Searching Video for Complex Activities Using Finite State Models
	We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach is based on units of activity at segments of the body, that can be composed across space and across the body to produce complex queries. The presence of search units is inferred automatically by tracking the body, lifting the tracks to 3D and comparing to models trained using motion capture data. We show results for a large range of queries applied to a collection of complex motion and activity. Our models of short time scale limb behaviour are built using labelled motion capture set. We compare with discriminative methods applied to tracker data; our method offers significantly improved performance. We show experimental evidence that our method is robust to view direction and is unaffected by the changes of clothing.
Publication(s)	Nazli Ikizler and David Forsyth, Searching video for complex activities with finite state models. CVPR 2007. pdf Nazli Ikizler and David Forsyth, Searching for Complex Human Activities with No Visual Examples In International Journal of Computer Vision (IJCV), 2008. pdf
Dataset	We collected our own set of motions, involving three subjects wearing a total of five different outfits in a total of 73 movies (15Hz). Each video shows a subject instructed to produce a complex activity. The sequences differ in length. new Download UIUC Complex Activities Dataset (~636MB)
Human Action Recognition with Histograms
Publication(s)	Nazli Ikizler and Pinar Duygulu, Histogram of Oriented Rectangles: A New Pose Descriptor for Human Action Recognition Image and Vision Computing, September 2009. pdf Nazli Ikizler and Pinar Duygulu, Human Action Recognition Using Distribution of Oriented Rectangular Patches 2nd Workshop on Human Motion Understanding, Modeling, Capture and Animation held in conjunction with Eleventh IEEE International Conference on Computer Vision (ICCV 2007), October 2007. pdf Nazli Ikizler, R. Gokberk Cinbis, Human Action Recognition With Line and Flow Histograms International Conference on Pattern Recognition (ICPR 2008), Tampa, December 2008. pdf
Recognizing Actions in Still Images
Publication(s)	Nazli Ikizler, R. Gokberk Cinbis, Selen Pehlivan, Recognizing Actions in Still Images International Conference on Pattern Recognition (ICPR 2008), Tampa, December 2008. pdf
Dataset	new Still Actions Dataset : A dataset consists of 467 images collected from the web which consists of six actions (running, walking, throwing, catching, crouching and kicking) Download Still Actions Dataset (~9.5MB)