Without further ado’ing, here – pretty banner compliments of the awesome 4padfoot!
Tags » SVM
In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a conditional model trained in a max-margin framework that is able to automatically discover discriminative and interesting segments of video, while simultaneously achieving competitive accuracies on difficult detection and recognition tasks. 297 more words