Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection
This addresses the problem of accurately detecting salient regions in videos for computer vision applications, representing an incremental improvement in spatiotemporal context modeling.
The paper tackled video saliency detection by proposing a graph-theoretic approach based on adaptive video structure discovery and manifold propagation to model spatiotemporal context, achieving effectiveness as demonstrated in experiments on benchmark datasets.
As an important and challenging problem in computer vision, video saliency detection is typically cast as a spatiotemporal context modeling problem over consecutive frames. As a result, a key issue in video saliency detection is how to effectively capture the intrinsical properties of atomic video structures as well as their associated contextual interactions along the spatial and temporal dimensions. Motivated by this observation, we propose a graph-theoretic video saliency detection approach based on adaptive video structure discovery, which is carried out within a spatiotemporal atomic graph. Through graph-based manifold propagation, the proposed approach is capable of effectively modeling the semantically contextual interactions among atomic video structures for saliency detection while preserving spatial smoothness and temporal consistency. Experiments demonstrate the effectiveness of the proposed approach over several benchmark datasets.