activity
20202024
most citedSalient Object Detection via Dynamic Scale Routing

47 citations · 110 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV20249 cited

Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Survey

Zhenyu Wu, Fengmao Lv, Chenglizhao Chen +2

Colorectal polyp segmentation (CPS), an essential problem in medical image analysis, has garnered growing research attention. Recently, the deep learning-based model completely ove…

cs.CV202228 cited

Synthetic Data Supervised Salient Object Detection

Zhenyu Wu, Lin Wang, Wei Wang +4

Although deep salient object detection (SOD) has achieved remarkable progress, deep SOD models are extremely data-hungry, requiring large-scale pixel-wise annotations to deliver su…

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.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…

cs.CV202023 cited

Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues

Jianrong Wang, Ge Zhang, Zhenyu Wu +2

In self-supervised monocular depth estimation, the depth discontinuity and motion objects' artifacts are still challenging problems. Existing self-supervised methods usually utiliz…