"Automatic Annotation of Everyday Movements"


This paper describes a system that can annotate a video sequence with: a description of the appearance of each actor; when the actor is in view; and a representation of the actor's activity while in view. The system does not require a fixed background, and is automatic. The system works by (1) tracking people in 2D and then, using an annotated motion capture dataset, (2) synthesizing an annotated 3D motion sequence matching the 2D tracks. The 3D motion capture data is manually annotated off-line using a class structure that describes everyday motions and allows motion annotations to be composed --- one may jump while running, for example. Descriptions computed from video of real motions show that the method is accurate.

Ramanan, D., Forsyth, D. A. "Automatic Annotation of Everyday Movements." Neural Info. Proc. Systems (NIPS), Vancouver, Canada, Dec 2003.

Paper           Journal version (draft)           Poster


The following movies are DIVX encoded.

Jacks Movie
Jacks Rot Movie Walk Movie
Jumping Jacks Jumping Jacks (3D) Walk
Weave Weave (Slow)
Weave Run
Weave Run (1/3 Speed)
lolaRun lolaStop lolaCorner
Lola Run
Lola Stop
Lola Corner

Back to home page