most citedSalient Object Detection via Dynamic Scale Routing

47 citations · 55 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CV202247 cited

Salient Object Detection via Dynamic Scale Routing

Zhenyu Wu, Shuai Li, Chenglizhao Chen +2

Recent research advances in salient object detection (SOD) could largely be attributed to ever-stronger multi-scale feature representation empowered by the deep learning technologi…

cs.CV2020

Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter

Zhenyu Wu, Shuai Li, Chenglizhao Chen +2

The real human attention is an interactive activity between our visual system and our brain, using both low-level visual stimulus and high-level semantic information. Previous imag…

cs.CV2020

Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection

Xuehao Wang, Shuai Li, Chenglizhao Chen +3

Existing RGB-D salient object detection methods treat depth information as an independent component to complement its RGB part, and widely follow the bi-stream parallel network arc…

cs.CV2020

Recursive Multi-model Complementary Deep Fusion forRobust Salient Object Detection via Parallel Sub Networks

Zhenyu Wu, Shuai Li, Chenglizhao Chen +2

Fully convolutional networks have shown outstanding performance in the salient object detection (SOD) field. The state-of-the-art (SOTA) methods have a tendency to become deeper an…

cs.CV20203 cited

Knowing Depth Quality In Advance: A Depth Quality Assessment Method For RGB-D Salient Object Detection

Xuehao Wang, Shuai Li, Chenglizhao Chen +2

Previous RGB-D salient object detection (SOD) methods have widely adopted deep learning tools to automatically strike a trade-off between RGB and D (depth), whose key rationale is…

cs.CV20203 cited

A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset

Zhenyu Wu, Shuai Li, Chenglizhao Chen +2

Compared with the conventional hand-crafted approaches, the deep learning based methods have achieved tremendous performance improvements by training exquisitely crafted fancy netw…