Olivieri et al. [12] proposed a spatiotemporal motion feature to represent activities termed motion vector flow instance (MVFI) templates.
Based on a novel motion feature to measure the relative motion of two patches, the SVM classifier learns their pairwise relationship.
It's the first of the studio's stop-motion features to be shot in digital and the first shot in 3-D, developments that some Aardman purists may find the outrageous equivalent of Bob Dylan going electric or David Fincher going digital.
To this end, first a novel spatial-temporal multi-feature is proposed by joining super-pixel based multi-appearance features and multi-motion features to solve fast moving crowd counting.
The proposed method makes use of fine-grained motion features, similarly to [33] to achieve superior performance, while having computational requirements that match those of much simpler and less well-performing approaches.
In the NSEEV model, the salience of the target is influenced by both static features (contrast of the item of interest and the environment; see Itti & Koch, 2000) and dynamic or motion features (moment-to-moment changes of static salience; see Loy, Xiang, & Gong, 2012; Yantis & Jonides, 1990).
Richards-Rissetto et al. [11] used Kinect's body motion detection features to perform navigation in a 3D reconstructed model of an ancient Maya city using virtual reality.
