With an efficient reliability evaluation and refinement of motion contours, the proposed segmentation strategy outperforms the other state-of-art approaches on ...
A flexible segmentation framework is formulated as a compositional model by combining saliency map with motion prior. A robust contour filling method is ...
A novel interactive video saliency prediction model that employs stacked-ConvLSTM based architecture along with a novel XY-shift frame differencing custom ...
With an efficient reliability evaluation and refinement of motion contours, the proposed segmentation strategy outperforms the other state-of-art approaches on ...
2019. Saliency flow based video segmentation via motion guided contour refinement. P Zhang, T Zhuo, H Huang, M Kankanhalli. Signal Processing 142, 431-440 ...
In this section, we present the Cascaded Refinement Net- work(CRN) which can effectively segment an object under the guidance of the coarse segmentation from ...
2018: Saliency flow based video segmentation via motion guided contour refinement Signal Processing 142: 431-440 · Hu, Z.; Liu, Z.; Li, G.; Ye, L.; Zhou, L ...
Saliency flow based video segmentation via motion guided contour refinement · Peng ZhangTao ZhuoHanqiao HuangM. Kankanhalli. Computer Science. Signal Processing.
In this repository, we mainly focus on deep learning based saliency methods (2D RGB, 3D RGB-D/T, Video SOD and 4D Light Field) and provide a summary (Code and ...
In this work, a novel contrastive motion clustering algorithm with an optical flow as its input is proposed for the online UVOS by exploiting the common fate ...