High-level event detection system based on discriminant visual concepts

Ioannis Tsampoulatidis, Nikolaos Gkalelis, Anastasios Dimou, Vasileios Mezaris, Ioannis Kompatsiaris
2011 Proceedings of the 1st ACM International Conference on Multimedia Retrieval - ICMR '11  
This paper demonstrates a new approach to detecting highlevel events that may be depicted in images or video frames. Given a non-annotated content item, a large number of previously trained visual concept detectors are applied to it and their responses are used for representing the content item with a model vector in a high-dimensional concept space. Subsequently, an improved subclass discriminant analysis method is used for identifying a concept subspace within the aforementioned concept
more » ... ioned concept space, that is most appropriate for detecting and recognizing the target high-level events. In this subspace, the nearest neighbor rule is used for comparing the non-annotated content item with a few known example instances of the target events. The high-level events used as target events in the present version of the system are those defined for the TRECVID 2010 Multimedia Event Detection (MED) task.
doi:10.1145/1991996.1992064 dblp:conf/mir/TsampoulatidisGDMK11 fatcat:mkl2tj3s7bgoxjw4urjjtosila