The annotation of video tampering dataset is a boring task that takes a lot\nof manpower and financial resources. At present, there is no published\nliterature which is capable to improve the annotation efficiency of forged\nvideos. We presented a computer-aided annotation method for video tampering\ndataset in this paper. This annotation method can be utilized to label the\nframes of forged video sequences. By means of comparing the original video\nframes with the forged video frames, we can locate the position and the\ntrajectory of the forged areas of the forged video frames. Then, we select\nseveral key points on the temporal domain according to the trajectory of the\nforged areas, and mark the forged area of the forged frames in the key point\nwith a mouse. Finally, we use the linear prediction algorithm based on the\ncoordinates of the key positions in the temporal domain to generate the\nannotation information of forged areas in other video frames which without\nmanually labeled. If the bounding box generated by the computer-aided algorithm\ndeviates from the actual location of the forged area, we can use the mouse to\nchange the position of the bounding box during the preview period. This method\ncombines the manual annotation with computer-aided annotation. It solves the\nproblems of the inaccuracy of annotation by computer-aided as well as the low\nefficiency of annotation manually, and meet the needs of annotation for an\nenormous amount of forged videos in the research of video passive forensics.\n