Recognizing Action at a Distance

  • Authors:

  • Alexei A. Efros;Alexander C. Berg;Greg Mori;Jitendra Malik

  • Affiliations:

  • -;-;-;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Our goal is to recognize human actions at a distance,at resolutions where a whole person may be, say, 30 pixelstall. We introduce a novel motion descriptor based onoptical flow measurements in a spatio-temporal volume foreach stabilized human figure, and an associated similaritymeasure to be used in a nearest-neighbor framework. Makinguse of noisy optical flow measurements is the key challenge,which is addressed by treating optical flow not asprecise pixel displacements, but rather as a spatial patternof noisy measurements which are carefully smoothed andaggregated to form our spatio-temporal motion descriptor.To classify the action being performed by a human figurein a query sequence, we retrieve nearest neighbor(s) from adatabase of stored, annotated video sequences. We can alsouse these retrieved exemplars to transfer 2D/3D skeletonsonto the figures in the query sequence, as well as two formsof data-based action synthesis "Do as I Do" and "Do as ISay". Results are demonstrated on ballet, tennis as well asfootball datasets.