ISOMER: Informative Segment Observations for Multimedia Event Recounting

This paper describes a system for multimedia event detec-tion and recounting. The goal is to detect a high level event class in unconstrained web videos and generate event ori-ented summarization for display to users. For this purpose, we detect informative segments and collect observations for them, leading to our ISOMER system. We combine a large collection of both low level and semantic level visual and audio features for event detection. For event recounting, we propose a novel approach to identify event oriented dis-criminative video segments and their descriptions with a linear SVM event classifier. User friendly concepts includ-ing objects, actions, scenes, speech and optical character recognition are used in generating descriptions. We also de-velop several mapping and filtering strategies to cope with noisy concept detectors. Our system performed competi-tively in the TRECVID 2013 Multimedia Event Detection task with near 100,000 videos and was the highest performe