Title | ||
---|---|---|
Real-time Gesture Recognition with Minimal Training Requirements and On-line Learning |
Abstract | ||
---|---|---|
In this paper, we introduce the semantic network model (SNM), a generalization of the hidden Markov model (HMM) that uses factorization of state transition proba- bilities to reduce training requirements, increase the effi- ciency of gesture recognition and on-line learning, and al- low more precision in gesture modeling. We demonstrate the advantages both formally and experimentally, using ex- amples such as full-body multimodal gesture recognition via optical motion capture and a pressure sensitive floor, as well as mouse / pen gesture recognition. Our results show that our algorithm performs much better than the tra- ditional approach in situations where training samples are limited and/or the precision of the gesture model is high. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/CVPR.2007.383330 | CVPR |
Keywords | Field | DocType |
gesture recognition,hidden Markov models,image motion analysis,learning (artificial intelligence),semantic networks,full-body multimodal gesture recognition,hidden Markov model,online learning,optical motion capture,real-time gesture recognition,semantic network model,state transition probabilities,training requirements | Motion capture,Computer science,Gesture,Gesture recognition,Artificial intelligence,Online learning,Computer vision,Pattern recognition,Speech recognition,Semantic network,Factorization,Hidden Markov model,Machine learning | Conference |
Volume | Issue | ISSN |
2007 | 1 | 1063-6919 |
Citations | PageRank | References |
21 | 1.35 | 6 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stjepan Rajko | 1 | 154 | 14.22 |
Gang Qian | 2 | 784 | 63.77 |
Todd Ingalls | 3 | 125 | 16.97 |
Jodi James | 4 | 70 | 9.92 |