Sciweavers

119 search results - page 7 / 24
» A novel method for learning policies from constrained motion
Sort
View
TNN
2010
234views Management» more  TNN 2010»
13 years 2 months ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes
ICCV
2003
IEEE
14 years 9 months ago
Machine Learning and Multiscale Methods in the Identification of Bivalve Larvae
This paper describes a novel application of support vector machines and multiscale texture and color invariants to a problem in biological oceanography: the identification of 6 sp...
Sanjay Tiwari, Scott Gallager
ICIP
2009
IEEE
14 years 8 months ago
Learning Local Models For 2d Human Motion Tracking
We present a novel approach to tracking 2D human motion in uncalibrated monocular videos. Human motion usually exhibits timevarying patterns, and we propose to use locally learnt ...
IJCV
2008
167views more  IJCV 2008»
13 years 7 months ago
Learning Layered Motion Segmentations of Video
We present an unsupervised approach for learning a generative layered representation of a scene from a video for motion segmentation. The learnt model is a composition of layers, ...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
SI3D
2006
ACM
14 years 1 months ago
Human motion estimation from a reduced marker set
Motion capture data from human subjects exhibits considerable redundancy. In this paper, we propose novel methods for exploiting this redundancy. In particular, we set out to find...
Guodong Liu, Jingdan Zhang, Wei Wang 0010, Leonard...