![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
Behavior recognition based on the improved density clustering and context-guided Bi-LSTM model
Context information is vital to research video human behavior recognition. Under the LSTM together with CNN of the framework, a novel action recognition method, which extracts keyframes by the improved density...
-
Article
Multi-feature aggregation network for salient object detection
As the network deepens, the boundary information and small object will be lost, which result in blurred edges and incomplete salient detection. In this paper, we propose a multi-feature aggregated network to s...
-
Article
Salient object detection based on multi-feature graphs and improved manifold ranking
In this paper, a salient object detection model based on multi-feature and modified manifold ranking is proposed. Different from traditional manifold ranking based models, the graphs in the proposed model are ...
-
Chapter and Conference Paper
Visual Tracking via Sparse Representation and Online Dictionary Learning
Sparse representation has been shown competitive performance on single object tracking. In this paper, we extend this technique to tracking multiple interactive objects and present a novel sparse tracker under...