This paper presents a new multiple-modality method for extracting semantic information from basketball video. The visual, motion, and audio information are extracted from video to first generate some low-level video segmentation and classification. Domain knowledge is further exploited for detecting interesting events in the basketball video. For video, both visual and motion prediction information are utilized for shot and scene boundary detection algorithm; this will be followed by scene classification. For audio, audio keysounds are sets of specific audio sounds related to semantic events and a classification method based on hidden Markov model (HMM) is used for audio keysound identification. Subsequently, by analyzing the multimodal information, the positions of potential semantic events, such as “foul” and “shot at the basket,” are located with additional domain knowledge. Finally, a video annotation is generated according to MPEG-7 multimedia description schemes (MDSs). Experimental results demonstrate the effectiveness of the proposed method.