Classifying web videos using a global video descriptor

Computing descriptors for videos is a crucial task in computer vision. In this paper, we propose a global video descriptor for classification of videos. Our method, bypasses the detection of interest points, the extraction of local video descriptors and the quantization of descriptors into a code book; it represents each video sequence as a single feature vector. Our global descriptor is computed by applying a bank of 3-D spatio-temporal filters on the frequency spectrum of a video sequence; hence, it integrates the information about the motion and scene structure. We tested our approach on three datasets, KTH (Schuldt et al., Proceedings of the 17th international conference on, pattern recognition (ICPR'04), vol. 3, pp. 32-36, 2004), UCF50 (http://vision.eecs.ucf.edu/datasetsActions.html) and HMDB51 (Kuehne et al., HMDB: a large video database for human motion recognition, 2011), and obtained promising results which demonstrate the robustness and the discriminative power of our global video descriptor for classifying videos of various actions. In addition, the combination of our global descriptor and a local descriptor resulted in the highest classification accuracies on UCF50 and HMDB51 datasets.