Probabilistic Visual Learning for Object Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic Human Recognition from Video
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Face Recognition from Long-Term Observations
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Adaptive Color-Image Embeddings for Database Navigation
ACCV '98 Proceedings of the Third Asian Conference on Computer Vision-Volume I - Volume I
Face Recognition Using Temporal Image Sequence
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
The Earth Mover's Distance under Transformation Sets
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Video-based face recognition using probabilistic appearance manifolds
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Video-based face recognition using adaptive hidden markov models
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Many-to-many graph matching via metric embedding
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Video-based face recognition: state of the art
CCBR'11 Proceedings of the 6th Chinese conference on Biometric recognition
| Hi-index | 0.00 |
This paper presents a novel approach for video-based face recognition We define a metric based on an average L2 Euclidean distance between two videos as the classifier This metric makes use of Earth Mover's Distance (EMD) as the underlying similarity measurement between videos Earth Mover's Distance is a recently proposed metric for geometric pattern matching and it reflects the average ground distance between two distributions Under the framework of EMD, each video is modeled as a video signature and Euclidean distance is selected as the ground distance of EMD Since clustering algorithm is employed, video signature can well represent the overall data distribution of faces in video Experimental results demonstrate the superior performance of our algorithm.