Consider a p-variate($p{geq}3$) normal distribution with mean ${ heta}$ and covariance matrix ${sum}={sigma}^2{mathbf{I}}_p$ for any unknown scalar ${sigma}^2$. In this paper we improve the James-Stein estimator of ${ heta}$ in cases of shrinking toward some vectors using the Stein variance estimator. It is also shown that this domination does not hold for the positive part versions of these estimators.