A video encoding/decoding method and apparatus in a temporal direct mode in a hierarchical structure. The video encoding method in the temporal direct mode in the hierarchical structure includes calculating a temporal position of a forward reference frame or a backward reference frame of a high-pass frame; searching for frames that exist at the temporal position and have motion vector information; if there is a plurality of frames searched for, selecting as a co-located frame a frame, among the plurality of frames, having a motion vector of which an interval is closest to a difference in interval between the forward reference frame and the backward reference frame of the high-pass frame, and extracting the motion vector of the selected frame; and encoding information on the selected frame so that the high-pass frame can use the extracted motion vector.