Recursive Estimation of Motion, Structure, and Focal Length
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Dynamics of Complex Motions from Image Sequences
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
From Regular Images to Animated Heads: A Least Squares Approach
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Bézier Volume Deformation Model for Facial Animation and Video Tracking
CAPTECH '98 Proceedings of the International Workshop on Modelling and Motion Capture Techniques for Virtual Environments
A bootstrapping algorithm for learning linear models of object classes
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
LAFTER: Lips and Face Real-Time Tracker
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Parametrized structure from motion for 3D adaptive feedback tracking of faces
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
The Representation and Recognition of Human Movement Using Temporal Templates
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Elliptical Head Tracking Using Intensity Gradients and Color Histograms
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Tracking and Segmenting People in Varying Lighting Conditions Using Colour
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Wide-Range, Person- and Illumination-Insensitive Head Orientation Estimation
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Hi-index | 0.00 |
In bootstrap initialization for tracking, we exploit a weak prior model used to track a target to learn a stronger model, without manual intervention. We define a general formulation of this problem and present a simple taxonomy of such tasks. The formulation is instantiated with algorithms for bootstrap initialization in two domains: In one, the goal is tracking the position of a face at a desktop; we learn color models of faces, using weak knowledge about the shape and movement of faces in video. In the other task, we seek coarse estimates of head orientation; we learn a person-specific ellipsoidal texture model for heads, given a generic model. For both tasks, we use nonparametric models of surface texture. Experimental results verify that bootstrap initialization is feasible in both domains. We find that (1) independence assumptions in the learning process can be violated to a significant degree, if enough data is taken; (2) there are both domain-independent and domain-specific means to mitigate learning bias; and (3) repeated bootstrapping does not necessarily result in increasingly better models.