Abstract. We consider inferring the future actions of people from a still image or a short video clip. Predicting future actions before they are actually executed is a critical ingredient for enabling us to effectively interact with other humans on a daily basis. However, challenges are two fold: First, we need to capture the subtle details inherent in human movements that may imply a future action; second, predictions usually should be carried out as quickly as possible in the social world, when limited prior observations are available. In this paper, we propose hierarchical movemes -a new representation to describe human movements at multiple levels of granularities, ranging from atomic movements (e.g. an open arm) to coarser movements that cover a larger temporal extent. We develop a max-margin learning framework for future action prediction, integrating a collection of moveme detectors in a hierarchical way. We validate our method on two publicly available datasets and show that it achieves very promising performance.

This paper describes a method for detecting human respiratory motion with respiration-rate estimation using ultrawideband (UWB) synthetic aperture radar (SAR). In addition, positions of the breathing humans can be spatially resolved. The coherence of the SAR data is used to derive the generalized coherence factor (GCF), the generalized incoherence factor (GICF), and the filter-bank-based GCF (FBGCF) for the detection and estimation. The coherence is decreased by motion of the image object, and the GCF and GICF are used to detect the position of the moving object. Furthermore, since the spectral shift of SAR data varies with motion, the FBGCF can be used to determine the respiration rate. The efficacy of the proposed method was tested by constructing a UWB SAR system with a 1.5-GHz center frequency and a 1-GHz bandwidth. Through-wall SAR data of objects with various motions were acquired and analyzed. Moving objects were successively detected with a spectral resolution of 0.1 Hz, and using the GICF achieved a rejection ratio of 38 dB between stationary and moving objects. These results indicate that the FBGCF can be used for respiration-rate estimation.

No abstract