The shanghai-hongkong team at mediaeval2012: Violent scene detection using trajectory-based features

• Main Authors: JIANG, Yu-Gang, DAI, Qi, TAN, Chun Chet, XUE, Xiangyang, NGO, Chong-wah
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2012
• Subjects: Movie; Multi-modality; Temporal smoothing; Trajectory-based feature; Violent scene detection; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/6596; https://ink.library.smu.edu.sg/context/sis_research/article/7599/viewcontent/mediaeval2012_submission_28.pdf
• Institution: Singapore Management University

The Violent Scene Detection task offers a very practical challenge in detecting complex and diverse violent video clips in movies. In this working note paper, we will briefly describe our system and discuss the results, which achieved top performance in mAP@201 and runner-up in mAP@100, among all 35 submissions worldwide. The central component of our system is a set of features derived from the appearance and motion of local patch trajectories [2]. We use these features and SVM classifier as the baseline approach and add in a few other components to further improve the performance. Our findings indicate that the trajectory-based visual features already offer very competitive results. Other audio-visual features like SpatialTemporal Interest Points and MFCC do not significantly enhance the performance. In addition, smoothing detection scores of nearby shots leads to significant improvement. We conclude that—while audio feature may help marginally— good visual features are still the key factor in violent scene detection, and temporal information is very useful.