Landmark localization in human brain from Magnetic Resonance Imaging (MRI) is primarily important for numerous medical analysis applications. Recently developed regression based (including deep networks) methods typically learn a mapping from input features to individual landmark positions or transform parameters. These methods neglect the geometric correlations among landmarks, thus resulting in inaccurate localization, especially for the parcellation functional regions whose boundaries are composed of a bunch of landmarks. In this paper, we build a shape energy for landmarks on 3D MRI features and learn the gradient regression for the energy. Our method accelerates the iterative gradient calculation and accurately detect brain landmarks. We validate the algorithm on two localization tasks for two key points, anterior commissure (AC) and posterior commissure (PC), and for three functional regions on the OASIS T1-weighted MR data set. Experimental results demonstrate its efficiency and effectiveness by comparing with the state-of-the-art.