A decision-theoretic generalization of on-line learning and an application to boosting
Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Applications of Video-Content Analysis and Retrieval
IEEE MultiMedia
Using output codes to boost multiclass learning problems
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Video retrieval using spatio-temporal descriptors
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Detecting Pedestrians Using Patterns of Motion and Appearance
International Journal of Computer Vision
Motion pattern-based video classification and retrieval
EURASIP Journal on Applied Signal Processing
Style similarity measure for video documents comparison
CIVR'05 Proceedings of the 4th international conference on Image and Video Retrieval
Local descriptors for spatio-temporal recognition
SCVMA'04 Proceedings of the First international conference on Spatial Coherence for Visual Motion Analysis
| Hi-index | 0.00 |
This paper presents a novel and efficient similarity measure between video segments. We consider local spatio-temporal descriptors. They are considered to be realizations of an unknown, but class-specific distribution. The similarity of two video segments is calculated by evaluating an appropriate statistical criterion issued from a rank test. It does not require any matching of the local features between the two considered video segments, and can deal with a different number of computed local features in the two segments. Furthermore, our measure is self-normalized which allows for simple cue integration, and even on-line adapted class-dependent combination of the different descriptors. Satisfactory results have been obtained on real video sequences for two motion event recognition problems.