Towards generalizable face forgery detection via mitigating spurious correlation.

The continuous advancement of face forgery techniques has caused a series of trust crises, posing a significant menace to information security and personal privacy. In response, deep learning is being employed to develop effective detection methods to identify deepfake images and videos. Currently, most detection methods generally achieve satisfactory performance in intra-domain detection.

HDF-Net: Capturing Homogeny Difference Features to Localize the Tampered Image.

Modern image editing software enables anyone to alter the content of an image to deceive the public, which can pose a security hazard to personal privacy and public safety. The detection and localization of image tampering is becoming an urgent issue to be addressed. We have revealed that the tampered region exhibits homogenous differences (the changes in metadata organization form and organization structure of the image) from the real region after manipulations such as splicing, copy-move, and removal.

The migration process and temperature effect of aqueous solutions contaminated by heavy metal ions in unsaturated silty soils.

Adsorption-desorption experiments of three heavy metal ions (i.e., lead, copper, cadmium) in silty soil were carried out at different temperatures, and the microscopic characteristics of silty soil loaded with the three heavy metal ions were analyzed.

Physical Education Teaching Strategy under Internet of Things Data Computing Intelligence Analysis.

Racket sports such as tennis are amongst the most popular recreational sports activities. Optimizing tennis teaching methods and improving teaching modes can effectively improve the teaching quality of tennis. In this study, a video and image action recognition system based on image processing techniques and Internet of things is developed to overcome the shortcomings of the traditional tennis teaching methods.