Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Sheng Xu

Sheng Xu

An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection



Sheng Xu

Figure 1 for An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection
Figure 2 for An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection
Figure 3 for An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection
Figure 4 for An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection
* 12 pages 
   Access Paper or Ask Questions

TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping



Hongjie Fang , Hao-Shu Fang , Sheng Xu , Cewu Lu

Figure 1 for TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping
Figure 2 for TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping
Figure 3 for TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping
Figure 4 for TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping
* project page: www.graspnet.net/transcg 
   Access Paper or Ask Questions

TerViT: An Efficient Ternary Vision Transformer



Sheng Xu , Yanjing Li , Teli Ma , Bohan Zeng , Baochang Zhang , Peng Gao , Jinhu Lv

Figure 1 for TerViT: An Efficient Ternary Vision Transformer
Figure 2 for TerViT: An Efficient Ternary Vision Transformer
Figure 3 for TerViT: An Efficient Ternary Vision Transformer
Figure 4 for TerViT: An Efficient Ternary Vision Transformer

   Access Paper or Ask Questions

Neural Content Extraction for Poster Generation of Scientific Papers



Sheng Xu , Xiaojun Wan

Figure 1 for Neural Content Extraction for Poster Generation of Scientific Papers
Figure 2 for Neural Content Extraction for Poster Generation of Scientific Papers
Figure 3 for Neural Content Extraction for Poster Generation of Scientific Papers
Figure 4 for Neural Content Extraction for Poster Generation of Scientific Papers

   Access Paper or Ask Questions

POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing



Sheng Xu , Yanjing Li , Junhe Zhao , Baochang Zhang , Guodong Guo

Figure 1 for POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
Figure 2 for POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
Figure 3 for POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
Figure 4 for POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
* Accepted by BMVC 2021. arXiv admin note: text overlap with arXiv:2010.05501 by other authors 
   Access Paper or Ask Questions

An adaptive recursive sliding mode attitude control for tiltrotor UAV in flight mode transition based on super-twisting extended state observer



Mengshan Xie , Sheng Xu , Cheng-yue Su , Zu-yong Feng , Yuandian Chen , Zhenhua Shi , Jiebo Lian

Figure 1 for An adaptive recursive sliding mode attitude control for tiltrotor UAV in flight mode transition based on super-twisting extended state observer
Figure 2 for An adaptive recursive sliding mode attitude control for tiltrotor UAV in flight mode transition based on super-twisting extended state observer
Figure 3 for An adaptive recursive sliding mode attitude control for tiltrotor UAV in flight mode transition based on super-twisting extended state observer
Figure 4 for An adaptive recursive sliding mode attitude control for tiltrotor UAV in flight mode transition based on super-twisting extended state observer
* 24 pages, 16 figures 
   Access Paper or Ask Questions

Collage: Automated Integration of Deep Learning Backends



Byungsoo Jeon , Sunghyun Park , Peiyuan Liao , Sheng Xu , Tianqi Chen , Zhihao Jia

Figure 1 for Collage: Automated Integration of Deep Learning Backends
Figure 2 for Collage: Automated Integration of Deep Learning Backends
Figure 3 for Collage: Automated Integration of Deep Learning Backends
Figure 4 for Collage: Automated Integration of Deep Learning Backends

   Access Paper or Ask Questions

End-to-end Ultrasound Frame to Volume Registration



Hengtao Guo , Xuanang Xu , Sheng Xu , Bradford J. Wood , Pingkun Yan

Figure 1 for End-to-end Ultrasound Frame to Volume Registration
Figure 2 for End-to-end Ultrasound Frame to Volume Registration
Figure 3 for End-to-end Ultrasound Frame to Volume Registration
Figure 4 for End-to-end Ultrasound Frame to Volume Registration
* Early accepted by MICCAI-2021 
   Access Paper or Ask Questions

Cross-modal Attention for MRI and Ultrasound Volume Registration



Xinrui Song , Hengtao Guo , Xuanang Xu , Hanqing Chao , Sheng Xu , Baris Turkbey , Bradford J. Wood , Ge Wang , Pingkun Yan

Figure 1 for Cross-modal Attention for MRI and Ultrasound Volume Registration
Figure 2 for Cross-modal Attention for MRI and Ultrasound Volume Registration
Figure 3 for Cross-modal Attention for MRI and Ultrasound Volume Registration
Figure 4 for Cross-modal Attention for MRI and Ultrasound Volume Registration
* This paper has been accepted by MICCAI 2021 
   Access Paper or Ask Questions
1
2
3
>>