Learning human actions via information maximization

In this paper, we present a novel approach for automatically learning a compact and yet discriminative appearance-based human action model. A video sequence is represented by a bag of spatiotemporal features called video-words by quantizing the extracted 3D interest points (cuboids) from the videos. Our proposed approach is able to automatically discover the optimal number of videoword clusters by utilizing Maximization of Mutual Information(MMI). Unlike the k-means algorithm, which is typically used to cluster spatiotemporal cuboids into video words based on their appearance similarity, MMI clustering further groups the video-words, which are highly correlated to some group of actions. To capture the structural information of the learnt optimal video-word clusters, we explore the correlation of the compact video-word clusters. We use the modified correlgoram, which is not only translation and rotation invariant, but also somewhat scale invariant. We extensively test our proposed appr...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Jingen Liu, Mubarak Shah
• Keywords: Compact Video-word Clusters, Computer Vision, CVPR 2008, Ixmas Multiview Dataset, KTH Dataset, Multiview Dataset, Optimal Video-word Clusters