Visual saliency: A manifold way of perception

摘要: Visual saliency plays an important role in the human visual system HVS since it is indispensable for object detection and recognition. A bottom-up model was proposed, following manifold characteristic of HVS, previously developed understanding mechanism. The a given location field defined as power features responses after dimensionality reduction with learning sparse representation raw input. This definition also explains reason that can suppress response redundant pattern excite attended pattern. Experiments show our produces better predictions eye fixations on two dataset comparsion four state-of-the-art methods.