کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
533491 870124 2011 9 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Discriminative semi-supervised learning of dynamical systems for motion estimation
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
پیش نمایش صفحه اول مقاله
Discriminative semi-supervised learning of dynamical systems for motion estimation
چکیده انگلیسی

We introduce novel discriminative semi-supervised learning algorithms for dynamical systems, and apply them to the problem of 3D human motion estimation. Our recent work on discriminative learning of dynamical systems has been proven to achieve superior performance than traditional generative learning approaches. However, one of the main issues of learning the dynamical systems is to gather labeled output sequences which are typically obtained from precise motion capture tools, hence expensive. In this paper we utilize a large amount of unlabeled (input) video data to improve the prediction performance of the dynamical systems significantly. We suggest two discriminative semi-supervised learning approaches that extend the well-known algorithms in static domains to the sequential, real-valued multivariate output domains: (i) self-training which we derive as coordinate ascent optimization of a proper discriminative objective over both model parameters and the unlabeled state sequences, (ii) minimum entropy approach which maximally reduces the model's uncertainty in state prediction for unlabeled data points. These approaches are shown to achieve significant improvement against the traditional generative semi-supervised learning methods. We demonstrate the benefits of our approaches on the 3D human motion estimation problems.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 44, Issues 10–11, October–November 2011, Pages 2325–2333
نویسندگان
,