Comparison of Feedforward (TDRBF) and Generative (TDRGBN) Network for Gesture Based [1 citations — 0 self]
Download:
by Helen Vassilakis, A. Jonathan Howell, Hilary Buxton
Control, Proceedings of the Int. Gesture Workshop 2001
http://www.techfak.uni-bielefeld.de/ags/wbski/gw2001book/draftpapers/gw2001paper_27.pdf
Add To MetaCart
Abstract:
Abstract. In Visually Mediated Interaction (VMI) there is a range of tasks that need to be supported (face and gesture recognition, camera controlled by gestures, visual interaction etc). These tasks vary in complexity: some can be predefined for supervised learning, some need self-organisation, some need generative models to be learned. Generative models may offer strong advantages in cases where a higher degree of generalization is needed. They have the potential of ``understanding' ' the gesture independent from the individual differences on the performance of a gesture. This paper presents a comparison between a feedforward network (RBF) and a generative one (RGBN) both extended in a time-delay version. 1
Citations
| 111 | Generative models for discovering sparse distributed representations – Hinton, Ghahramani - 1997 |
| 102 | Image representation for visual learning – Beymer, Poggio - 1996 |
| 15 | A similarity-based method for the generalization of face recognition over pose and expression – Duvdevani-Bar, Edelman, et al. - 1998 |
| 12 | Learning identity with radial basis function networks – Howell, Buxton - 1998 |
| 11 | Face recognition using radial basis function neural networks – Howell, Buxton - 1996 |
| 7 | Learning gestures for visually mediated interaction – Howell, Buxton - 1998 |
| 4 | Interpretation of group behaviour in visually mediated interaction – Sherrah, Gong, et al. - 2000 |
| 3 | Towards visually mediated interaction using appearance-based models – Howell, Buxton - 1998 |
| 3 | Face detection and attentional frames for visually mediated interaction – Howell, Buxton - 2000 |
