145 citations · 153 across the 5 of their papers we have counts for
4 papers
Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning
Linbo Wang, Jing Wu, Xianyong Fang +3
Recent studies of two-view correspondence learning usually establish an end-to-end network to jointly predict correspondence reliability and relative pose. We improve such a framew…
Scribble-Supervised RGB-T Salient Object Detection
Zhengyi Liu, Xiaoshen Huang, Guanghui Zhang +3
Salient object detection segments attractive objects in scenes. RGB and thermal modalities provide complementary information and scribble annotations alleviate large amounts of hum…
HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection
Bin Tang, Zhengyi Liu, Yacheng Tan +1
The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in w…
RGB-T Multi-Modal Crowd Counting Based on Transformer
Zhengyi Liu, Wei Wu, Yacheng Tan +1
Crowd counting aims to estimate the number of persons in a scene. Most state-of-the-art crowd counting methods based on color images can't work well in poor illumination conditions…