Paper Info
Title
Multi-Modality Gesture Detection And Recognition With Un-Supervision, Randomization And Discrimination
Abstract
We describe in this paper our gesture detection and recognition system for the 2014 ChaLearn Looking at People (Track 3: Gesture Recognition) organized by ChaLearn in conjunction with the ECCV 2014 conference. The competition's task was to learn a vacabulary of 20 types of Italian gestures and detect them in sequences. Our system adopts a multi-modality approach for detecting as well as recognizing the gestures. The goal of our approach is to identify semantically meaningful contents from dense sampling spatio-temporal feature space for gesture recognition. To achieve this, we develop three concepts under the random forest framework: un-supervision; discrimination; and randomization. Un-supervision learns spatio-temporal features from two channels (grayscale and depth) of RGB-D video in an unsupervised way. Discrimination extracts the information in dense sampling spatio-temporal space effectively. Randomization explores the dense sampling spatio-temporal feature space efficiently. An evaluation of our approach shows that we achieve a mean Jaccard Index of 0.6489, and a mean average accuracy of 90.3% over the test dataset.
Year
DOI
Venue
2014
10.1007/978-3-319-16178-5_43
COMPUTER VISION - ECCV 2014 WORKSHOPS, PT I
Keywords
Field
DocType
Multi-modality gesture, Unsupervised learning, Random forest, Discriminative training
Computer science,Gesture,Gesture recognition,Unsupervised learning,Artificial intelligence,Jaccard index,Random forest,Grayscale,Computer vision,Feature vector,Pattern recognition,Sampling (statistics),Machine learning
Conference
Volume
ISSN
Citations 
8925
0302-9743
13
PageRank 
References 
Authors
0.55
14
7
Name
Order
Citations
PageRank
Guang Chen1375.15
Daniel Clarke2384.21
Manuel Giuliani323820.89
Andre Gaschler41359.32
Di Wu5636117.73
David Weikersdorfer6130.55
Alois Knoll Knoll71700271.32