Multimedia Event Detection Using Segment-Based Approach for Motion Feature

Multimedia event detection has become a popular research topic due to the explosive growth of video data. The motion features in a video are often used to detect events because an event may contain some specific actions or moving patterns. Raw motion features are extracted from the entire video first and then aggregated to form the final S. Phan ( ) · T. D. Ngo The Graduate University for Advanced Studies (SOKENDAI), Shonan Village, Hayama, Kanagawa 240-0193, Japan e-mail: [email protected] T. D. Ngo e-mail: [email protected] V. Lam · S. Tran Faculty of Information Technology, Ho Chi Minh City University of Science, 227 Nguyen Van Cu St., Dist. 5, Ho Chi Minh City, Vietnam V. Lam e-mail: [email protected] S. Tran e-mail: [email protected] D.-D. Le · D. A. Duong Multimedia Communications Lab, University of Information Technology, KM20 Xa Lo Ha Noi, Linh Trung Ward, Thu Duc District, Ho Chi Minh City, Vietnam D.-D. Le e-mail: [email protected] D. A. Duong e-mail: [email protected] D.-D. Le · S. Satoh National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan S. Satoh e-mail: [email protected] video representation. However, this video-based representation approach is ineffective when used for realistic videos because the video length can be very different and the clues for determining an event may happen in only a small segment of the entire video. In this paper, we propose using a segment-based approach for video representation. Basically, original videos are divided into segments for feature extraction and classification, while still keeping the evaluation at the video level. The experimental results on recent TRECVID Multimedia Event Detection datasets proved the effectiveness of our approach.