activity
20172022
most citedJL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection

29 citations · 70 across the 9 of their papers we have counts for

collaborators

16 papers

cs.CV20222 cited

Unsupervised Homography Estimation with Coplanarity-Aware GAN

Mingbo Hong, Yuhang Lu, Nianjin Ye +3

Estimating homography from an image pair is a fundamental problem in image alignment. Unsupervised learning methods have received increasing attention in this field due to their pr…

cs.CV20214 cited

Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection

Wenbo Zhang, Ge-Peng Ji, Zhuo Wang +2

RGB-D salient object detection (SOD) recently has attracted increasing research interest by benefiting conventional RGB SOD with extra depth information. However, existing RGB-D SO…

cs.CV2021

Equivalence of Correlation Filter and Convolution Filter in Visual Tracking

Shuiwang Li, Qijun Zhao, Ziliang Feng +1

(Discriminative) Correlation Filter has been successfully applied to visual tracking and has advanced the field significantly in recent years. Correlation filter-based trackers con…

cs.CV20213 cited

Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking

Shuiwang Li, Yuting Liu, Qijun Zhao +1

Unmanned aerial vehicle (UAV)-based tracking is attracting increasing attention and developing rapidly in applications such as agriculture, aviation, navigation, transportation and…

cs.CV20211 cited

BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detection

Wenbo Zhang, Yao Jiang, Keren Fu +1

Depth information has been proved beneficial in RGB-D salient object detection (SOD). However, depth maps obtained often suffer from low quality and inaccuracy. Most existing RGB-D…

cs.CV2021

RGB-D Salient Object Detection via 3D Convolutional Neural Networks

Qian Chen, Ze Liu, Yi Zhang +3

RGB-D salient object detection (SOD) recently has attracted increasing research interest and many deep learning methods based on encoder-decoder architectures have emerged. However…