Projects:
Video Saliency Detection via Sparsity-based Reconstruction and Propagation (2019-TIP) [Details]
Video saliency detection aims to continuously discover the motion-related salient objects from the video sequences. Since it needs to consider the spatial and temporal constraints jointly, video saliency detection is more challenging than image saliency detection. In this project, we propose a new method to detect the salient objects in video based on sparse reconstruction and propagation.
Going from RGB to RGBD Saliency: A Depth-guided Transformation Model (2019-TCyb) [Details]
Depth information has demonstrated to be useful for saliency detection. However, the existing methods for RGBD saliency detection mainly focus on designing straightforward and comprehensive models, while ignoring the transferable ability of the existing RGB saliency detection models. In this paper, we propose a novel depth-guided transformation model going from RGB saliency to RGBD saliency. The proposed model includes three components, i.e., multi-level RGBD saliency initialization, depth-guided saliency refinement, and saliency optimization with depth constraints.
HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Images (2019-TMM) [Details]
Co-saliency detection aims at discovering the common and salient objects from an image group containing more than two related images. Moreover, depth information has been demonstrated to be effective for many computer vision tasks. In this project, we propose a novel co-saliency detection method for RGBD images based on hierarchical sparsity reconstruction and energy function refinement.
An Iterative Co-Saliency Framework for RGBD Images (2019-TCyb) [Details]
The existing co-saliency detection methods often generate the co-saliency map through a direct forward pipeline which is based on the designed cues or initialization, but lack the refinement-cycle scheme. In this project, we propose an iterative RGBD co-saliency framework for RGBD images, which utilizes the existing single saliency maps as the initialization, and generates the final RGBD cosaliency map by using a refinement-cycle model.
Co-Saliency Detection for RGBD Images Based on Multi-Constraint Feature Matching and Cross Label Propagation (2018-TIP) [Details]
Co-saliency detection aims at extracting the common salient regions from an image group containing two or more relevant images. It is a newly emerging and significant topic in computer vision community. Different from the most existing co-saliency methods focusing on RGB images, in this project, we propose a novel co-saliency detection model for RGBD images, which utilizes the depth information to enhance identification of co-saliency.
RGBD Saliency Detection Based on Depth Confidence Analysis and Multiple Cues Fusion (2016-SPL) [Details]
Stereoscopic perception is an important part of human visual system that allows the brain to perceive depth. However, depth information has not been well explored in existing saliency detection models. In this project, a novel saliency detection method for stereoscopic images is proposed.