frames with the forged video frames, we can locate the position and the trajectory of the forged areas of the forged video frames. Then, we select several key points on the temporal domain according to the trajectory of the forged areas, and mark the forged area of the forged frames in the key point with a mouse. Finally, we use the linear prediction algorithm based on the coordinates of the key positions in the temporal domain to generate the annotation information of forged areas in other video frames which without manually labeled. If the bounding box generated by the computer-aided algorithm deviates from the actual location of the forged area, we can use the mouse to change the position of the bounding box during the preview period. This method combines the manual annotation with computer-aided annotation. It solves the problems of the inaccuracy of annotation by computer-aided as well as the low efficiency of annotation manually, and meet the needs of annotation for an enormous amount of forged videos in the research of video passive forensics.

Yuanfang Chen, Falin Chen, Yizhi Ren et al.

Traffic flow prediction is an important research issue to avoid traffic congestion in transportation systems. Traffic congestion avoiding can be achieved by knowing traffic flow and then conducting transportation planning. Achieving traffic flow prediction is challenging as the prediction is affected by many complex factors such as inter-region traffic, vehicles' relations, and sudden events. However, as the mobile data of vehicles has been widely collected by sensor-embedded devices in transportation systems, it is possible to predict the traffic flow by analysing mobile data. This study proposes a deep learning based prediction algorithm, DeepTFP, to collectively predict the traffic flow on each and every traffic road of a city. This algorithm uses three deep residual neural networks to model temporal closeness, period, and trend properties of traffic flow. Each residual neural network consists of a branch of residual convolutional units. DeepTFP aggregates the outputs of the three residual neural networks to optimize the parameters of a time series prediction model. Contrast experiments on mobile time series data from the transportation system of England demonstrate that the proposed DeepTFP outperforms the Long Short-Term Memory (LSTM) architecture based method in prediction accuracy.