A survey of advances in vision-based human motion capture and analysis
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Vision-based human motion analysis: An overview
Computer Vision and Image Understanding
Recovery of upper body poses in static images based on joints detection
Pattern Recognition Letters
Boosted multiple deformable trees for parsing human poses
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Hierarchical vibrations for part-based recognition of complex objects
Pattern Recognition
Segmentation of human body parts using deformable triangulation
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on recent advances in biometrics
Online visual tracking with histograms and articulating blocks
Computer Vision and Image Understanding
Cascaded models for articulated pose estimation
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Efficient inference with multiple heterogeneous part detectors for human pose estimation
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Computer Vision and Image Understanding
Inference and Learning with Hierarchical Shape Models
International Journal of Computer Vision
Discriminative Appearance Models for Pictorial Structures
International Journal of Computer Vision
Discriminative hierarchical part-based models for human parsing and action recognition
The Journal of Machine Learning Research
Hi-index | 0.00 |
We present a new method for training deformable models. Assume that we have training images where part locations have been labeled. Typically, one fits a model by maximizing the likelihood of the part labels. Alternatively, one could fit a model such that, when the model is run on the training images, it finds the parts. We do this by maximizing the conditional likelihood of the training data. We formulate model-learning as parameter estimation in a conditional random field (CRF). Initializing parameters with their maximum likelihood estimates, we reach the global optimum by gradient ascent. We present a learning algorithm that searches exhaustively over all part locations in an image without relying on feature detectors. This provides millions of examples of training data, and seems to avoid over-fitting issues known with CRFs. Results for part localization are relatively scarce in the community. We present results on three established datasets; Caltech motorbikes [8], USC people [19], and Weizmann horses [3]. In the Caltech set we significantly outperform the state-of-the-art [6]. For the challenging people dataset, we present results that are comparable to [19], but are obtained using a significantly more generic model (devoid of a face or skin detector). Our model is general enough to find other articulated objects; we use it to recover poses of horses in the challenging Weizmann database.